From 10b7406c364b16ee01a5dcdbadacb6a1d960e450 Mon Sep 17 00:00:00 2001 From: Jason Desrosiers Date: Fri, 28 Jul 2023 12:06:53 -0700 Subject: [PATCH 01/11] Convert core/validation specs to non-IETF markdown --- .gitignore | 3 + README.md | 76 +- build/build.js | 114 + build/remark-number-headings.js | 35 + jsonschema-core.md | 3317 +++++++++++++++++++++++ jsonschema-core.xml | 4406 ------------------------------- jsonschema-validation.md | 1046 ++++++++ jsonschema-validation.xml | 1492 ----------- package.json | 33 + 9 files changed, 4601 insertions(+), 5921 deletions(-) create mode 100644 build/build.js create mode 100644 build/remark-number-headings.js create mode 100644 jsonschema-core.md delete mode 100644 jsonschema-core.xml create mode 100644 jsonschema-validation.md delete mode 100644 jsonschema-validation.xml create mode 100644 package.json diff --git a/.gitignore b/.gitignore index f375fa6e..dc05e9da 100644 --- a/.gitignore +++ b/.gitignore @@ -7,3 +7,6 @@ relative-json-pointer.txt # For the Python enviornment .venv + +package-lock.json +node_modules/ diff --git a/README.md b/README.md index 58007547..73a6da2d 100644 --- a/README.md +++ b/README.md @@ -22,29 +22,59 @@ For the current status of issues and pull requests, please see the following lab Labels are assigned based on [Sensible Github Labels](https://github.com/Relequestual/sensible-github-labels). -## Contents - -* Makefile - scripts to build the Internet-Draft txt/html -* _Internet-Draft sources_ - * jsonschema-core.xml - source for JSON Schema's "core" I-D - * jsonschema-validation.xml - source for the validation vocabulary I-D - * relative-json-pointer.xml - source for the Relative JSON Pointer I-D -* _meta-schemas and recommended output formats_ - * schema.json - JSON Schema "core" and Validation meta-schema - -The Makefile will create the necessary Python venv for you as part of the regular make target. - -`make clean` will remove all output including the venv. To clean just the spec output and -keep the venv, use `make spec-clean`. - -If you want to run `xml2rfc` manually after running make for the first time, you will -need to activate the virtual environment: - -```sh -source .venv/bin/activate -``` - -The version of "xml2rfc" that this project uses is updated by modifying `requirements.in` and running `pip-compile requirements.in`. +## Authoring and Building + +### Specification +To build the spec files to HTML from the Markdown sources, run `npm run build`. +You can also build each individually with `npm run build-core` and `npm run +build-validation`. + +The spec is built using [Remark](https://remark.js.org/), a markdown engine with +good support for plugins and lots of existing plugins we can use. + +#### Plugins +The following is a not-necessarily-complete list of configured plugins and the +features they make available to you. + +- [remark-lint](https://github.com/remarkjs/remark-lint) -- Enforce markdown + styles guide. +- [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-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 + `warning`, `note`, and `experimental`. + + ``` + ::: {type} {title} + {content} + ::: + ``` + +### Internet-Drafts +To build components that are being maintained as IETF Internet-Drafts, run +`make`. The Makefile will create the necessary Python venv for you as part of +the regular make target. + +`make clean` will remove all output including the venv. To clean just the spec +output and keep the venv, use `make spec-clean`. + +If you want to run `xml2rfc` manually after running make for the first time, you +will need to activate the virtual environment: `source .venv/bin/activate`. + +The version of "xml2rfc" that this project uses is updated by modifying +`requirements.in` and running `pip-compile requirements.in`. Descriptions of the xml2rfc, I-D documents, and RFC processes: diff --git a/build/build.js b/build/build.js new file mode 100644 index 00000000..403d7660 --- /dev/null +++ b/build/build.js @@ -0,0 +1,114 @@ +/* eslint-disable no-console */ +import dotenv from "dotenv"; +import { readFileSync, writeFileSync } from "node:fs"; +import { reporter } from "vfile-reporter"; +import { remark } from "remark"; +import remarkPresetLintMarkdownStyleGuide from "remark-preset-lint-markdown-style-guide"; +import remarkGfm from "remark-gfm"; +import remarkToc from "remark-toc"; +import torchLight from "remark-torchlight"; +import remarkRehype from "remark-rehype"; +import rehypeSlug from "rehype-slug"; +import rehypeAutolinkHeadings from "rehype-autolink-headings"; +import rehypeStringify from "rehype-stringify"; +import remarkNumberHeadings from "./remark-number-headings.js"; +import remarkFlexibleContainers from "remark-flexible-containers"; + + +dotenv.config(); + +(async function () { + const md = readFileSync(0, "utf-8"); + const html = await remark() + .use(remarkPresetLintMarkdownStyleGuide) + .use(remarkGfm) + .use(remarkNumberHeadings, { startDepth: 2, skip: ["Abstract", "Note to Readers", "Table of Contents"] }) + .use(remarkToc, { tight: true, heading: "Table of Contents" }) + .use(torchLight) + .use(remarkFlexibleContainers) + .use(remarkRehype) + .use(rehypeSlug) + .use(rehypeAutolinkHeadings, { behavior: "wrap" }) + .use(rehypeStringify) + .process(md); + + writeFileSync(1, ` + + + + + + + + + ${String(html)} + +`); + + console.error(reporter(html)); +}()); diff --git a/build/remark-number-headings.js b/build/remark-number-headings.js new file mode 100644 index 00000000..8517e042 --- /dev/null +++ b/build/remark-number-headings.js @@ -0,0 +1,35 @@ +import { visit } from "unist-util-visit"; + + +const defaultOptions = { + startDepth: 1, + skip: [] +}; + +const remarkNumberHeadings = (options) => (tree) => { + options = { ...defaultOptions, ...options }; + + let sectionNumbers = []; + + visit(tree, "heading", (node) => { + if (node.depth < options.startDepth) { + return; + } + + visit(node, "text", (textNode) => { + const text = textNode.value ? textNode.value.trim() : ""; + + if (options.skip.includes(text)) { + return; + } + + sectionNumbers[node.depth] = (sectionNumbers[node.depth] ?? 0) + 1; + sectionNumbers = sectionNumbers.slice(0, node.depth + 1); + + const sectionNumber = sectionNumbers.slice(options.startDepth, node.depth + 1).join("."); + textNode.value = `${sectionNumber}. ${text}`; + }); + }); +}; + +export default remarkNumberHeadings; diff --git a/jsonschema-core.md b/jsonschema-core.md new file mode 100644 index 00000000..09ee2bcb --- /dev/null +++ b/jsonschema-core.md @@ -0,0 +1,3317 @@ +# 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 +interact with it. The `application/schema-instance+json` media type provides +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 +. + +For additional information, see . + +To provide feedback, use this issue tracker, the communication methods listed on +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. + +This specification defines JSON Schema core terminology and mechanisms, +including pointing to another JSON Schema by reference, dereferencing a JSON +Schema reference, specifying the dialect being used, specifying a dialect's +vocabulary requirements, and defining the expected output. + +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). + +The terms "JSON", "JSON text", "JSON value", "member", "element", "object", +"array", "number", "string", "boolean", "true", "false", and "null" in this +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 +features. JSON Schemas are themselves JSON documents. This, and related +specifications, define keywords allowing authors to describe JSON data in +several ways. + +JSON Schema uses keywords to assert constraints on JSON instances or annotate +those instances with additional information. Additional keywords are used to +apply assertions and annotations to more complex JSON data structures, or based +on some sort of condition. + +To facilitate re-use, keywords can be organized into vocabularies. A vocabulary +consists of a list of keywords, together with their syntax and semantics. A +dialect is defined as a set of vocabularies and their required support +identified in a meta-schema. + +JSON Schema can be extended either by defining additional vocabularies, or less +formally by defining additional keywords outside of any vocabulary. Unrecognized +individual keywords simply have their values collected as annotations, while the +behavior with respect to an unrecognized vocabulary can be controlled when +declaring which vocabularies are in use. + +This document defines a core vocabulary that MUST be supported by any +implementation, and cannot be disabled. Its keywords are each prefixed with a +"$" character to emphasize their required nature. This vocabulary is essential +to the functioning of the `application/schema+json` media type, and is used to +bootstrap the loading of other vocabularies. + +Additionally, this document defines a RECOMMENDED vocabulary of keywords for +applying subschemas conditionally, and for applying subschemas to the contents +of objects and arrays. Either this vocabulary or one very much like it is +required to write schemas for non-trivial JSON instances, whether those schemas +are intended for assertion validation, annotation, or both. While not part of +the required core vocabulary, for maximum interoperability this additional +vocabulary is included in this document and its use is strongly encouraged. + +Further vocabularies for purposes such as structural validation or hypermedia +annotation are defined in other documents. These other documents each define a +dialect collecting the standard sets of vocabularies needed to write schemas for +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 +[Section 4.2.1](#421-instance-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 +model can be interpreted against a JSON Schema, including media types like +[CBOR](#rfc7049). + +### Instance + +A JSON document to which a schema is applied is known as an "instance". + +JSON Schema is defined over `application/json` or compatible documents, +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 + +JSON Schema interprets documents according to a data model. A JSON value +interpreted according to this data model is called an "instance". + +An instance has one of six primitive types, and a range of possible values +depending on the type: + +null: A JSON "null" value + +boolean: A "true" or "false" value, from the JSON "true" or "false" value + +object: An unordered set of properties mapping a string to an instance, from the +JSON "object" value + +array: An ordered list of instances, from the JSON "array" value + +number: An arbitrary-precision, base-10 decimal number value, from the JSON +"number" value + +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. + +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. + +#### 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: + +- both are null; or +- both are true; or +- both are false; or +- 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. + +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 +no way to define multiple properties with the same key, and mere formatting +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. + +In this case, annotations still apply; but most validation keywords will not be +useful, as they will always pass or always fail. + +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 +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 +`application/schema-instance+json`. The `application/schema+json` media type is +defined to offer a superset of the fragment identifier syntax and semantics +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: + +identifiers: control schema identification through setting a IRI for the schema +and/or changing how the base IRI is determined + +assertions: produce a boolean result when applied to an instance + +annotations: attach information to an instance for application use + +applicators: apply one or more subschemas to a particular location in the +instance, and combine or modify their results + +reserved locations: do not directly affect results, but reserve a place for a +specific purpose to ensure interoperability + +Keywords may fall into multiple categories, although applicators SHOULD only +produce assertion results based on their subschemas' results. They should not +define additional constraints independent of their subschemas. + +Keywords which are properties within the same schema object are referred to as +adjacent keywords. + +Extension keywords, meaning those defined outside of this document and its +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 +[Section 6.5.2](#652-handling-of-unrecognized-or-unsupported-keywords). + +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). + +`true`: Always passes validation, as if the empty schema `{}` + +`false`: Always fails validation, as if the schema `{ "not": {} }` + +While the empty schema object is unambiguous, there are many possible +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 +interface generation, will involve different sets of vocabularies. + +Vocabularies are the primary unit of re-use in JSON Schema, as schema authors +can indicate what vocabularies are required or optional in order to process the +schema. Since vocabularies are identified by IRIs in the meta-schema, generic +implementations can load extensions to support previously unknown vocabularies. +While keywords can be supported outside of any vocabulary, there is no analogous +mechanism to indicate individual keyword usage. + +A schema vocabulary can be defined by anything from an informal description to a +standards proposal, depending on the audience and interoperability expectations. +In particular, in order to facilitate vocabulary use within non-public +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. + +Typically, a meta-schema will specify a set of vocabularies, and validate +schemas that conform to the syntax of those vocabularies. However, meta-schemas +and vocabularies are separate in order to allow meta-schemas to validate schema +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 +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 +by [section 3.5 of RFC 3986](#rfc3986)) is identical to the primary resource. +This can occur with the empty fragment, or when one schema resource is embedded +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 [Section 9.1.1](#911-initial-base-iri).[^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 +Schema document and resource concepts will be clarified in a future draft. + +Some keywords take schemas themselves, allowing JSON Schemas to be nested: + +```json +{ + "title": "root", + "items": { + "title": "array item" + } +} +``` + +In this example document, the schema titled "array item" is a subschema, and the +schema titled "root" is the root schema. + +As with the root schema, a subschema is either an object or a boolean. + +As discussed in [Section 8.2.1](#821-the-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 +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 +fragment identification syntax defined for `application/json`.) + +Additionally, the `application/schema+json` media type supports two fragment +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 +identifier syntaxes, fragment identifiers matching the JSON Pointer syntax, +including the empty string, MUST be interpreted as JSON Pointer fragment +identifiers. + +Per the W3C's [best practices for fragment +identifiers](#w3cwd-fragid-best-practices-20121025), plain name fragment +identifiers in `application/schema+json` are reserved for referencing locally +named schemas. + +Plain name fragments MUST start with a letter ([A-Za-z]) or underscore ("\_"), +followed by any number of letters, digits ([0-9]), hyphens ("-"), underscores +("\_"), and periods ("."). This matches the US-ASCII part of XML's [NCName +production](#xml-names), which allows for compatibility with the recommended +plain name [syntax](#w3crec-xptr-framework-20030325) for XML-based media types. + +All fragment identifiers that do not match the JSON Pointer syntax MUST be +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. + +## 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 +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 +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 +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, +section 21.2.1](#ecma262). + +Unless otherwise specified by a keyword, regular expressions MUST NOT be +considered to be implicitly anchored at either end. All regular expression +keywords in this specification and its companion documents are un-anchored. + +Regular expressions SHOULD be built with the "u" flag (or equivalent) to provide +Unicode support, or processed in such a way which provides Unicode support as +defined by ECMA-262. + +Furthermore, given the high disparity in regular expression constructs support, +schema authors SHOULD limit themselves to the following regular expression +tokens: + +- individual Unicode characters, as defined by the [JSON +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 ("+?", "*?", "??"); +- range quantifiers: "{x}" (exactly x occurrences), "{x,y}" (at least x, at most +y, occurrences), {x,} (x occurrences or more), and their lazy versions; +- the beginning-of-input ("^") and end-of-input ("$") anchors; +- simple grouping ("(...)") and alternation ("|"). + +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 +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 +explicitly document such support. + +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 +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 +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 +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 +fit. Applicators apply subschemas to parts of the instance and combine their +results. + +Extension keywords SHOULD stay within these categories, keeping in mind that +annotations in particular are extremely flexible. Complex behavior is usually +better delegated to applications on the basis of annotation data than +implemented directly as schema keywords. However, extension keywords MAY define +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. +The interactions of those keyword results to produce the schema object results +are governed by [Section 7.7.1.2](#7712-annotations-and-assertions), while the +relationship of subschema results to the results of the applicator keyword that +applied them is described by [Section 7.5](#75-applicators). + +Evaluation of a parent schema object can complete once all of its subschemas +have been evaluated, although in some circumstances evaluation may be +short-circuited due to assertion results. When annotations are being collected, +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 + +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. + +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 +IRI, which is found through the lexical structure of the JSON document. The +`$id`, `$ref`, and `$dynamicRef` core keywords, and the "base" JSON Hyper-Schema +keyword, are examples of this sort of behavior. + +Note that some keywords, such as `$schema`, apply to the lexical scope of the +entire schema resource, and therefore MUST only appear in a schema resource's +root schema. + +Other keywords may take into account the dynamic scope that exists during the +evaluation of a schema, typically together with an instance document. The +outermost dynamic scope is the schema object at which processing begins, even if +it is not a schema resource root. The path from this root schema to any +particular keyword (that includes any `$ref` and `$dynamicRef` keywords that may +have been resolved) is considered the keyword's "evaluation path." + +Lexical and dynamic scopes align until a reference keyword is encountered. While +following the reference keyword moves processing from one lexical scope into a +different one, from the perspective of dynamic scope, following a reference is +no different from descending into a subschema present as a value. A keyword on +the far side of that reference that resolves information through the dynamic +scope will consider the originating side of the reference to be their dynamic +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. + +### 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). + +### 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 +contribute annotations, the lack of annotation results may indirectly change the +behavior of other keywords. + +In some cases, the missing keyword assertion behavior of a keyword is identical +to that produced by a certain value, and keyword definitions SHOULD note such +values where known. However, even if the value which produces the default +behavior would produce annotation results if present, the default behavior still +MUST NOT result in annotations. + +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. + +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 `$id`. + +Canonical schema IRIs MUST NOT change while processing an instance, but keywords +that affect IRI-reference resolution MAY have behavior that is only fully +determined at runtime. + +While custom identifier keywords are possible, vocabulary designers should take +care not to disrupt the functioning of core keywords. For example, the +`$dynamicAnchor` keyword in this specification limits its IRI resolution effects +to the matching `$dynamicRef` keyword, leaving the behavior of `$ref` +undisturbed. + +### 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. + +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 +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 +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 [Section 7.7.1](#771-collecting-annotations) 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 +As noted in [Section 7.5](#75-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 +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. + +### 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. + +JSON Schema implementations produce a single boolean result when evaluating an +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. + +For example, the `maxLength` keyword from the companion [validation +vocabulary](#json-schema-validation): will only restrict certain strings (that +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 +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: + +```json +{ + "type": ["string", "null"], + "maxLength": 255 +} +``` + +If `maxLength` also restricted the instance type to be a string, then this would +be substantially more cumbersome to express because the example as written would +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 +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 +calculated based on the instance contents. + +Annotations are attached to specific locations in an instance. Since many +subschemas can be applied to any single location, applications may need to +decide how to handle differing annotation values being attached to the same +instance location by the same schema keyword in different schema objects. + +Unlike assertion results, annotation data can take a wide variety of forms, +which are provided to applications to use as they see fit. JSON Schema +implementations are not expected to make use of the collected information on +behalf of applications. + +Unless otherwise specified, the value of an annotation keyword is the keyword's +value. However, other behaviors are possible. For example, [JSON +Hyper-Schema's](#json-hyper-schema) `links` keyword is a complex annotation that +produces a value based in part on the instance data. + +While "short-circuit" evaluation is possible for assertions, collecting +annotations requires examining all schemas that apply to an instance location, +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 +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. + +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. +- 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. +- 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. + +For example, consider this schema, which uses annotations and assertions from +the [Validation specification](#json-schema-validation): + +Note that some lines are wrapped for clarity. + +```json +{ + "title": "Feature list", + "type": "array", + "prefixItems": [ + { + "title": "Feature A", + "properties": { + "enabled": { + "$ref": "#/$defs/enabledToggle", + "default": true + } + } + }, + { + "title": "Feature B", + "properties": { + "enabled": { + "description": "If set to null, Feature B + inherits the enabled + value from Feature A", + "$ref": "#/$defs/enabledToggle" + } + } + } + ], + "$defs": { + "enabledToggle": { + "title": "Enabled", + "description": "Whether the feature is enabled (true), + disabled (false), or under + automatic control (null)", + "type": ["boolean", "null"], + "default": null + } + } +} +``` + +In this example, both Feature A and Feature B make use of the re-usable +"enabledToggle" schema. That schema uses the `title`, `description`, and +`default` annotations. Therefore the application has to decide how to handle +the additional `default` value for Feature A, and the additional `description` +value for Feature B. + +The application programmer and the schema author need to agree on the usage. For +this example, let's assume that they agree that the most specific `default` +value will be used, and any additional, more generic `default` values will be +silently ignored. Let's also assume that they agree that all `description` text +is to be used, starting with the most generic, and ending with the most +specific. This requires the schema author to write descriptions that work when +combined in this way. + +The application can use the evaluation path to determine which values are which. +The values in the feature's immediate "enabled" property schema are more +specific, while the values under the re-usable schema that is referenced to with +`$ref` are more generic. The evaluation path will show whether each value was +found by crossing a `$ref` or not. + +Feature A will therefore use a default value of true, while Feature B will use +the generic default value of null. Feature A will only have the generic +description from the "enabledToggle" schema, while Feature B will use that +description, and also append its locally defined description that explains how +to interpret a null value. + +Note that there are other reasonable approaches that a different application +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 +Schema objects that produce a false assertion result MUST NOT produce any +annotation results, whether from their own keywords or from keywords in +subschemas. + +Note that the overall schema results may still include annotations collected +from other schema locations. Given this schema: + +```json +{ + "oneOf": [ + { + "title": "Integer Value", + "type": "integer" + }, + { + "title": "String Value", + "type": "string" + } + ] +} +``` + +Against the instance `"This is a string"`, the title annotation "Integer Value" +is discarded because the type assertion in that schema object fails. The title +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 +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 [Section +9.4.2](#942-references-to-possible-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. + +Keywords MAY be defined to use JSON Pointers or Relative JSON Pointers to +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 +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 +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 +[`$vocabulary`](#81-meta-schemas-and-vocabularies) keyword to declare the +vocabularies in use MUST explicitly list the Core vocabulary, which MUST have a +value of true indicating that it is required. + +The behavior of a false value for this vocabulary (and only this vocabulary) is +undefined, as is the behavior when `$vocabulary` is present but the Core +vocabulary is not included. However, it is RECOMMENDED that implementations +detect these cases and raise an error when they occur. It is not meaningful to +declare that a meta-schema optionally uses Core. + +Meta-schemas that do not use `$vocabulary` MUST be considered to require the +Core vocabulary as if its IRI were present with a value of true. + +The current IRI for the Core vocabulary is: +`https://json-schema.org/draft/next/vocab/core`. + +The current IRI for the corresponding meta-schema is: +`https://json-schema.org/draft/next/meta/core`. + +The "$" prefix is reserved for use by the Core vocabulary. Vocabulary extensions +MUST NOT define new keywords that begin with "$". + +### Meta-Schemas and Vocabularies +Two concepts, meta-schemas and vocabularies, are used to inform an +implementation how to interpret a schema. Every schema has a meta-schema, which +can be declared using the `$schema` keyword. + +The meta-schema serves two purposes: + +Declaring the vocabularies in use: The `$vocabulary` keyword, when it appears in +a meta-schema, declares which vocabularies are available to be used in schemas +that refer to that meta-schema. Vocabularies define keyword semantics, as well +as their general syntax. + +Describing valid schema syntax: A schema MUST successfully validate against its +meta-schema, which constrains the syntax of the available keywords. The syntax +described is expected to be compatible with the vocabularies declared; while it +is possible to describe an incompatible syntax, such a meta-schema would be +unlikely to be useful. + +Meta-schemas are separate from vocabularies to allow for vocabularies to be +combined in different ways, and for meta-schema authors to impose additional +constraints such as forbidding certain keywords, or performing unusually strict +syntactical validation, as might be done during a development and testing cycle. +Each vocabulary typically identifies a meta-schema consisting only of the +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 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. + +The value of this keyword MUST be a [IRI](#rfc3987) (containing a scheme) and +this IRI MUST be normalized. The current schema MUST be valid against the +meta-schema identified by this IRI. + +If this IRI identifies a retrievable resource, that resource SHOULD be of media +type `application/schema+json`. + +The `$schema` keyword SHOULD be used in the document root schema object, and MAY +be used in the root schema objects of embedded schema resources. It MUST NOT +appear in non-resource root schema objects. If absent from the document root +schema, the resulting behavior is implementation-defined, but MUST fall within +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 + +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. + +The value of this keyword MUST be an object. The property names in the object +MUST be IRIs (containing a scheme) and each IRI MUST be normalized. Each IRI +that appears as a property name identifies a specific set of keywords and their +semantics. + +The IRI MAY be a URL, but the nature of the retrievable resource is currently +undefined, and reserved for future use. Vocabulary authors MAY use the URL of +the vocabulary specification, in a human-readable media type such as `text/html` +or `text/plain`, as the vocabulary IRI.[^2] + +[^2]: Vocabulary documents may be added in forthcoming drafts. For now, +identifying the keyword set is deemed sufficient as that, along with meta-schema +validation, is how the current "vocabularies" work today. Any future vocabulary +document format will be specified as a JSON document, so using `text/html` or +other non-JSON formats in the meantime will not produce any future ambiguity. + +The values of the object properties MUST be booleans. If the value is true, then +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 +`$vocabulary`, the set of vocabularies in use is determined according to +[Section 8.1.2.4](#8124-default-vocabularies). + +Any vocabulary in use by a schema and understood by the implementation MUST be +processed in a manner consistent with the semantic definitions contained within +the vocabulary, regardless of whether that vocabulary is required or optional. + +Any vocabulary that is not present in `$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 [Section +8](#8-the-json-schema-core-vocabulary). + +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 [Section +6.5.2](#652-handling-of-unrecognized-or-unsupported-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. + +##### Vocabularies are schema resource-scoped +The `$vocabulary` keyword SHOULD be used in the root schema of any schema +resource intended for use as a meta-schema. It MUST NOT appear in subschemas. + +The `$vocabulary` keyword MUST be ignored in schema resources that are not being +processed as a meta-schema. This allows validating a meta-schema M against its +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 +`$vocabulary`. + +In particular the keywords defined in this specification and its companion +documents MUST be considered to be vocabulary keywords, with availability +governed by `$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). + +##### 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 +recognized prior to the existence of vocabularies. + +If the meta-schema, as referenced by the schema, is not recognized, or is +missing, then the behavior is implementation-defined. If the implementation +proceeds with processing the schema, it MUST assume the use of the core +vocabulary. If the implementation is built for a specific purpose, then it +SHOULD assume the use of all of the most relevant vocabularies for that purpose. + +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] + +[^3]: This requirement allows implementations to find all vocabulary requirement +information in a single place for each meta-schema. As schema extensibility +means that there are endless potential ways to combine more fine-grained +meta-schemas by reference, requiring implementations to anticipate all +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. + +Several keywords can accept a relative [IRI-reference](#rfc3987), or a value +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 $id Keyword +The `$id` keyword identifies a schema resource with its [canonical](#rfc6596) +IRI. + +Note that this IRI is an identifier and not necessarily a network locator. In +the case of a network-addressable URL, a schema need not be downloadable from +its canonical IRI. + +If present, the value for this keyword MUST be a string, and MUST represent a +valid [IRI-reference](#rfc3987). This IRI-reference SHOULD be normalized, and +MUST resolve to an [absolute-IRI](#rfc3987) (without a fragment). + +The resulting absolute-IRI serves as the base IRI for relative IRI-references in +keywords within the schema resource, in accordance with [RFC 3987 section +6.5](#rfc3987) and [RFC 3986 section 5.1.1](#rfc3986) regarding base IRIs +embedded in content. + +The presence of `$id` in a subschema indicates that the subschema constitutes a +distinct schema resource within a single schema document. Furthermore, in +accordance with [RFC 3987 section 6.5](#rfc3987) and [RFC 3986 section +5.1.2](#rfc3986) regarding encapsulating entities, if an `$id` in a subschema is +a relative IRI-reference, the base IRI for resolving that reference is the IRI +of the parent schema resource. Note that an `$id` consisting of an empty IRI or +of the empty fragment only will result in the embedded resource having the same +IRI as the encapsulating resource, which SHOULD be considered an error per +[Section 8.2.3](#823-duplicate-schema-identifiers). + +If no parent schema object explicitly identifies itself as a resource with +`$id`, the base IRI is that of the entire document, as established by the steps +given in the [previous section.](#911-initial-base-iri) + +##### Identifying the root schema +The root schema of a JSON Schema document SHOULD contain an `$id` keyword with +an [absolute-IRI](#rfc3987) (containing a scheme, but no fragment). + +#### Defining location-independent identifiers +Using JSON Pointer fragments requires knowledge of the structure of the schema. +When writing schema documents with the intention to provide re-usable schemas, +it may be preferable to use a plain name fragment that is not tied to any +particular structural location. This allows a subschema to be relocated without +requiring JSON Pointer references to be updated. + +The `$anchor` and `$dynamicAnchor` keywords are used to specify such fragments. +They are identifier keywords that can only be used to create plain name +fragments, rather than absolute IRIs as seen with `$id`. + +The base IRI to which the resulting fragment is appended is the canonical IRI of +the schema resource containing the `$anchor` or `$dynamicAnchor` in question. +As discussed in the previous section, this is either the nearest `$id` in the +same or parent schema object, or the base IRI for the document as determined +according to [RFC 3987](#rfc3987) and [RFC 3986](#rfc3986). + +Separately from the usual usage of IRIs, `$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. + +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 [Section +5](#5-fragment-identifiers).[^4] + +[^4]: Note that the anchor string does not include the "#" character, as it is +not a IRI-reference. An `$anchor`: "foo" becomes the fragment `#foo` when used +in a IRI. See below for full examples. + +#### Duplicate schema identifiers +A schema MAY (and likely will) have multiple IRIs, but there is no way for an +IRI to identify more than one schema. When multiple schemas attempt to identify +as the same IRI through the use of `$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. + +As the values of `$ref` and `$dynamicRef` are IRI References, this allows the +possibility to externalise or divide a schema across multiple files, and +provides the ability to validate recursive structures through self-reference. + +The resolved IRI produced by these keywords is not necessarily a network +locator, only an identifier. A schema need not be downloadable from the address +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 $ref +The `$ref` keyword is an applicator that is used to reference a statically +identified schema. Its results are the results of the referenced schema.[^5] + +[^5]: Note that this definition of how the results are determined means that +other keywords can appear alongside of `$ref` in the same schema object. + +The value of the `$ref` keyword MUST be a string which is a IRI-Reference. +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 $dynamicRef +The `$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. + +Together with `$dynamicAnchor`, `$dynamicRef` implements a cooperative extension +mechanism that is primarily useful with recursive schemas (schemas that +reference themselves). The extension point is defined with `$dynamicAnchor` and +only exhibits runtime dynamic behavior when referenced with `$dynamicRef`. + +The value of the `$dynamicRef` property MUST be a string which is a +IRI-Reference that contains a valid [plain name +fragment](#822-defining-location-independent-identifiers). Resolved against the +current IRI base, it indicates the schema resource used as the starting point +for runtime resolution. This initial resolution is safe to perform on schema +load. + +The schema to apply is the outermost schema resource in the [dynamic +scope](#71-lexical-scope-and-dynamic-scope) that defines a `$dynamicAnchor` that +matches the plain name fragment in the initially resolved IRI. + +For a full example using these keyword, see [Appendix +C](#appendix-c-example-of-recursive-schema-extension).[^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 $defs +The `$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. + +This keyword's value MUST be an object. Each member value of this object MUST be +a valid JSON Schema. + +As an example, here is a schema describing an array of positive integers, where +the positive integer constraint is a subschema in `$defs`: + +```json +{ + "type": "array", + "items": { "$ref": "#/$defs/positiveInteger" }, + "$defs": { + "positiveInteger": { + "type": "integer", + "exclusiveMinimum": 0 + } + } +} +``` + +### Comments With $comment +This keyword reserves a location for comments from schema authors to readers or +maintainers of the schema. + +The value of this keyword MUST be a string. Implementations MUST NOT present +this string to end users. Tools for editing schemas SHOULD support displaying +and editing this keyword. The value of this keyword MAY be used in debug or +error output which is intended for developers making use of schemas. + +Schema vocabularies SHOULD allow `$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. + +Tools that translate other media types or programming languages to and from +`application/schema+json` MAY choose to convert that media type or programming +language's native comments to or from `$comment` values. The behavior of such +translation when both native comments and `$comment` properties are present is +implementation-dependent. + +Implementations MAY strip `$comment` values at any point during processing. In +particular, this allows for shortening schemas when the size of deployed schemas +is a concern. + +Implementations MUST NOT take any other action based on the presence, absence, +or contents of `$comment` properties. In particular, the value of `$comment` +MUST NOT be collected as an annotation result. + +## Loading and Processing Schemas + +### Loading a Schema + +#### Initial Base IRI +[RFC 3987 Section 6.5](#rfc3987) and [RFC 3986 Section 5.1](#rfc3986) defines +how to determine the default base IRI of a document. + +Informatively, the initial base IRI of a schema is the IRI at which it was +found, whether that was a network location, a local filesystem, or any other +situation identifiable by a IRI of any known scheme. + +If a schema document defines no explicit base IRI with `$id` (embedded in +content), the base IRI is that determined per [RFC 3987 Section 6.5](#rfc3987) +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. + +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. + +Unless the `$id` keyword described in an earlier section is present in the root +schema, this base IRI SHOULD be considered the canonical IRI of the schema +document's root schema resource. + +#### Loading a referenced schema +The use of IRIs to identify remote schemas does not necessarily mean anything is +downloaded, but instead JSON Schema implementations SHOULD understand ahead of +time which schemas they will be using, and the IRIs that identify them. + +When schemas are downloaded, for example by a generic user-agent that does not +know until runtime which schemas to download, see [Usage for +Hypermedia](#951-usage-for-hypermedia). + +Implementations SHOULD be able to associate arbitrary IRIs with an arbitrary +schema and/or automatically associate a schema's `$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). + +#### 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 `$schema` keyword. This +means that a single schema document might sometimes be considered a regular +schema, and other times be considered a meta-schema. + +In the case of examining a schema which is its own meta-schema, when an +implementation begins processing it as a regular schema, it is processed under +those rules. However, when loaded a second time as a result of checking its own +`$schema` value, it is treated as a meta-schema. So the same document is +processed both ways in the course of one session. + +Implementations MAY allow a schema to be explicitly passed as a meta-schema, for +implementation-specific purposes, such as pre-loading a commonly used +meta-schema and checking its vocabulary support requirements up front. +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 +the current base IRI per [RFC 3986](#rfc3986). + +If the resulting IRI identifies a schema within the current document, or within +another schema document that has been made available to the implementation, then +that schema SHOULD be used automatically. + +For example, consider this schema: + +```json +{ + "$id": "https://example.net/root.json", + "type": "array", + "items": { "$ref": "#item" }, + "$defs": { + "single": { + "$anchor": "item", + "type": "object", + "additionalProperties": { "$ref": "other.json" } + } + } +} +``` + +When an implementation encounters the `#/$defs/single` schema, it resolves the +`$anchor` value as a fragment name against the current base IRI to form +`https://example.net/root.json#item`. + +When an implementation then looks inside the `#/items` schema, it encounters the +`#item` reference, and resolves this to `https://example.net/root.json#item`, +which it has seen defined in this same document and can therefore use +automatically. + +When an implementation encounters the reference to "other.json", it resolves +this to `https://example.net/other.json`, which is not defined in this document. +If a schema with that identifier has otherwise been supplied to the +implementation, it can also be used automatically.[^7] + +[^7]: What should implementations do when the referenced schema is not known? +Are there circumstances in which automatic network dereferencing is allowed? A +same origin policy? A user-configurable option? In the case of an evolving API +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 +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, +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. + +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 +document and referenced, applications and schemas SHOULD NOT use such IRIs to +identify embedded schema resources or locations within them. + +Consider the following schema document that contains another schema resource +embedded within it: + +```json +{ + "$id": "https://example.com/foo", + "items": { + "$id": "https://example.com/bar", + "additionalProperties": { } + } +} +``` + +The IRI `https://example.com/foo#/items` points to the `items` schema, which is +an embedded resource. The canonical IRI of that schema resource, however, is +`https://example.com/bar`. + +For the `additionalProperties` schema within that embedded resource, the IRI +`https://example.com/foo#/items/additionalProperties` points to the correct +object, but that object's IRI relative to its resource's canonical IRI is +`https://example.com/bar#/additionalProperties`. + +Now consider the following two schema resources linked by reference using a IRI +value for `$ref`: + +```json +{ + "$id": "https://example.com/foo", + "items": { + "$ref": "bar" + } +} +``` + +```json +{ + "$id": "https://example.com/bar", + "additionalProperties": { } +} +``` + +Here we see that `https://example.com/bar#/additionalProperties`, using a JSON +Pointer fragment appended to the canonical IRI of the "bar" schema resource, is +still valid, while `https://example.com/foo#/items/additionalProperties`, which +relied on a JSON Pointer fragment appended to the canonical IRI of the "foo" +schema resource, no longer resolves to anything. + +Note also that `https://example.com/foo#/items` is valid in both arrangements, +but resolves to a different value. This IRI ends up functioning similarly to a +retrieval IRI for a resource. While this IRI is valid, it is more robust to use +the `$id` of the embedded or referenced resource unless it is specifically +desired to identify the object containing the `$ref` in the second +(non-embedded) arrangement. + +An implementation MAY choose not to support addressing schema resource contents +by IRIs using a base other than the resource's canonical IRI, plus a JSON +Pointer fragment relative to that base. Therefore, schema authors SHOULD NOT +rely on such IRIs, as using them may reduce interoperability.[^8] + +[^8]: This is to avoid requiring implementations to keep track of a whole stack +of possible base IRIs and JSON Pointer fragments for each, given that all but +one will be fragile if the schema resources are reorganized. Some have argued +that this is easy so there is no point in forbidding it, while others have +argued that it complicates schema identification and should be forbidden. +Feedback on this topic is encouraged. After some discussion, we feel that we +need to remove the use of "canonical" in favour of talking about JSON Pointers +which reference across schema resource boundaries as undefined or even forbidden +behavior (, +) + +Further examples of such non-canonical IRI construction, as well as the +appropriate canonical IRI-based fragments to use instead, are provided in +[Appendix A](#appendix-a-schema-identification-examples). + +### Compound Documents +A Compound Schema Document is defined as a JSON document (sometimes called a +"bundled" schema) which has multiple embedded JSON Schema Resources bundled into +the same document to ease transportation. + +Each embedded Schema Resource MUST be treated as an individual Schema Resource, +following standard schema loading and processing requirements, including +determining vocabulary support. + +#### Bundling +The bundling process for creating a Compound Schema Document is defined as +taking references (such as `$ref`) to an external Schema Resource and embedding +the referenced Schema Resources within the referring document. Bundling SHOULD +be done in such a way that all IRIs (used for referencing) in the base document +and any referenced/embedded documents do not require altering. + +Each embedded JSON Schema Resource MUST identify itself with a IRI using the +`$id` keyword, and SHOULD make use of the `$schema` keyword to identify the +dialect it is using, in the root of the schema resource. It is RECOMMENDED that +the IRI identifier value of `$id` be an Absolute IRI. + +When the Schema Resource referenced by a by-reference applicator is bundled, it +is RECOMMENDED that the Schema Resource be located as a value of a `$defs` +object at the containing schema's root. The key of the `$defs` for the now +embedded Schema Resource MAY be the `$id` of the bundled schema or some other +form of application defined unique identifer (such as a UUID). This key is not +intended to be referenced in JSON Schema, but may be used by an application to +aid the bundling process. + +A Schema Resource MAY be embedded in a location other than `$defs` where the +location is defined as a schema value. + +A Bundled Schema Resource MUST NOT be bundled by replacing the schema object +from which it was referenced, or by wrapping the Schema Resource in other +applicator keywords. + +In order to produce identical output, references in the containing schema +document to the previously external Schema Resources MUST NOT be changed, and +now resolve to a schema using the `$id` of an embedded Schema Resource. Such +identical output includes validation evaluation and IRIs or paths used in +resulting annotations or errors. + +While the bundling process will often be the main method for creating a Compound +Schema Document, it is also possible and expected that some will be created by +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. + +Since any schema that can be referenced can also be embedded, embedded schema +resources MAY specify different processing dialects using the `$schema` values +from their enclosing resource. + +#### Validating +Given that a Compound Schema Document may have embedded resources which identify +as using different dialects, these documents SHOULD NOT be validated by applying +a meta-schema to the Compound Schema Document as an instance. It is RECOMMENDED +that an alternate validation process be provided in order to validate Schema +Documents. Each Schema Resource SHOULD be separately validated against its +associated meta-schema.[^9] + +[^9]: If you know a schema is what's being validated, you can identify if the +schemas is a Compound Schema Document or not, by way of use of `$id`, which +identifies an embedded resource when used not at the document's root. + +A Compound Schema Document in which all embedded resources identify as using the +same dialect, or in which `$schema` is omitted and therefore defaults to that of +the enclosing resource, MAY be validated by applying the appropriate +meta-schema. + +### Caveats + +#### Guarding Against Infinite Recursion +A schema MUST NOT be run into an infinite loop against an instance. For example, +if two schemas `#alice` and `#bob` both have an `allOf` property that refers to +the other, a naive validator might get stuck in an infinite recursive loop +trying to validate the instance. Schemas SHOULD NOT make use of infinite +recursive nesting like this; the behavior is undefined. + +#### References to Possible Non-Schemas +Subschema objects (or booleans) are recognized by their use with known +applicator keywords or with location-reserving keywords such as +[`$defs`](#825-schema-re-use-with-defs) that take one or more subschemas as a +value. These keywords may be `$defs` and the standard applicators from this +document, or extension keywords from a known vocabulary, or +implementation-specific custom keywords. + +Multi-level structures of unknown keywords are capable of introducing nested +subschemas, which would be subject to the processing rules for `$id`. Therefore, +having a reference target in such an unrecognized structure cannot be reliably +implemented, and the resulting behavior is undefined. Similarly, a reference +target under a known keyword, for which the value is known not to be a schema, +results in undefined behavior in order to avoid burdening implementations with +the need to detect such targets.[^10] + +[^10]: These scenarios are analogous to fetching a schema over HTTP but +receiving a response with a Content-Type other than `application/schema+json`. +An implementation can certainly try to interpret it as a schema, but the origin +server offered no guarantee that it actually is any such thing. Therefore, +interpreting it as such has security implication and may produce unpredictable +results. + +Note that single-level custom keywords with identical syntax and semantics to +`$defs` do not allow for any intervening `$id` keywords, and therefore will +behave correctly under implementations that attempt to use any reference target +as a schema. However, this behavior is implementation-specific and MUST NOT be +relied upon for interoperability. + +### Associating Instances and Schemas + +#### Usage for 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). + +In HTTP, such links can be attached to any response using the [Link +header](#rfc8288). An example of such a header would be: + +``` +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 +frequently than necessary, when it's instead possible to cache a schema for a +long period of time. + +HTTP servers SHOULD set long-lived caching headers on JSON Schemas. HTTP clients +SHOULD observe caching headers and not re-request documents within their +freshness period. Distributed systems SHOULD make use of a shared cache and/or +caching proxy. + +Clients SHOULD set or prepend a User-Agent header specific to the JSON Schema +implementation or software product. Since symbols are listed in decreasing order +of significance, the JSON Schema library name/version should precede the more +generic HTTP library name (if any). For example: + +``` +User-Agent: product-name/5.4.1 so-cool-json-schema/1.0.2 curl/7.43.0 +``` + +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. + +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. + +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`. + +### Keyword Independence +Schema keywords typically operate independently, without affecting each other's +outcomes. + +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` +- `items`, whose behavior is defined in terms of `prefixItems` +- `contains`, whose behavior is affected by the presence and value of +`minContains` + +### 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. + +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 +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 +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 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. + +An instance validates successfully against this keyword if it validates +successfully against at least one schema defined by this keyword's value. Note +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 +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 +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. + +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 +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 +overall validation result. Rather, it controls which of the `then` or `else` +keywords are evaluated. + +Instances that successfully validate against this keyword's subschema MUST also +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 +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 +subschema, then validation succeeds against this keyword if the instance also +successfully validates against this keyword's subschema. + +This keyword has no effect when `if` is absent, or when the instance fails to +validate against its subschema. Implementations MUST NOT evaluate the instance +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, +then validation succeeds against this keyword if the instance successfully +validates against this keyword's subschema. + +This keyword has no effect when `if` is absent, or when the instance +successfully validates against its subschema. Implementations MUST NOT evaluate +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. + +This keyword's value MUST be an object. Each value in the object MUST be a valid +JSON Schema. + +If the object key is a property in the instance, the entire instance must +validate against the subschema. Its use is dependent on the presence of the +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. + +This keyword's value MUST be an object. Each value in the object MUST be an +object whose values MUST be valid JSON Schemas. + +If the outer object key is a property in the instance and the inner object key +is equal to the value of that property, the entire instance must validate +against the schema. Its use is dependent on the presence and value of the +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. + +#### 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 +subschema at the same position, if any. This keyword does not constrain the +length of the array. Only array positions present in both the keyword's value +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`. + +Omitting this keyword has the same assertion behavior as an empty array. + +##### items +The value of `items` MUST be a valid JSON Schema. + +This keyword applies its subschema to all instance elements at indexes greater +than the length of the `prefixItems` array in the same schema object, as +reported by the annotation result of that `prefixItems` keyword. If no such +annotation result exists, `items` applies its subschema to all instance array +elements.[^11] + +[^11]: Note that the behavior of `items` without `prefixItems` is identical to +that of the schema form of `items` in prior drafts. When `prefixItems` is +present, the behavior of `items` is identical to the former `additionalItems` +keyword. + +If the `items` subschema is applied to any positions within the instance array, +it produces an annotation result of boolean true, indicating that all remaining +array elements have been evaluated against this keyword's subschema. This +annotation affects the behavior of `unevaluatedItems` in the Unevaluated +vocabulary. + +Omitting this keyword has the same assertion behavior as an empty schema. + +Implementations MAY choose to implement or optimize this keyword in another way +that produces the same effect, such as by directly checking for the presence and +size of a `prefixItems` array. Implementations that do not support annotation +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. + +Validation succeeds if, for each name that appears in both the instance and as a +name within this keyword's value, the child instance for that name successfully +validates against the corresponding schema. + +The annotation result of this keyword is the set of instance property names +which are also present under this keyword. This annotation affects the behavior +of `additionalProperties` (in this vocabulary) and `unevaluatedProperties` in +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 +Schema. + +Validation succeeds if, for each instance name that matches any regular +expressions that appear as a property name in this keyword's value, the child +instance for that name successfully validates against each schema that +corresponds to a matching regular expression. Recall: regular expressions are +not implicitly anchored. + +The annotation result of this keyword is the set of instance property names +matched by at least one property under this keyword. This annotation affects the +behavior of `additionalProperties` (in this vocabulary) and +`unevaluatedProperties` (in the Unevaluated vocabulary). + +Omitting this keyword has the same assertion behavior as an empty object. + +##### additionalProperties +The value of `additionalProperties` MUST be a valid JSON Schema. + +The behavior of this keyword depends on the presence and annotation results of +`properties` and `patternProperties` within the same schema object. Validation +with `additionalProperties` applies only to the child values of instance names +that do not appear in the annotation results of either `properties` or +`patternProperties`. + +For all such properties, validation succeeds if the child instance validates +against the `additionalProperties` schema. + +The annotation result of this keyword is the set of instance property names +validated by this keyword's subschema. This annotation affects the behavior of +`unevaluatedProperties` in the Unevaluated vocabulary. + +Omitting this keyword has the same assertion behavior as an empty schema. + +Implementations MAY choose to implement or optimize this keyword in another way +that produces the same effect, such as by directly checking the names in +`properties` and the patterns in `patternProperties` against the instance +property set. Implementations that do not support annotation collection MUST do +so.[^12] + +[^12]: In defining this option, it seems there is the potential for ambiguity in +the output format. The ambiguity does not affect validation results, but it does +affect the resulting output format. The ambiguity allows for multiple valid +output results depending on whether annotations are used or a solution that +"produces the same effect" as draft-07. It is understood that annotations from +failing schemas are dropped. See our [Decision +Record](https://github.com/json-schema-org/json-schema-spec/tree/HEAD/adr/2022-04-08-cref-for-ambiguity-and-fix-later-gh-spec-issue-1172.md) +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 +the instance validates against the provided schema. Note the property name that +the schema is testing will always be a string. + +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, +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. + +##### minContains +The value of this keyword MUST be a non-negative integer. + +This keyword modifies the behavior of `contains` within the same schema object, +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 [Section 7.3](#73-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. + +An instance is valid against `contains` if the number of elements or property +values that are valid against its subschema is with the inclusive range of the +minimum and (if any) maximum number of occurrences. + +The maximum number of occurrences is provided by the `maxContains` keyword +within the same schema object as `contains`. If `maxContains` is absent, the +maximum number of occurrences MUST be unbounded. + +The minimum number of occurrences is provided by the `minContains` keyword +within the same schema object as `contains`. If `minContains` is absent, the +minimum number of occurrences MUST be 1. + +Implementations MAY implement the dependency on `minContians` and `maxContains` +by inspecting their values rather than reading annotations produced by those +keywords. + +This keyword produces an annotation value which is an array of the indexes or +property names to which this keyword validates successfully when applying its +subschema, in ascending order. The value MAY be a boolean `true` if the +subschema validates successfully when applied to every index or property value +of the instance. The annotation MUST be present if the instance array or object +to which this keyword's schema applies is empty. + +This annotation affects the behavior of `unevaluatedItems` in the Unevaluated +vocabulary. + +The subschema MUST be applied to every array element or object property value +even after the first match has been found, in order to collect annotations for +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. + +These instance items or properties may have been unsuccessfully evaluated +against one or more adjacent keyword subschemas, such as when an assertion in a +branch of an `anyOf` fails. Such failed evaluations are not considered to +contribute to whether or not the item or property has been evaluated. Only +successful evaluations are considered. + +If an item in an array or an object property is "successfully evaluated", it is +logically considered to be valid in terms of the representation of the object or +array that's expected. For example if a subschema represents a car, which +requires between 2-4 wheels, and the value of "wheels" is 6, the instance object +is not "evaluated" to be a car, and the "wheels" property is considered +"unevaluated (successfully as a known thing)", and does not retain any +annotations. + +Recall that adjacent keywords are keywords within the same schema object, and +that the dynamic-scope subschemas include reference targets as well as lexical +subschemas. + +The behavior of these keywords depend on the annotation results of adjacent +keywords that apply to the instance location being validated. + +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. + +The current IRI for this vocabulary, known as the Unevaluated Applicator +vocabulary, is: `https://json-schema.org/draft/next/vocab/unevaluated`. + +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 +- `unevaluatedProperties`, whose behavior is defined in terms of annotations +from `properties`, `patternProperties`, `additionalProperties`, `contains`, and +itself + +### unevaluatedItems +The value of `unevaluatedItems` MUST be a valid JSON Schema. + +The behavior of this keyword depends on the annotation results of adjacent +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. + +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 +any of the relevant annotations, `unevaluatedItems` MUST be ignored. Otherwise, +the subschema MUST be applied to any index greater than the largest annotation +value for `prefixItems`, which does not appear in any annotation value for +`contains`. + +This means that `prefixItems`, `items`, `contains`, and all in-place applicators +MUST be evaluated before this keyword can be evaluated. Authors of extension +keywords MUST NOT define an in-place applicator that would need to be evaluated +after this keyword. + +If the `unevaluatedItems` subschema is applied to any positions within the +instance array, it produces an annotation result of boolean true, analogous to +the behavior of `items`. This annotation affects the behavior of +`unevaluatedItems` in parent schemas. + +Omitting this keyword has the same assertion behavior as an empty schema. + +### unevaluatedProperties +The value of `unevaluatedProperties` MUST be a valid JSON Schema. + +The behavior of this keyword depends on the annotation results of adjacent +keywords that apply to the instance location being validated. Specifically, the +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. + +Validation with `unevaluatedProperties` applies only to the child values of +instance names that do not appear in the `properties`, `patternProperties`, +`additionalProperties`, `contains`, or `unevaluatedProperties` annotation +results that apply to the instance location being validated. + +For all such properties, validation succeeds if the child instance validates +against the `unevaluatedProperties` schema. + +This means that `properties`, `patternProperties`, `additionalProperties`, +`contains` and all in-place applicators MUST be evaluated before this keyword +can be evaluated. Authors of extension keywords MUST NOT define an in-place +applicator that would need to be evaluated after this keyword. + +The annotation result of this keyword is the set of instance property names +validated by this keyword's subschema. This annotation affects the behavior of +`unevaluatedProperties` in parent schemas. + +Omitting this keyword has the same assertion behavior as an empty schema. + +## Output Formatting +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 +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. + +Flag: A boolean which simply indicates the overall validation result with no +further details. + +List: Provides validation information in a flat list structure. + +Hierarchical: Provides validation information in a hierarchical structure that +follows the evaluation paths generated while processing the schema. + +An implementation MUST provide the "flag" format and SHOULD provide at least one +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. + +A single object that contains all of these components is considered an output +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] + +[^13]: The schema may not actually have a value at the location indicated by +this pointer. It is provided as an indication of the traversal path only. + +``` +/properties/width/$ref/allOf/1 +``` + +Note that this pointer may not be resolvable by the normal JSON Pointer process +due to the inclusion of these by-reference applicator keywords. + +The JSON key for this information is "evaluationPath". + +#### Schema Location +The absolute, dereferenced location of the schema object that produced the +output unit. The value MUST be expressed using the canonical IRI of the +relevant schema resource plus a JSON Pointer fragment that indicates the schema +object that produced the output. It MUST NOT include by-reference applicators +such as `$ref` or `$dynamicRef`.[^14] + +[^14]: Note that "absolute" here is in the sense of "absolute filesystem path" +(meaning the complete location) rather than the "absolute-IRI" terminology from +RFC 3987 (meaning with scheme and without fragment). Schema locations will have +a fragment in order to identify the specific schema object. + +``` +https://example.com/schemas/common#/$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 +by the associated keyword. + +If the subschema itself is producing the error, that error MUST be listed with +an empty string key.[^15] + +[^15]: Although there may be other cases where a subschema can produce an error, +the most common case is the `false` schema. In cases like these, there is no +keyword that produces the error, so there is nothing to use as a key. Thus the +empty string is used instead. + +The specific wording for the message is not defined by this specification. +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. + +The value for this property MUST be an object where the keys are the names of +keywords and the values are the annotations produced by the associated keyword. + +Each keyword defines its own annotation data type (e.g. `properties` produces a +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. +It MUST NOT be included if the local validation result of the containing +subschema was successful. + +Implementations that wish to provide these annotations MUST NOT provide them as +their default behavior. These annotations MUST only be included by explicitly +configuring the implementation to do so. + +The value for this property MUST be an object where the keys are the names of +keywords and the values are the annotations produced by the associated keyword. + +Each keyword defines its own annotation data type (e.g. `properties` produces a +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 +potentially multiple results, the value of this property MUST be an array of +output units, even if only a single output unit is produced. + +For "list", this property will appear only at the root output unit and will hold +all output units in a flat list. + +For "hierarchical", this property will contain results in a tree structure where +each output unit may itself have further nested results. + +The sequence of output units within this list is not specified and MAY be +determined by the implementation. Sets of output units are considered equivalent +if they contain the same units, in any order. + +The JSON key for these additional results is "details". + +### 12.4. Output Structure + +The output MUST be an object containing a boolean property named "valid". When +additional information about the result is required, the output MUST also +contain "details" as described below. + +valid: a boolean value indicating the overall validation success or failure + +details: the collection of results produced by subschemas + +For these examples, the following schema and instances will be used. + +Schema +```json +{ + "$schema": "https://json-schema.org/draft/next/schema", + "$id": "https://json-schema.org/schemas/example", + "type": "object", + "title": "root", + "properties": { + "foo": { + "allOf": [ + { "required": [ "unspecified-prop" ] }, + { + "type": "object", + "title": "foo-title", + "properties": { + "foo-prop": { + "const": 1, + "title": "foo-prop-title" + } + }, + "additionalProperties": { "type": "boolean" } + } + ] + }, + "bar": { + "$ref": "#/$defs/bar" + } + }, + "$defs": { + "bar": { + "type": "object", + "title": "bar-title", + "properties": { + "bar-prop": { + "type": "integer", + "minimum": 10, + "title": "bar-prop-title" + } + } + } + } +} +``` + +Failing instance +```json +{ + "foo": {"foo-prop": "not 1", "other-prop": false}, + "bar": {"bar-prop": 2} +} +``` + +Passing instance +```json +{ + "foo": { + "foo-prop": 1, + "unspecified-prop": true + }, + "bar": {"bar-prop": 20} +} +``` + +The failing instance will produce the following errors: + +- The value at `/foo` evaluated at `/properties/foo/allOf/0` by following the +path `/properties/foo/allOf/0` by the `required` keyword is missing the property +`unspecified-prop`. +- The value at `/foo/foo-prop` evaluated at +`/properties/foo/allOf/1/properties/foo-prop` by following the path +`/properties/foo/allOf/1/properties/foo-prop` by the `const` keyword is not the +constant value 1. +- The value at `/bar/bar-prop` evaluated at `/$defs/bar/properties/bar-prop` by +following the path `/properties/bar/$ref/properties/bar-prop` by the `type` +keyword is not a number.[^16][^17] + +[^16]: `minimum` doesn't produce an error because it only operates on instances +that are numbers. + +[^17]: Note that the error message wording as depicted in the examples below is +not a requirement of this specification. Implementations SHOULD craft error +messages tailored for their audience or provide a templating mechanism that +allows their users to craft their own messages. + +The passing instance will produce the following annotations: + +- The keyword `title` evaluated at `` by following the path `` will produce +`"root"`. +- The keyword `properties` evaluated at `` by following the path `` will produce +`["foo", "bar"]`. +- The keyword `title` evaluated at `/properties/foo` by following the path +`/properties/foo` will produce `"foo-title"`. +- The keyword `properties` evaluated at `/properties/foo/allOf/1` by following +the path `/properties/foo/allOf/1` will produce `["foo-prop"]`. +- The keyword `additionalProperties` evaluated at `/properties/foo/allOf/1` by +following the path `/properties/foo/allOf/1` will produce +`["unspecified-prop"]`. +- The keyword `title` evaluated at `/properties/foo/allOf/1/properties/foo-prop` +by following the path `/properties/foo/allOf/1/properties/foo-prop` will produce +`"foo-prop-title"`. +- The keyword `title` evaluated at `/$defs/bar` by following the path +`/properties/bar/$ref` will produce `"bar-title"`. +- The keyword `properties` evaluated at `/$defs/bar` by following the path +`/properties/var/$ref` will produce `["bar-prop"]`. +- The keyword `title` evaluated at `/$defs/bar/properties/bar-prop` by following +the path `/properties/bar/$ref/properties/bar-prop` will produce +`"bar-prop-title"`. + +#### Flag +In the simplest case, merely the boolean result for the "valid" valid property +needs to be fulfilled. For this format, all other information is explicitly +omitted. + +```json +{ + "valid": false +} +``` + +Because no errors or annotations are returned with this format, it is +RECOMMENDED that implementations use short-circuiting logic to return failure or +success as soon as the outcome can be determined. For example, if an `anyOf` +keyword contains five subschemas, and the second one passes, there is no need to +check the other three. The logic can simply return with success. + +#### List +The "List" structure is a flat list of output units contained within a root +output unit. + +The root output unit contains "valid" for the overall result and "details" for +the list of specific results. All other information is explicitly omitted from +the root output unit. If the root schema produces errors or annotations, then +the output node for the root MUST be present within the root output unit's +"details" list with those errors or annotations. + +Output units which do not contain errors or annotations SHOULD be excluded from +this format, however implementations MAY choose to include them for +completeness. + +Failing results +```json +{ + "valid": false, + "details": [ + { + "valid": false, + "evaluationPath": "/properties/foo/allOf/0", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/foo/allOf/0", + "instanceLocation": "/foo", + "errors": { + "required": "Required properties [\"unspecified-prop\"] were not present" + } + }, + { + "valid": false, + "evaluationPath": "/properties/foo/allOf/1/properties/foo-prop", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/foo/allOf/1/properties/foo-prop", + "instanceLocation": "/foo/foo-prop", + "errors": { + "const": "Expected \"1\"" + } + }, + { + "valid": false, + "evaluationPath": "/properties/bar/$ref/properties/bar-prop", + "schemaLocation": "https://json-schema.org/schemas/example#/$defs/bar/properties/bar-prop", + "instanceLocation": "/bar/bar-prop", + "errors": { + "minimum": "2 is less than or equal to 10" + } + } + ] +} +``` + +Passing results +```json +{ + "valid": true, + "details": [ + { + "valid": true, + "evaluationPath": "", + "schemaLocation": "https://json-schema.org/schemas/example#", + "instanceLocation": "", + "annotations": { + "title": "root", + "properties": [ + "foo", + "bar" + ] + } + }, + { + "valid": true, + "evaluationPath": "/properties/foo/allOf/1", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/foo/allOf/1", + "instanceLocation": "/foo", + "annotations": { + "title": "foo-title", + "properties": [ + "foo-prop" + ], + "additionalProperties": [ + "unspecified-prop" + ] + } + }, + { + "valid": true, + "evaluationPath": "/properties/bar/$ref", + "schemaLocation": "https://json-schema.org/schemas/example#/$defs/bar", + "instanceLocation": "/bar", + "annotations": { + "title": "bar-title", + "properties": [ + "bar-prop" + ] + } + }, + { + "valid": true, + "evaluationPath": "/properties/foo/allOf/1/properties/foo-prop", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/foo/allOf/1/properties/foo-prop", + "instanceLocation": "/foo/foo-prop", + "annotations": { + "title": "foo-prop-title" + } + }, + { + "valid": true, + "evaluationPath": "/properties/bar/$ref/properties/bar-prop", + "schemaLocation": "https://json-schema.org/schemas/example#/$defs/bar/properties/bar-prop", + "instanceLocation": "/bar/bar-prop", + "annotations": { + "title": "bar-prop-title" + } + } + ] +} +``` + +#### 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 +keywords. + +All output units are included in this format. + +The location properties of the root output unit MAY be omitted. + +Failing results (errors) +```json +{ + "valid": false, + "evaluationPath": "", + "schemaLocation": "https://json-schema.org/schemas/example#", + "instanceLocation": "", + "details": [ + { + "valid": false, + "evaluationPath": "/properties/foo", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/foo", + "instanceLocation": "/foo", + "details": [ + { + "valid": false, + "evaluationPath": "/properties/foo/allOf/0", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/foo/allOf/0", + "instanceLocation": "/foo", + "errors": { + "required": "Required properties [\"unspecified-prop\"] were not present" + } + }, + { + "valid": false, + "evaluationPath": "/properties/foo/allOf/1", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/foo/allOf/1", + "instanceLocation": "/foo", + "droppedAnnotations": { + "properties": [ "foo-prop" ], + "title": "foo-title" + }, + "details": [ + { + "valid": false, + "evaluationPath": "/properties/foo/allOf/1/properties/foo-prop", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/foo/allOf/1/properties/foo-prop", + "instanceLocation": "/foo/foo-prop", + "errors": { + "const": "Expected \"1\"" + }, + "droppedAnnotations": { + "title": "foo-prop-title" + } + }, + { + "valid": true, + "evaluationPath": "/properties/foo/allOf/1/additionalProperties", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/foo/allOf/1/additionalProperties", + "instanceLocation": "/foo/other-prop" + } + ] + } + ] + }, + { + "valid": false, + "evaluationPath": "/properties/bar", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/bar", + "instanceLocation": "/bar", + "details": [ + { + "valid": false, + "evaluationPath": "/properties/bar/$ref", + "schemaLocation": "https://json-schema.org/schemas/example#/$defs/bar", + "instanceLocation": "/bar", + "droppedAnnotations": { + "properties": [ "bar-prop" ], + "title": "bar-title" + }, + "details": [ + { + "valid": false, + "evaluationPath": "/properties/bar/$ref/properties/bar-prop", + "schemaLocation": "https://json-schema.org/schemas/example#/$defs/bar/properties/bar-prop", + "instanceLocation": "/bar/bar-prop", + "errors": { + "minimum": "2 is less than or equal to 10" + }, + "droppedAnnotations": { + "title": "bar-prop-title" + } + } + ] + } + ] + } + ] +} +``` + +Passing results (annotations) +```json +{ + "valid": true, + "evaluationPath": "", + "schemaLocation": "https://json-schema.org/schemas/example#", + "instanceLocation": "", + "annotations": { + "title": "root", + "properties": [ + "foo", + "bar" + ] + }, + "details": [ + { + "valid": true, + "evaluationPath": "/properties/foo", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/foo", + "instanceLocation": "/foo", + "details": [ + { + "valid": true, + "evaluationPath": "/properties/foo/allOf/0", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/foo/allOf/0", + "instanceLocation": "/foo" + }, + { + "valid": true, + "evaluationPath": "/properties/foo/allOf/1", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/foo/allOf/1", + "instanceLocation": "/foo", + "annotations": { + "title": "foo-title", + "properties": [ + "foo-prop" + ], + "additionalProperties": [ + "unspecified-prop" + ] + }, + "details": [ + { + "valid": true, + "evaluationPath": "/properties/foo/allOf/1/properties/foo-prop", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/foo/allOf/1/properties/foo-prop", + "instanceLocation": "/foo/foo-prop", + "annotations": { + "title": "foo-prop-title" + } + }, + { + "valid": true, + "evaluationPath": "/properties/foo/allOf/1/additionalProperties", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/foo/allOf/1/additionalProperties", + "instanceLocation": "/foo/unspecified-prop" + } + ] + } + ] + }, + { + "valid": true, + "evaluationPath": "/properties/bar", + "schemaLocation": "https://json-schema.org/schemas/example#/properties/bar", + "instanceLocation": "/bar", + "details": [ + { + "valid": true, + "evaluationPath": "/properties/bar/$ref", + "schemaLocation": "https://json-schema.org/schemas/example#/$defs/bar", + "instanceLocation": "/bar", + "annotations": { + "title": "bar-title", + "properties": [ + "bar-prop" + ] + }, + "details": [ + { + "valid": true, + "evaluationPath": "/properties/bar/$ref/properties/bar-prop", + "schemaLocation": "https://json-schema.org/schemas/example#/$defs/bar/properties/bar-prop", + "instanceLocation": "/bar/bar-prop", + "annotations": { + "title": "bar-prop-title" + } + } + ] + } + ] + } + ] +} +``` + +#### Output validation schemas +For convenience, JSON Schema has been provided to validate output generated by +implementations. Its IRI is: . + +## Security Considerations +Both schemas and instances are JSON values. As such, all security considerations +defined in [RFC 8259](#rfc8259) apply. + +Instances and schemas are both frequently written by untrusted third parties, to +be deployed on public Internet servers. Implementations should take care that +the parsing and evaluating against schemas does not consume excessive system +resources. Implementations MUST NOT fall into an infinite loop. + +A malicious party could cause an implementation to repeatedly collect a copy of +a very large value as an annotation. Implementations SHOULD guard against +excessive consumption of system resources in such a scenario. + +Servers MUST ensure that malicious parties cannot change the functionality of +existing schemas by uploading a schema with a pre-existing or very similar +`$id`. + +Individual JSON Schema vocabularies are liable to also have their own security +considerations. Consult the respective specifications for more information. + +Schema authors should take care with `$comment` contents, as a malicious +implementation can display them to end-users in violation of a spec, or fail to +strip them if such behavior is expected. + +A malicious schema author could place executable code or other dangerous +material within a `$comment`. Implementations MUST NOT parse or otherwise take +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 + +Subtype name:: schema+json + +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 [Section 13](#13-security-considerations) above. + +Interoperability considerations:: See Sections +[6.2](#62-programming-language-independence), [6.3](#63-mathematical-integers), +and [6.4](#64-regular-expressions) above. + +Fragment identifier considerations:: See [Section 5](#5-fragment-identifiers) + +### 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: + +Type name:: application + +Subtype name:: schema-instance+json + +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 [Section 13](#13-security-considerations) above. + +Interoperability considerations:: See Sections +[6.2](#62-programming-language-independence), [6.3](#63-mathematical-integers), +and [6.4](#64-regular-expressions) above. + +Fragment identifier considerations:: See [Section 5](#5-fragment-identifiers) + +## References + +### Normative References + +#### [RFC2119] +Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", BCP 14, +RFC 2119, DOI 10.17487/RFC2119, March 1997, +<>. + +#### [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] +Duerst, M. and M. Suignard, "Internationalized Resource Identifiers (IRIs)", RFC +3987, DOI 10.17487/RFC3987, January 2005, +<>. + +#### [RFC6839] +Hansen, T. and A. Melnikov, "Additional Media Type Structured Syntax Suffixes", +RFC 6839, DOI 10.17487/RFC6839, January 2013, +<>. + +#### [RFC6901] +Bryan, P., Ed., Zyp, K., and M. Nottingham, Ed., "JavaScript Object Notation +(JSON) Pointer", RFC 6901, DOI 10.17487/RFC6901, April 2013, +<>. + +#### [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] +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] +"ECMA-262, 11th edition specification", June 2020, +<>. + +### Informative References + +#### [RFC6596] +Ohye, M. and J. Kupke, "The Canonical Link Relation", RFC 6596, DOI +10.17487/RFC6596, April 2012, <>. + +#### [RFC7049] +Bormann, C. and P. Hoffman, "Concise Binary Object Representation (CBOR)", RFC +7049, DOI 10.17487/RFC7049, October 2013, +<>. + +#### [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] +Nottingham, M., "Web Linking", RFC 8288, DOI 10.17487/RFC8288, October 2017, +<>. + +#### [W3C.WD-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] +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] +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] +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] +Bray, T., Ed., Hollander, D., Ed., Layman, A., Ed., and R. Tobin, Ed., +"Namespaces in XML 1.1 (Second Edition)", August 2006, +<>. + +## Appendix A. Schema identification examples +Consider the following schema, which shows `$id` being used to identify both the +root schema and various subschemas, and `$anchor` being used to define plain +name fragment identifiers. + +```json +{ + "$id": "https://example.com/root.json", + "$defs": { + "A": { "$anchor": "foo" }, + "B": { + "$id": "other.json", + "$defs": { + "X": { "$anchor": "bar" }, + "Y": { + "$id": "t/inner.json", + "$anchor": "bar" + } + } + }, + "C": { + "$id": "urn:uuid:ee564b8a-7a87-4125-8c96-e9f123d6766f" + } + } +} +``` + +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 [Section 5](#5-fragment-identifiers) and [Section +9.2.1](#921-json-pointer-fragments-and-embedded-schema-resources) above. + +`#` (document root): canonical (and base) IRI: `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` + +`#/$defs/B`: canonical (and base) `IRI: https://example.com/other.json` +canonical resource IRI plus pointer fragment: `https://example.com/other.json#` +base IRI of enclosing (root.json) resource plus fragment: +`https://example.com/root.json#/$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/$defs/X` + +`#/$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` + +`#/$defs/C`: canonical (and base) IRI: +`urn:uuid:ee564b8a-7a87-4125-8c96-e9f123d6766f` canonical IRI plus pointer +fragment: `urn:uuid:ee564b8a-7a87-4125-8c96-e9f123d6766f#` base IRI of enclosing +(root.json) resource plus fragment: `https://example.com/root.json#/$defs/C` + +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 +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](#921-json-pointer-fragments-and-embedded-schema-resources) section +for futher comments. + +## Appendix B. Manipulating schema documents and references +Various tools have been created to rearrange schema documents based on how and +where references (`$ref`) appear. This appendix discusses which use cases and +actions are compliant with this specification. + +### B.1. Bundling schema resources into a single document +A set of schema resources intended for use together can be organized with each +in its own schema document, all in the same schema document, or any granularity +of document grouping in between. + +Numerous tools exist to perform various sorts of reference removal. A common +case of this is producing a single file where all references can be resolved +within that file. This is typically done to simplify distribution, or to +simplify coding so that various invocations of JSON Schema libraries do not have +to keep track of and load a large number of resources. + +This transformation can be safely and reversibly done as long as all static +references (e.g. `$ref`) use IRI-references that resolve to IRIs using the +canonical resource IRI as the base, and all schema resources have an +absolute-IRI as the `$id` in their root schema. + +With these conditions met, each external resource can be copied under `$defs`, +without breaking any references among the resources' schema objects, and without +changing any aspect of validation or annotation results. The names of the +schemas under `$defs` do not affect behavior, assuming they are each unique, as +they do not appear in the canonical IRIs for the embedded resources. + +### B.2. Reference removal is not always safe +Attempting to remove all references and produce a single schema document does +not, in all cases, produce a schema with identical behavior to the original +form. + +Since `$ref` is now treated like any other keyword, with other keywords allowed +in the same schema objects, fully supporting non-recursive `$ref` removal in all +cases can require relatively complex schema manipulations. It is beyond the +scope of this specification to determine or provide a set of safe `$ref` removal +transformations, as they depend not only on the schema structure but also on the +intended usage. + +## Appendix C. Example of recursive schema extension +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 +and only allows the "data" and "children" properties. An example instance with +"data" misspelled as "daat" is also shown. + +Tree schema, extensible +```json +{ + "$schema": "https://json-schema.org/draft/next/schema", + "$id": "https://example.com/tree", + "$dynamicAnchor": "node", + + "type": "object", + "properties": { + "data": true, + "children": { + "type": "array", + "items": { + "$dynamicRef": "#node" + } + } + } +} +``` + +Strict-tree schema, guards against misspelled properties +```json +{ + "$schema": "https://json-schema.org/draft/next/schema", + "$id": "https://example.com/strict-tree", + "$dynamicAnchor": "node", + + "$ref": "tree", + "unevaluatedProperties": false +} +``` + +Instance with misspelled field +```json +{ + "children": [ { "daat": 1 } ] +} +``` + +When we load these two schemas, we will notice the `$dynamicAnchor` named "node" +(note the lack of "#" as this is just the name) present in each, resulting in +the following full schema IRIs: + +- `https://example.com/tree#node` +- `https://example.com/strict-tree#node` + +In addition, JSON Schema implementations keep track of the fact that these +fragments were created with `$dynamicAnchor`. + +If we apply the "strict-tree" schema to the instance, we will follow the `$ref` +to the "tree" schema, examine its "children" subschema, and find the +`$dynamicRef`: to "#node" (note the `#` for IRI fragment syntax) in its `items` +subschema. That reference resolves to `https://example.com/tree#node`, which is +a IRI with a fragment created by `$dynamicAnchor`. Therefore we must examine the +dynamic scope before following the reference. + +At this point, the evaluation path is +`#/$ref/properties/children/items/$dynamicRef`, with a dynamic scope containing +(from the outermost scope to the innermost): + +1. `https://example.com/strict-tree#` +1. `https://example.com/tree#` +1. `https://example.com/tree#/properties/children` +1. `https://example.com/tree#/properties/children/items` + +Since we are looking for a plain name fragment, which can be defined anywhere +within a schema resource, the JSON Pointer fragments are irrelevant to this +check. That means that we can remove those fragments and eliminate consecutive +duplicates, producing: + +1. `https://example.com/strict-tree` +1. `https://example.com/tree` + +In this case, the outermost resource also has a "node" fragment defined by +`$dynamicAnchor`. Therefore instead of resolving the `$dynamicRef` to +`https://example.com/tree#node`, we resolve it to +`https://example.com/strict-tree#node`. + +This way, the recursion in the "tree" schema recurses to the root of +"strict-tree", instead of only applying "strict-tree" to the instance root, but +applying "tree" to instance children. + +This example shows both `$dynamicAnchor`s in the same place in each schema, +specifically the resource root schema. Since plain-name fragments are +independent of the JSON structure, this would work just as well if one or both +of the node schema objects were moved under `$defs`. It is the matching +`$dynamicAnchor` values which tell us how to resolve the dynamic reference, not +any sort of correlation in JSON structure. + +## Appendix D. Working with vocabularies + +### D.1. Best practices for vocabulary and meta-schema authors +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 +also does not constrain keyword names, allowing for any number of namespacing +approaches. + +Vocabularies may build on each other, such as by defining the behavior of their +keywords with respect to the behavior of keywords from another vocabulary, or by +using a keyword from another vocabulary with a restricted or expanded set of +acceptable values. Not all such vocabulary re-use will result in a new +vocabulary that is compatible with the vocabulary on which it is built. +Vocabulary authors should clearly document what level of compatibility, if any, +is expected. + +Meta-schema authors should not use `$vocabulary` to combine multiple +vocabularies that define conflicting syntax or semantics for the same keyword. +As semantic conflicts are not generally detectable through schema validation, +implementations are not expected to detect such conflicts. If conflicting +vocabularies are declared, the resulting behavior is undefined. + +Vocabulary authors SHOULD provide a meta-schema that validates the expected +usage of the vocabulary's keywords on their own. Such meta-schemas SHOULD not +forbid additional keywords, and MUST not forbid any keywords from the Core +vocabulary. + +It is recommended that meta-schema authors reference each vocabulary's +meta-schema using the [`allOf`](#10211-allof) keyword, although other mechanisms +for constructing the meta-schema may be appropriate for certain use cases. + +The recursive nature of meta-schemas makes the `$dynamicAnchor` and +`$dynamicRef` keywords particularly useful for extending existing meta-schemas, +as can be seen in the JSON Hyper-Schema meta-schema which extends the Validation +meta-schema. + +Meta-schemas may impose additional constraints, including describing keywords +not present in any vocabulary, beyond what the meta-schemas associated with the +declared vocabularies describe. This allows for restricting usage to a subset of +a vocabulary, and for validating locally defined keywords not intended for +re-use. + +However, meta-schemas should not contradict any vocabularies that they declare, +such as by requiring a different JSON type than the vocabulary expects. The +resulting behavior is undefined. + +Meta-schemas intended for local use, with no need to test for vocabulary support +in arbitrary implementations, can safely omit `$vocabulary` entirely. + +### D.2. Example meta-schema with vocabulary declarations +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 +keywords in that vocabulary, is shown after the main example meta-schema. + +The main example meta-schema also restricts the usage of the Unevaluated +vocabulary by forbidding the keywords prefixed with "unevaluated", which are +particularly complex to implement. This does not change the semantics or set of +keywords defined by the other vocabularies. It just ensures that schemas using +this meta-schema that attempt to use the keywords prefixed with "unevaluated" +will fail validation against this meta-schema. + +Finally, this meta-schema describes the syntax of a keyword, "localKeyword", +that is not part of any vocabulary. Presumably, the implementors and users of +this meta-schema will understand the semantics of "localKeyword". JSON Schema +does not define any mechanism for expressing keyword semantics outside of +vocabularies, making them unsuitable for use except in a specific environment in +which they are understood. + +This meta-schema combines several vocabularies for general use. + +```json +{ + "$schema": "https://json-schema.org/draft/next/schema", + "$id": "https://example.com/meta/general-use-example", + "$dynamicAnchor": "meta", + "$vocabulary": { + "https://json-schema.org/draft/next/vocab/core": true, + "https://json-schema.org/draft/next/vocab/applicator": true, + "https://json-schema.org/draft/next/vocab/validation": true, + "https://example.com/vocab/example-vocab": true + }, + "allOf": [ + {"$ref": "https://json-schema.org/draft/next/meta/core"}, + {"$ref": "https://json-schema.org/draft/next/meta/applicator"}, + {"$ref": "https://json-schema.org/draft/next/meta/validation"}, + {"$ref": "https://example.com/meta/example-vocab", + ], + "patternProperties": { + "^unevaluated": false + }, + "properties": { + "localKeyword": { + "$comment": "Not in vocabulary, but validated if used", + "type": "string" + } + } +} +``` + +This meta-schema describes only a single extension vocabulary. + +```json +{ + "$schema": "https://json-schema.org/draft/next/schema", + "$id": "https://example.com/meta/example-vocab", + "$dynamicAnchor": "meta", + "$vocabulary": { + "https://example.com/vocab/example-vocab": true, + }, + "type": ["object", "boolean"], + "properties": { + "minDate": { + "type": "string", + "pattern": "\\d\\d\\d\\d-\\d\\d-\\d\\d", + "format": "date", + } + } +} +``` + +As shown above, even though each of the single-vocabulary meta-schemas +referenced in the general-use meta-schema's `allOf` declares its corresponding +vocabulary, this new meta-schema must re-declare them. + +The standard meta-schemas that combine all vocabularies defined by the Core and +Validation specification, and that combine all vocabularies defined by those +specifications as well as the Hyper-Schema specification, demonstrate additional +complex combinations. These IRIs for these meta-schemas may be found in the +Validation and Hyper-Schema specifications, respectively. + +While the general-use meta-schema can validate the syntax of `minDate`, it is +the vocabulary that defines the logic behind the semantic meaning of `minDate`. +Without an understanding of the semantics (in this example, that the instance +value must be a date equal to or after the date provided as the keyword's value +in the schema), an implementation can only validate the syntactic usage. In this +case, that means validating that it is a date-formatted string (using `pattern` +to ensure that it is validated even when `format` functions purely as an +annotation, as explained in the [Validation +specification](#json-schema-validation). + +## Appendix E. References and generative use cases +While the presence of references is expected to be transparent to validation +results, generative use cases such as code generators and UI renderers often +consider references to be semantically significant. + +To make such use case-specific semantics explicit, the best practice is to +create an annotation keyword for use in the same schema object alongside of a +reference keyword such as `$ref`. + +For example, here is a hypothetical keyword for determining whether a code +generator should consider the reference target to be a distinct class, and how +those classes are related. Note that this example is solely for illustrative +purposes, and is not intended to propose a functional code generation keyword. + +```json +{ + "allOf": [ + { + "classRelation": "is-a", + "$ref": "classes/base.json" + }, + { + "$ref": "fields/common.json" + } + ], + "properties": { + "foo": { + "classRelation": "has-a", + "$ref": "classes/foo.json" + }, + "date": { + "$ref": "types/dateStruct.json", + } + } +} +``` + +Here, this schema represents some sort of object-oriented class. The first +reference in the `allOf` is noted as the base class. The second is not assigned +a class relationship, meaning that the code generator should combine the +target's definition with this one as if no reference were involved. + +Looking at the properties, "foo" is flagged as object composition, while the +"date" property is not. It is simply a field with sub-fields, rather than an +instance of a distinct class. + +This style of usage requires the annotation to be in the same object as the +reference, which must be recognizable as a reference. + +## Appendix F. Acknowledgments +Thanks to Gary Court, Francis Galiegue, Kris Zyp, Geraint Luff, and Henry +Andrews for their work on the initial drafts of JSON Schema. + +Thanks to Jason Desrosiers, Daniel Perrett, Erik Wilde, Evgeny Poberezkin, Brad +Bowman, Gowry Sankar, Donald Pipowitch, Dave Finlay, Denis Laxalde, Phil +Sturgeon, Shawn Silverman, and Karen Etheridge for their submissions and patches +to the document. + +## Appendix G. Change Log[^19] +[^19]: This section to be removed before leaving Internet-Draft status. + +### G.1. draft-bhutton-json-schema-next +- `contains` now applies to objects as well as arrays +- Use IRIs instead of URIs +- Remove bookending requirement for `$dynamicRef` +- Add `propertyDependencies` keyword + +### G.2. draft-bhutton-json-schema-01 +- Improve and clarify the `type`, `contains`, `unevaluatedProperties`, and +`unevaluatedItems` keyword explanations +- Clarify various aspects of "canonical URIs" +- Comment on ambiguity around annotations and `additionalProperties` +- Clarify Vocabularies need not be formally defined +- Remove references to remaining media-type parameters +- Fix multiple examples + +### G.3. draft-bhutton-json-schema-00 +- `$schema` MAY change for embedded resources +- Array-value `items` functionality is now `prefixItems` +- `items` subsumes the old function of `additionalItems` +- `contains` annotation behavior, and `contains` and `unevaluatedItems` +interactions now specified +- Rename $recursive* to $dynamic*, with behavior modification +- $dynamicAnchor defines a fragment like $anchor +- $dynamic* (previously $recursive) no longer use runtime base URI determination +- Define Compound Schema Documents (bundle) and processing +- Reference ECMA-262, 11th edition for regular expression support +- Regular expression should support unicode +- Remove media type parameters +- Specify Unknown keywords are collected as annotations +- Moved `unevaluatedItems` and `unevaluatedProperties` from core into their own +vocabulary + +### G.4. draft-handrews-json-schema-02 +- Update to RFC 8259 for JSON specification +- Moved `definitions` from the Validation specification here as `$defs` +- Moved applicator keywords from the Validation specification as their own +vocabulary +- Moved the schema form of `dependencies` from the Validation specification as +`dependentSchemas` +- Formalized annotation collection +- Specified recommended output formats +- Defined keyword interactions in terms of annotation and assertion results +- Added `unevaluatedProperties` and `unevaluatedItems` +- Define `$ref` behavior in terms of the assertion, applicator, and annotation +model +- Allow keywords adjacent to `$ref` +- Note undefined behavior for `$ref` targets involving unknown keywords +- Add recursive referencing, primarily for meta-schema extension +- Add the concept of formal vocabularies, and how they can be recognized through +meta-schemas +- Additional guidance on initial base URIs beyond network retrieval +- Allow "schema" media type parameter for `application/schema+json` +- Better explanation of media type parameters and the HTTP Accept header +- Use `$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 + +### G.5. draft-handrews-json-schema-01 +- This draft is purely a clarification with no functional changes +- Emphasized annotations as a primary usage of JSON Schema +- Clarified $id by use cases +- Exhaustive schema identification examples +- Replaced "external referencing" with how and when an implementation might know +of a schema from another document +- Replaced "internal referencing" with how an implementation should recognized +schema identifiers during parsing +- Dereferencing the former "internal" or "external" references is always the +same process +- Minor formatting improvements + +### G.6. draft-handrews-json-schema-00 +- Make the concept of a schema keyword vocabulary more clear +- Note that the concept of "integer" is from a vocabulary, not the data model +- Classify keywords as assertions or annotations and describe their general +behavior +- Explain the boolean schemas in terms of generalized assertions +- Reserve `$comment` for non-user-visible notes about the schema +- Wording improvements around `$id` and fragments +- Note the challenges of extending meta-schemas with recursive references +- Add `application/schema-instance+json` media type +- Recommend a "schema" link relation / parameter instead of "profile" + +### G.7. draft-wright-json-schema-01 +- Updated intro +- Allowed for any schema to be a boolean +- `$schema` SHOULD NOT appear in subschemas, although that may change +- 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 + +### G.8. draft-wright-json-schema-00 +- Updated references to JSON +- Updated references to HTTP +- Updated references to JSON Pointer +- Behavior for `id` is now specified in terms of RFC3986 +- Aligned vocabulary usage for URIs with RFC3986 +- Removed reference to draft-pbryan-zyp-json-ref-03 +- Limited use of `$ref` to wherever a schema is expected +- Added definition of the "JSON Schema data model" +- Added additional security considerations +- Defined use of subschema identifiers for `id` +- Rewrote section on usage with HTTP +- Rewrote section on usage with rel="describedBy" and rel="profile" +- Fixed numerous invalid examples + +### G.9. draft-zyp-json-schema-04 +- Salvaged from draft v3. +- Split validation keywords into separate document. +- Split hypermedia keywords into separate document. +- Initial post-split draft. +- Mandate the use of JSON Reference, JSON Pointer. +- Define the role of `id`. Define URI resolution scope. +- Add interoperability considerations. + +### G.10. draft-zyp-json-schema-00 +- Initial draft. + +## Authors' Addresses + +### Austin Wright (*editor*) +Email: + +### Ben Hutton (*editor*) +Postman + +Email: + +URI: + +### Greg Dennis + +Email: + +URI: diff --git a/jsonschema-core.xml b/jsonschema-core.xml deleted file mode 100644 index 4c4b662a..00000000 --- a/jsonschema-core.xml +++ /dev/null @@ -1,4406 +0,0 @@ - - - - - - - - - - - - - - -]> - - - - - - - - - - - JSON Schema: A Media Type for Describing JSON Documents - - -
- aaa@bzfx.net -
- - - - Postman -
- ben@jsonschema.dev - https://jsonschema.dev -
- - - -
- gregsdennis@yahoo.com - https://github.com/gregsdennis -
- - - - Internet Engineering Task Force - JSON - Schema - Hyper Schema - Hypermedia - - - - 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 interact with it. - The "application/schema-instance+json" media type provides additional - feature-rich integration with "application/schema+json" beyond what can be offered - for "application/json" documents. - - - - - The issues list for this draft can be found at - . - - - For additional information, see . - - - To provide feedback, use this issue tracker, the communication methods listed on the - homepage, or email the document editors. - - - - - -
- - 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. - - - This specification defines JSON Schema core terminology and mechanisms, including - pointing to another JSON Schema by reference, - dereferencing a JSON Schema reference, - specifying the dialect being used, - specifying a dialect's vocabulary requirements, - and defining the expected output. - - - Other specifications define the vocabularies that perform assertions about validation, - linking, annotation, navigation, and interaction. - -
- -
- - - - 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. - - - - The terms "JSON", "JSON text", "JSON value", "member", "element", "object", "array", - "number", "string", "boolean", "true", "false", and "null" in this document are to - be interpreted as defined in RFC 8259. - -
- -
- - 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 features. - JSON Schemas are themselves JSON documents. - This, and related specifications, define keywords allowing authors to describe JSON - data in several ways. - - - JSON Schema uses keywords to assert constraints on JSON instances or annotate those - instances with additional information. Additional keywords are used to apply - assertions and annotations to more complex JSON data structures, or based on - some sort of condition. - - - To facilitate re-use, keywords can be organized into vocabularies. A vocabulary - consists of a list of keywords, together with their syntax and semantics. - A dialect is defined as a set of vocabularies and their required support - identified in a meta-schema. - - - JSON Schema can be extended either by defining additional vocabularies, - or less formally by defining additional keywords outside of any vocabulary. - Unrecognized individual keywords simply have their values collected as annotations, - while the behavior with respect to an unrecognized vocabulary can be controlled - when declaring which vocabularies are in use. - - - This document defines a core vocabulary that MUST be supported by any - implementation, and cannot be disabled. Its keywords are each prefixed - with a "$" character to emphasize their required nature. This vocabulary - is essential to the functioning of the "application/schema+json" media - type, and is used to bootstrap the loading of other vocabularies. - - - Additionally, this document defines a RECOMMENDED vocabulary of keywords - for applying subschemas conditionally, and for applying subschemas to - the contents of objects and arrays. Either this vocabulary or one very - much like it is required to write schemas for non-trivial JSON instances, - whether those schemas are intended for assertion validation, annotation, - or both. While not part of the required core vocabulary, for maximum - interoperability this additional vocabulary is included in this document - and its use is strongly encouraged. - - - Further vocabularies for purposes such as structural validation or - hypermedia annotation are defined in other documents. These other - documents each define a dialect collecting the standard sets of - vocabularies needed to write schemas for that document's purpose. - -
- -
- -
- - 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 . - - - 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 - model can be interpreted against a JSON Schema, including media types like - CBOR. - -
- -
- - A JSON document to which a schema is applied is known as an "instance". - - - JSON Schema is defined over "application/json" or compatible documents, - 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. - - -
- - JSON Schema interprets documents according to a data model. A JSON value - interpreted according to this data model is called an "instance". - - - An instance has one of six primitive types, and a range of possible values - depending on the type: - -
-
null
A JSON "null" value
-
boolean
A "true" or "false" value, from the JSON "true" or "false" value
-
object
An unordered set of properties mapping a string to an instance, from the JSON "object" value
-
array
An ordered list of instances, from the JSON "array" value
-
number
An arbitrary-precision, base-10 decimal number value, from the JSON "number" value
-
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 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. - -
- -
- - 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: - -
    -
  • both are null; or
    • -
  • both are true; or
    • -
  • both are false; or
    • -
  • 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.
    • -
- - - 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 no way to define multiple properties with the same key, - and mere formatting differences (indentation, placement of commas, trailing - zeros) are insignificant. - -
- -
- - 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. - - - In this case, annotations still apply; but most validation keywords will not be useful, - as they will always pass or always fail. - - - 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. - -
-
- -
- - 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 - "application/schema-instance+json". The "application/schema+json" media - type is defined to offer a superset of the - fragment identifier syntax and semantics provided by - "application/schema-instance+json". - - - A JSON Schema MUST be an object or a boolean. - -
- - 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 -
-
assertions
-
- produce a boolean result when applied to an instance -
-
annotations
-
- attach information to an instance for application use -
-
applicators
-
- apply one or more subschemas to a particular location - in the instance, and combine or modify their results -
-
reserved locations
-
- do not directly affect results, but reserve a place - for a specific purpose to ensure interoperability -
-
- - Keywords may fall into multiple categories, although applicators - SHOULD only produce assertion results based on their subschemas' - results. They should not define additional constraints independent - of their subschemas. - - - Keywords which are properties within the same schema object are referred to as adjacent keywords. - - - Extension keywords, meaning those defined outside of this document - and its 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 . - - - An empty schema is a JSON Schema with no properties. - -
-
- - 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). - -
-
true
-
- Always passes validation, as if the empty schema {} -
- -
false
-
- Always fails validation, as if the schema { "not": {} } -
-
- - While the empty schema object is unambiguous, there are many - possible equivalents to the "false" schema. Using the boolean - values ensures that the intent is clear to both human readers - and implementations. - -
-
- - 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 interface generation, will - involve different sets of vocabularies. - - - Vocabularies are the primary unit of re-use in JSON Schema, as schema - authors can indicate what vocabularies are required or optional in - order to process the schema. Since vocabularies are identified by IRIs - in the meta-schema, generic implementations can load extensions to support - previously unknown vocabularies. While keywords can be supported outside - of any vocabulary, there is no analogous mechanism to indicate individual - keyword usage. - - - A schema vocabulary can be defined by anything from an informal description - to a standards proposal, depending on the audience and interoperability - expectations. In particular, in order to facilitate vocabulary use within - non-public organizations, a vocabulary specification need not be published - outside of its scope of use. - -
-
- - 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. - - - Typically, a meta-schema will specify a set of vocabularies, and validate - schemas that conform to the syntax of those vocabularies. However, meta-schemas - and vocabularies are separate in order to allow meta-schemas to validate - schema 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. - -
-
- - A JSON Schema resource is a schema which is - canonically identified by an - absolute IRI. Schema resources MAY - also be identified by IRIs, including IRIs with fragments, - if the resulting secondary resource (as defined by - section 3.5 of RFC 3986) is identical - to the primary resource. This can occur with the empty fragment, - or when one schema resource is embedded 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 . - - 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 Schema document and resource concepts will be - clarified in a future draft. - - - - Some keywords take schemas themselves, allowing JSON Schemas to be nested: - - - - In this example document, the schema titled "array item" is a subschema, - and the schema titled "root" is the root schema. - - - As with the root schema, a subschema is either an object or a boolean. - - - As discussed in , 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. - -
-
- -
- -
- - In accordance with section 3.1 of RFC 6839, - 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 fragment identification - syntax defined for "application/json".) - - - Additionally, the "application/schema+json" media type supports two - fragment 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. - 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. - - - Per the W3C's - best practices for fragment identifiers, - plain name fragment identifiers in "application/schema+json" are reserved for referencing - locally named schemas. - - - Plain name fragments MUST start with a letter ([A-Za-z]) or underscore ("_"), - followed by any number of letters, digits ([0-9]), hyphens ("-"), - underscores ("_"), and periods ("."). This matches the US-ASCII part of XML's - NCName production, which allows for compatibility - with the recommended plain name syntax for - XML-based media types. - - - All fragment identifiers that do - not match the JSON Pointer syntax MUST be 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 section. - -
- -
- -
- - An instance may be any valid JSON value as defined by JSON. - JSON Schema imposes no restrictions on type: JSON Schema can describe any JSON - value, including, for example, null. - -
- -
- - 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. - -
- -
- - 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. - -
- -
- - 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, section 21.2.1. - - - Unless otherwise specified by a keyword, regular expressions MUST NOT be - considered to be implicitly anchored at either end. All regular expression - keywords in this specification and its companion documents are un-anchored. - - - Regular expressions SHOULD be built with the "u" flag (or equivalent) to provide - Unicode support, or processed in such a way which provides Unicode support as - defined by ECMA-262. - - - Furthermore, given the high disparity in regular expression constructs support, - schema authors SHOULD limit themselves to the following regular expression - tokens: - -
    -
  • individual Unicode characters, as defined by the JSON specification;
    • -
  • 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 ("+?", "*?", "??");
    • -
  • range quantifiers: "{x}" (exactly x occurrences), "{x,y}" (at least x, at - most y, occurrences), {x,} (x occurrences or more), and their lazy - versions;
    • -
  • the beginning-of-input ("^") and end-of-input ("$") anchors;
    • -
  • simple grouping ("(...)") and alternation ("|").
    • -
- - - 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". - -
- -
- - 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 explicitly document such support. - - - 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. - - -
- - 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 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. - -
- -
- - 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. - -
-
- -
- -
- - 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 fit. - Applicators apply subschemas to parts of the instance and combine - their results. - - - Extension keywords SHOULD stay within these categories, keeping in mind - that annotations in particular are extremely flexible. Complex behavior - is usually better delegated to applications on the basis of annotation - data than implemented directly as schema keywords. However, extension - keywords MAY define 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. The interactions of those - keyword results to produce the schema object results are governed by - , while the - relationship of subschema results to the results of the applicator - keyword that applied them is described by . - - - Evaluation of a parent schema object can complete once all of its - subschemas have been evaluated, although in some circumstances evaluation - may be short-circuited due to assertion results. When annotations are - being collected, 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. - -
- - 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. - - - 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 IRI, which is found through the lexical - structure of the JSON document. The "$id", "$ref", and - "$dynamicRef" core keywords, and the "base" JSON Hyper-Schema - keyword, are examples of this sort of behavior. - - - Note that some keywords, such as "$schema", apply to the lexical - scope of the entire schema resource, and therefore MUST only - appear in a schema resource's root schema. - - - Other keywords may take into account the dynamic scope that - exists during the evaluation of a schema, typically together - with an instance document. - The outermost dynamic scope is the schema object at - which processing begins, even if it is not a schema resource root. - The path from this root schema to any particular keyword (that - includes any "$ref" and "$dynamicRef" keywords that may have - been resolved) is considered the keyword's "evaluation path." - - - Lexical and dynamic scopes align until a reference keyword - is encountered. While following the reference keyword moves processing - from one lexical scope into a different one, from the perspective - of dynamic scope, following a reference is no different from descending - into a subschema present as a value. A keyword on the far side of - that reference that resolves information through the dynamic scope - will consider the originating side of the reference to be their - dynamic 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. - -
-
- - Keyword behavior MAY be defined in terms of the annotation results - of subschemas 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. - -
-
- - 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 contribute annotations, - the lack of annotation results may indirectly change the behavior - of other keywords. - - - In some cases, the missing keyword assertion behavior of a keyword is - identical to that produced by a certain value, and keyword definitions - SHOULD note such values where known. However, even if the value which - produces the default behavior would produce annotation results if - present, the default behavior still MUST NOT result in annotations. - - - 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 - "" and - "" 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 define IRIs for a schema, or affect how such IRIs are - resolved in references, or both. - The Core vocabulary defined in this document defines several - identifying keywords, most notably "$id". - - - Canonical schema IRIs MUST NOT change while processing an instance, but - keywords that affect IRI-reference resolution MAY have behavior that - is only fully determined at runtime. - - - While custom identifier keywords are possible, vocabulary designers should - take care not to disrupt the functioning of core keywords. For example, - the "$dynamicAnchor" keyword in this specification limits its IRI resolution - effects to the matching "$dynamicRef" keyword, leaving the behavior - of "$ref" undisturbed. - -
-
- - Applicators allow for building more complex schemas than can be accomplished - with a single schema object. Evaluation of an instance against a - schema document begins by applying - the root schema 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 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 - 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 results from subschemas - are preserved in accordance with so that applications - can decide how to interpret multiple values. Applicator keywords - do not play a direct role in this preservation. - -
- - As noted in , 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 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 - "$ref", the referenced schema can be determined - by static analysis of the schema document's lexical scope. Others, - such as "$dynamicRef" (with "$dynamicAnchor"), may make use of dynamic - scoping, and therefore only be resolvable in the process of evaluating - the schema with an instance. - -
-
- -
- - 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. - - - JSON Schema implementations produce a single boolean result when evaluating - an instance against schema assertions. - - - An instance can only fail an assertion that is present in the schema. - - -
- - 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. - - - For example, the "maxLength" keyword from the companion - validation vocabulary: - will only restrict certain strings - (that 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 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: - - - - If "maxLength" also restricted the instance type to be a string, - then this would be substantially more cumbersome to express because - the example as written would 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. - -
-
- -
- - 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 - calculated based on the instance contents. - - - Annotations are attached to specific locations in an instance. - Since many subschemas can be applied to any single - location, applications may need to decide how to handle differing - annotation values being attached to the same instance location by - the same schema keyword in different schema objects. - - - Unlike assertion results, annotation data can take a wide variety of forms, - which are provided to applications to use as they see fit. JSON Schema - implementations are not expected to make use of the collected information - on behalf of applications. - - - Unless otherwise specified, the value of an annotation keyword - is the keyword's value. However, other behaviors are possible. - For example, JSON Hyper-Schema's - "links" keyword is a complex annotation that produces a value based - in part on the instance data. - - - While "short-circuit" evaluation is possible for assertions, collecting - annotations requires examining all schemas that apply to an instance - location, 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. - - -
- - 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. - - - 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. -
    • -
  • - 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. -
    • -
  • - The attached value(s) -
    • -
-
- - 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. - - - For example, consider this schema, which uses annotations and assertions from - the Validation specification: - - - 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. - - - 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" value will be used, and any additional, more generic - "default" values will be silently ignored. Let's also assume that they - agree that all "description" text is to be used, starting with the most - generic, and ending with the most specific. This requires the schema - author to write descriptions that work when combined in this way. - - - The application can use the evaluation path to determine which - values are which. The values in the feature's immediate "enabled" - property schema are more specific, while the values under the re-usable - schema that is referenced to with "$ref" are more generic. The evaluation - path will show whether each value was found by crossing a - "$ref" or not. - - - Feature A will therefore use a default value of true, while Feature B - will use the generic default value of null. Feature A will only - have the generic description from the "enabledToggle" schema, while - Feature B will use that description, and also append its locally - defined description that explains how to interpret a null value. - - - Note that there are other reasonable approaches that a different application - 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. - -
-
- - Schema objects that produce a false assertion result MUST NOT - produce any annotation results, whether from their own keywords - or from keywords in subschemas. - - - Note that the overall schema results may still include annotations - collected from other schema locations. Given this schema: - - - - Against the instance "This is a string", the - title annotation "Integer Value" is discarded because the type assertion - in that schema object fails. The title annotation "String Value" - is kept, as the instance passes the string type assertions. - -
-
-
-
- - 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 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 - unrecognized - extension keywords that reserve locations for re-usable schemas may have - undesirable interactions with references in certain circumstances. - -
-
- - 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. - - - Keywords MAY be defined to use JSON Pointers or Relative JSON Pointers to 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. - -
-
-
- - Keywords declared in this section, which all begin with "$", make up - the JSON Schema Core vocabulary. These keywords are either required in - order to process any schema or meta-schema, including those split across - multiple documents, or exist to reserve keywords for purposes that - require guaranteed interoperability. - - - The Core vocabulary MUST be considered mandatory at all times, in order - to bootstrap the processing of further vocabularies. Meta-schemas - that use the "$vocabulary" 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 "$vocabulary" - is present but the Core vocabulary is not included. However, it - is RECOMMENDED that implementations detect these cases and raise - an error when they occur. It is not meaningful to declare that - a meta-schema optionally uses Core. - - - Meta-schemas that do not use "$vocabulary" MUST be considered to - require the Core vocabulary as if its IRI were present with a value of true. - - - The current IRI for the Core vocabulary is: - <https://json-schema.org/draft/next/vocab/core>. - - - The current IRI for the corresponding meta-schema is: - . - - - The "$" prefix is reserved for use by the Core vocabulary. - Vocabulary extensions MUST NOT define new keywords that begin with "$". - - -
- - 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 "$schema" keyword. - - - The meta-schema serves two purposes: - -
-
Declaring the vocabularies in use
-
- The "$vocabulary" keyword, when it appears in a meta-schema, declares - which vocabularies are available to be used in schemas that refer - to that meta-schema. Vocabularies define keyword semantics, - as well as their general syntax. -
-
Describing valid schema syntax
-
- A schema MUST successfully validate against its meta-schema, which - constrains the syntax of the available keywords. The syntax described - is expected to be compatible with the vocabularies declared; while - it is possible to describe an incompatible syntax, such a meta-schema - would be unlikely to be useful. -
-
- - Meta-schemas are separate from vocabularies to allow for - vocabularies to be combined in different ways, and for meta-schema authors - to impose additional constraints such as forbidding certain keywords, or - performing unusually strict syntactical validation, as might be done - during a development and testing cycle. Each vocabulary typically identifies - a meta-schema consisting only of the 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 "$schema" keyword is both used as a JSON Schema dialect identifier and - as the identifier of a resource which is itself a JSON Schema, which describes the - set of valid schemas written for this particular dialect. - - - The value of this keyword MUST be a IRI - (containing a scheme) and this IRI MUST be normalized. - The current schema MUST be valid against the meta-schema identified by this IRI. - - - If this IRI identifies a retrievable resource, that resource SHOULD be of - media type "application/schema+json". - - - The "$schema" keyword SHOULD be used in the document root schema object, - and MAY be used in the root schema objects of embedded schema resources. - It MUST NOT appear in non-resource root schema objects. If absent from - the document root schema, the resulting behavior is implementation-defined, - but MUST fall within 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
    • -
- - - Values for this property are defined elsewhere in this and other documents, - and by other parties. - -
-
- - The "$vocabulary" keyword is used in meta-schemas to identify the - vocabularies available for use in schemas described by that meta-schema, - and whether each vocabulary is required or optional. Together, this - information forms a dialect. - - - The value of this keyword MUST be an object. The property names in the - object MUST be IRIs (containing a scheme) and each IRI MUST be normalized. - Each IRI that appears as a property name identifies a specific set of - keywords and their semantics. - - - The IRI MAY be a URL, but the nature of the retrievable resource is - currently undefined, and reserved for future use. Vocabulary authors - MAY use the URL of the vocabulary specification, in a human-readable - media type such as text/html or text/plain, as the vocabulary IRI. - - Vocabulary documents may be added in forthcoming drafts. - For now, identifying the keyword set is deemed sufficient as that, - along with meta-schema validation, is how the current "vocabularies" - work today. Any future vocabulary document format will be specified - as a JSON document, so using text/html or other non-JSON formats - in the meantime will not produce any future ambiguity. - - - - The values of the object properties MUST be booleans. - If the value is true, then the vocabulary MUST be considered to be required. - If the value is false, then the vocabulary MUST be considered to be optional. - -
- - A schema is said to use a dialect and its constituent vocabularies if it is - associated with a meta-schema defining the dialect with "$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 . - - - 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 the vocabulary, regardless of whether that vocabulary - is required or optional. - - - Any vocabulary that is not present in "$vocabulary" MUST NOT be made - available for use in schemas described by that meta-schema, except for - the core vocabulary as specified by the introduction to - . - - - Implementations that do not support a vocabulary required by a schema - MUST refuse to process that schema. - - - Implementations that do not support a vocabulary that is optionally used - by a schema SHOULD proceed with processing the schema. The keywords will - be considered to be unrecognized keywords as addressed by - . Note that since - the recommended behavior for such keywords is to collect them as - annotations, vocabularies consisting only of annotations will have - the same behavior when used optionally whether the implementation - supports them or not. This allows annotation-only vocabularies to - be supported without custom code, even in implementations that do - not support providing custom code for extension vocabularies. - -
-
- - The "$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. - - - The "$vocabulary" keyword MUST be ignored in schema resources that - are not being processed as a meta-schema. This allows validating - a meta-schema M against its own meta-schema M' without requiring - the validator to understand the vocabularies declared by M. - -
-
- - Keywords from different vocabularies, as well as non-vocabulary - extension keywords, can have identical names. These are not - considered to be the same keyword from the perspective of - enabling or disabling them through "$vocabulary". - - - In particular the keywords defined in this specification and its - companion documents MUST be considered to be vocabulary keywords, - with availability governed by "$vocabulary" even in implementations - that do not support any extension vocabularies. - - - Guidance regarding vocabularies with identically-named keywords is provided - in . - -
-
- - If "$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 "$schema" keyword. - This is how behavior (such as Hyper-Schema usage) has been - recognized prior to the existence of vocabularies. - - - If the meta-schema, as referenced by the schema, is not recognized, - or is missing, then the behavior is implementation-defined. - If the implementation - proceeds with processing the schema, it MUST assume the use of the - core vocabulary. If the implementation is built for a specific purpose, - then it SHOULD assume the use of all of the most relevant vocabularies - for that purpose. - - - For example, an implementation that is a validator - SHOULD assume the use of all vocabularies in this - specification and the companion Validation specification. - -
-
- - Note that the processing restrictions on "$vocabulary" mean that - meta-schemas that reference other meta-schemas using "$ref" or - similar keywords do not automatically inherit the vocabulary - declarations of those other meta-schemas. All such declarations - must be repeated in the root of each schema document intended - for use as a meta-schema. This is demonstrated in - the example meta-schema. - - This requirement allows implementations to find all vocabulary - requirement information in a single place for each meta-schema. - As schema extensibility means that there are endless potential - ways to combine more fine-grained meta-schemas by reference, - requiring implementations to anticipate all possibilities and - search for vocabularies in referenced meta-schemas would - be overly burdensome. - - -
-
-
- - Updated vocabulary and meta-schema IRIs MAY be published between - specification drafts in order to correct errors. Implementations - SHOULD consider IRIs dated after this specification draft and - before the next to indicate the same syntax and semantics - as those listed here. - -
-
- -
- - To differentiate between schemas in a vast ecosystem, schemas are - identified by IRI, and can embed references - to other schemas by specifying their IRI. - - - Several keywords can accept a relative IRI-reference, - or a value used to construct a relative IRI-reference. For these keywords, - it is necessary to establish a base IRI in order to resolve the reference. - - -
- - The "$id" keyword identifies a schema resource with its - canonical IRI. - - - Note that this IRI is an identifier and not necessarily a network locator. - In the case of a network-addressable URL, a schema need not be downloadable - from its canonical IRI. - - - If present, the value for this keyword MUST be a string, and MUST represent a - valid IRI-reference. This IRI-reference - SHOULD be normalized, and MUST resolve to an - absolute-IRI (without a fragment). - - - The resulting absolute-IRI serves as the base IRI for relative IRI-references - in keywords within the schema resource, in accordance with - RFC 3987 section 6.5 and - RFC 3986 section 5.1.1 regarding base IRIs - embedded in content. - - - The presence of "$id" in a subschema indicates that the subschema constitutes - a distinct schema resource within a single schema document. Furthermore, - in accordance with RFC 3987 section 6.5 and - RFC 3986 section 5.1.2 regarding - encapsulating entities, if an "$id" in a subschema is a relative - IRI-reference, the base IRI for resolving that reference is the IRI of - the parent schema resource. Note that an "$id" consisting of an empty IRI or - of the empty fragment only will result in the embedded resource having - the same IRI as the encapsulating resource, which SHOULD be considered - an error per . - - - If no parent schema object explicitly identifies itself as a resource - with "$id", the base IRI is that of the entire document, as established - by the steps given in the previous section. - -
- - The root schema of a JSON Schema document SHOULD contain an "$id" keyword - with an absolute-IRI (containing a scheme, - but no fragment). - -
-
-
- - Using JSON Pointer fragments requires knowledge of the structure of the schema. - When writing schema documents with the intention to provide re-usable - schemas, it may be preferable to use a plain name fragment that is not tied to - any particular structural location. This allows a subschema to be relocated - without requiring JSON Pointer references to be updated. - - - The "$anchor" and "$dynamicAnchor" keywords are used to specify such - fragments. They are identifier keywords that can only be used to create - plain name fragments, rather than absolute IRIs as seen with "$id". - - - The base IRI to which the resulting fragment is appended is the canonical - IRI of the schema resource containing the "$anchor" or "$dynamicAnchor" - in question. As discussed in the previous section, this is either the - nearest "$id" in the same or parent schema object, - or the base IRI for the document as determined according to - RFC 3987 and - RFC 3986. - - - Separately from the usual usage of IRIs, "$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" - 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 - . - - Note that the anchor string does not include the "#" character, - as it is not a IRI-reference. An "$anchor": "foo" becomes the - fragment "#foo" when used in a IRI. See below for full examples. - - -
- -
- - A schema MAY (and likely will) have multiple IRIs, but there is no way - for an IRI to identify more than one schema. When multiple schemas - attempt to identify as the same IRI through the use of "$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. - -
- -
- - 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 provides the ability to validate recursive structures through - self-reference. - - - The resolved IRI produced by these keywords is not necessarily a network - locator, only an identifier. A schema need not be downloadable from the - address 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. - - -
- - The "$ref" keyword is an applicator that is used to reference a statically - identified schema. Its results are the results of the referenced schema. - - Note that this definition of how the results are determined means that - other keywords can appear alongside of "$ref" in the same schema object. - - - - The value of the "$ref" keyword MUST be a string which is a IRI-Reference. - Resolved against the current IRI base, it produces the IRI of the schema - to apply. This resolution is safe to perform on schema load, as the - process of evaluating an instance cannot change how the reference resolves. - -
- -
- - The "$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. - - - Together with "$dynamicAnchor", "$dynamicRef" implements a cooperative - extension mechanism that is primarily useful with recursive schemas - (schemas that reference themselves). The extension point is defined with - "$dynamicAnchor" and only exhibits runtime dynamic behavior when referenced - with "$dynamicRef". - - - The value of the "$dynamicRef" property MUST be a string which is a - IRI-Reference that contains a valid plain name - fragment. Resolved against the current IRI base, it indicates - the schema resource used as the starting point for runtime resolution. - This initial resolution is safe to perform on schema load. - - - The schema to apply is the outermost schema resource in the - dynamic scope that defines a - "$dynamicAnchor" that matches the plain name fragment in the initially - resolved IRI. - - - For a full example using these keyword, see . - - The difference between the hyper-schema meta-schema in pre-2019 - drafts and an this draft dramatically demonstrates the utility - of these keywords. - - -
- -
- -
- - The "$defs" keyword reserves a location for schema - authors to inline re-usable JSON Schemas into a more general schema. - The keyword does not directly affect the validation result. - - - This keyword's value MUST be an object. - Each member value of this object MUST be a valid JSON Schema. - - - As an example, here is a schema describing an array of positive - integers, where the positive integer constraint is a subschema in - "$defs": - - -
-
- -
- - This keyword reserves a location for comments from schema authors - to readers or maintainers of the schema. - - - The value of this keyword MUST be a string. Implementations MUST NOT present this - string to end users. Tools for editing schemas SHOULD support displaying 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 "$comment" beyond what is described in this - specification. - - - Tools that translate other media types or programming languages - to and from application/schema+json MAY choose to convert that media type or - programming language's native comments to or from "$comment" values. - The behavior of such translation when both native comments and "$comment" - properties are present is implementation-dependent. - - - Implementations MAY strip "$comment" values at any point during processing. - In particular, this allows for shortening schemas when the size of deployed - schemas is a concern. - - - Implementations MUST NOT take any other action based on the presence, absence, - or contents of "$comment" properties. In particular, the value of "$comment" - MUST NOT be collected as an annotation result. - -
-
- -
- - -
-
- - RFC 3987 Section 6.5 and - RFC 3986 Section 5.1 defines how to determine the - default base IRI of a document. - - - Informatively, the initial base IRI of a schema is the IRI at which it was - found, whether that was a network location, a local filesystem, or any other - situation identifiable by a IRI of any known scheme. - - - If a schema document defines no explicit base IRI with "$id" - (embedded in content), the base IRI is that determined per - RFC 3987 Section 6.5 and - RFC 3986 section 5. - - - If no source is known, or no IRI scheme is known for the source, a suitable - implementation-specific default IRI MAY be used as described in - RFC 3987 Section 6.5 and - RFC 3986 Section 5.1.4. It is RECOMMENDED - that implementations document any default base IRI that they assume. - - - If a schema object is embedded in a document of another media type, then - the initial base IRI is determined according to the rules of that - media type. - - - Unless the "$id" keyword described in an earlier section is present in the - root schema, this base IRI SHOULD be considered the canonical IRI of the - schema document's root schema resource. - -
- -
- - 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. - - - Implementations SHOULD be able to associate arbitrary IRIs with an arbitrary - schema and/or automatically associate a schema's "$id"-given IRI, depending - on the trust that the validator has in the schema. Such IRIs and schemas - can be supplied to an implementation prior to processing instances, or may - be noted within a schema document as it is processed, producing associations - as shown in . - -
- -
- - Implementations MUST recognize a schema as a meta-schema if it - is being examined because it was identified as such by another - schema's "$schema" keyword. This means that a single schema - document might sometimes be considered a regular schema, and - other times be considered a meta-schema. - - - In the case of examining a schema which is its own meta-schema, - when an implementation begins processing it as a regular schema, - it is processed under those rules. However, when loaded a second - time as a result of checking its own "$schema" value, it is treated - as a meta-schema. So the same document is processed both ways in - the course of one session. - - - Implementations MAY allow a schema to be explicitly passed as a meta-schema, - for implementation-specific purposes, such as pre-loading a commonly - used meta-schema and checking its vocabulary support requirements - up front. Meta-schema authors MUST NOT expect such features to be - interoperable across implementations. - -
-
- -
- - Schemas can be identified by any IRI that has been given to them, including - a JSON Pointer or their IRI given directly by "$id". In all cases, - dereferencing a "$ref" reference involves first resolving its value as a - IRI reference against the current base IRI per - RFC 3986. - - - If the resulting IRI identifies a schema within the current document, or - within another schema document that has been made available to the implementation, - then that schema SHOULD be used automatically. - - - For example, consider this schema: - - - - - When an implementation encounters the <#/$defs/single> schema, - it resolves the "$anchor" value as a fragment name against the current - base IRI to form <https://example.net/root.json#item>. - - - When an implementation then looks inside the <#/items> schema, it - encounters the <#item> reference, and resolves this to - <https://example.net/root.json#item>, which it has seen defined in - this same document and can therefore use automatically. - - - When an implementation encounters the reference to "other.json", it resolves - this to <https://example.net/other.json>, which is not defined in this - document. If a schema with that identifier has otherwise been supplied to - the implementation, it can also be used automatically. - - What should implementations do when the referenced schema is not known? - Are there circumstances in which automatic network dereferencing is - allowed? A same origin policy? A user-configurable option? In the - case of an evolving API 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. - - - -
- - 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, 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, 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 document and referenced, applications and schemas - SHOULD NOT use such IRIs to identify embedded schema resources or - locations within them. - - - Consider the following schema document that contains another - schema resource embedded within it: - - - - The IRI "https://example.com/foo#/items" points to the "items" schema, - which is an embedded resource. The canonical IRI of that schema - resource, however, is "https://example.com/bar". - - - For the "additionalProperties" schema within that embedded resource, - the IRI "https://example.com/foo#/items/additionalProperties" points - to the correct object, but that object's IRI relative to its resource's - canonical IRI is "https://example.com/bar#/additionalProperties". - - - Now consider the following two schema resources linked by reference - using a IRI value for "$ref": - - - - - Here we see that "https://example.com/bar#/additionalProperties", - using a JSON Pointer fragment appended to the canonical IRI of - the "bar" schema resource, is still valid, while - "https://example.com/foo#/items/additionalProperties", which relied - on a JSON Pointer fragment appended to the canonical IRI of the - "foo" schema resource, no longer resolves to anything. - - - Note also that "https://example.com/foo#/items" is valid in both - arrangements, but resolves to a different value. This IRI ends up - functioning similarly to a retrieval IRI for a resource. While this IRI - is valid, it is more robust to use the "$id" of the embedded or referenced - resource unless it is specifically desired to identify the object containing - the "$ref" in the second (non-embedded) arrangement. - - - An implementation MAY choose not to support addressing schema resource - contents by IRIs using a base other than the resource's canonical IRI, - plus a JSON Pointer fragment relative to that base. Therefore, schema - authors SHOULD NOT rely on such IRIs, as using them may reduce interoperability. - - This is to avoid requiring implementations to keep track of a whole - stack of possible base IRIs and JSON Pointer fragments for each, - given that all but one will be fragile if the schema resources - are reorganized. Some - have argued that this is easy so there is - no point in forbidding it, while others have argued that it complicates - schema identification and should be forbidden. Feedback on this - topic is encouraged. - After some discussion, we feel that we need to remove the use of - "canonical" in favour of talking about JSON Pointers which reference - across schema resource boundaries as undefined or even forbidden behavior - (https://github.com/json-schema-org/json-schema-spec/issues/937, - https://github.com/json-schema-org/json-schema-spec/issues/1183) - - - - Further examples of such non-canonical IRI construction, as well as - the appropriate canonical IRI-based fragments to use instead, - are provided in . - -
-
- -
- - 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. - - - Each embedded Schema Resource MUST be treated as an individual Schema Resource, following standard - schema loading and processing requirements, including determining vocabulary support. - -
- - The bundling process for creating a Compound Schema Document is defined as taking - references (such as "$ref") to an external Schema Resource and embedding the referenced - Schema Resources within the referring document. Bundling SHOULD be done in such a way that - all IRIs (used for referencing) in the base document and any referenced/embedded - documents do not require altering. - - - Each embedded JSON Schema Resource MUST identify itself with a IRI using the "$id" keyword, - and SHOULD make use of the "$schema" keyword to identify the dialect it is using, in the root of the - schema resource. It is RECOMMENDED that the IRI identifier value of "$id" be an Absolute IRI. - - - When the Schema Resource referenced by a by-reference applicator is bundled, it is RECOMMENDED that - the Schema Resource be located as a value of a "$defs" object at the containing schema's root. - The key of the "$defs" for the now embedded Schema Resource MAY be the "$id" of the bundled schema - or some other form of application defined unique identifer (such as a UUID). This key is not - intended to be referenced in JSON Schema, but may be used by an application to aid the - bundling process. - - - A Schema Resource MAY be embedded in a location other than "$defs" where the location is defined - as a schema value. - - - A Bundled Schema Resource MUST NOT be bundled by replacing the schema object from which it was - referenced, or by wrapping the Schema Resource in other applicator keywords. - - - In order to produce identical output, references in the containing schema document to the - previously external Schema Resources MUST NOT be changed, and now resolve to a schema using the - "$id" of an embedded Schema Resource. Such identical output includes validation evaluation and IRIs - or paths used in resulting annotations or errors. - - - While the bundling process will often be the main method for creating a Compound Schema Document, - it is also possible and expected that some will be created by hand, potentially without individual - Schema Resources existing on their own previously. - -
-
- - When multiple schema resources are present in a single document, - schema resources which do not define with which dialect they should be processed - MUST be processed with the same dialect as the enclosing resource. - - - Since any schema that can be referenced can also be embedded, embedded schema resources MAY - specify different processing dialects using the "$schema" values from their enclosing resource. - -
-
- - 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 that an alternate - validation process be provided in order to validate Schema Documents. Each Schema Resource - SHOULD be separately validated against its associated meta-schema. - - If you know a schema is what's being validated, you can identify if the schemas - is a Compound Schema Document or not, by way of use of "$id", which identifies an - embedded resource when used not at the document's root. - - - - A Compound Schema Document in which all embedded resources identify as using the same - dialect, or in which "$schema" is omitted and therefore defaults to that of the enclosing resource, - MAY be validated by applying the appropriate meta-schema. - -
-
- -
-
- - 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. - -
- -
- - Subschema objects (or booleans) are recognized by their use with known - applicator keywords or with location-reserving keywords such as - "$defs" that take one or more subschemas - as a value. These keywords may be "$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 - "$id". Therefore, having a reference target in such an unrecognized - structure cannot be reliably implemented, and the resulting behavior - is undefined. Similarly, a reference target under a known keyword, - for which the value is known not to be a schema, results in undefined - behavior in order to avoid burdening implementations with the need - to detect such targets. - - These scenarios are analogous to fetching a schema over HTTP - but receiving a response with a Content-Type other than - application/schema+json. An implementation can certainly - try to interpret it as a schema, but the origin server - offered no guarantee that it actually is any such thing. - Therefore, interpreting it as such has security implications - and may produce unpredictable results. - - - - Note that single-level custom keywords with identical syntax and - semantics to "$defs" do not allow for any intervening "$id" keywords, - and therefore will behave correctly under implementations that attempt - to use any reference target as a schema. However, this behavior is - implementation-specific and MUST NOT be relied upon for interoperability. - -
-
- -
- -
- - - 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. - - -
- - 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. - - - - In HTTP, such links can be attached to any response using the - Link header. An example of such a header would be: - - - ; rel="describedby" -]]> - -
- -
- - When used for hypermedia systems over a network, - HTTP 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 frequently than - necessary, when it's instead possible to cache a schema for a long period of - time. - - - HTTP servers SHOULD set long-lived caching headers on JSON Schemas. - HTTP clients SHOULD observe caching headers and not re-request documents within - their freshness period. - Distributed systems SHOULD make use of a shared cache and/or caching proxy. - - - Clients SHOULD set or prepend a User-Agent header specific to the JSON Schema - implementation or software product. Since symbols are listed in decreasing order - of significance, the JSON Schema library name/version should precede the more - generic HTTP library name (if any). For example: - - - - Clients SHOULD be able to make requests with a "From" header so that server - operators can contact the owner of a potentially misbehaving script. - -
- -
- -
- -
- -
- - This section defines a vocabulary of applicator keywords that - are RECOMMENDED for use as the basis of other vocabularies. - - - 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. - - - 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: - . - -
- - Schema keywords typically operate independently, without - affecting each other's outcomes. - - - 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" -
    • -
  • - "items", whose behavior is defined in terms of "prefixItems" -
    • -
  • - "contains", whose behavior is affected by the presence and value of - "minContains" -
    • -
-
- -
- - 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. - - - - 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. - - -
- - 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. - -
- - 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 all schemas defined by this keyword's value. - -
- -
- - 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 at least one schema defined by this keyword's value. - Note that when annotations are being collected, all subschemas MUST - be examined so that annotations are collected from each subschema - that validates successfully. - -
- -
- - 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. - -
- -
- - 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. - -
-
- -
- - 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. - - - 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 schema, and when - "if" is not present, both "then" and "else" MUST be - entirely ignored. - -
- - This keyword's value MUST be a valid JSON Schema. - - - This validation outcome of this keyword's subschema - has no direct effect on the overall validation - result. Rather, it controls which of the "then" - or "else" keywords are evaluated. - - - Instances that successfully validate against this - keyword's subschema MUST also 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 - 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". - -
-
- - This keyword's value MUST be a valid JSON Schema. - - - When "if" is present, and the instance successfully - validates against its subschema, then validation - succeeds against this keyword if the instance also - successfully validates against this keyword's subschema. - - - This keyword has no effect when "if" is absent, or - when the instance fails to validate against its - subschema. Implementations MUST NOT evaluate - the instance against this keyword, for either validation - or annotation collection purposes, in such cases. - -
-
- - This keyword's value MUST be a valid JSON Schema. - - - When "if" is present, and the instance fails to - validate against its subschema, then validation - succeeds against this keyword if the instance - successfully validates against this keyword's subschema. - - - This keyword has no effect when "if" is absent, or - when the instance successfully validates against its - subschema. Implementations MUST NOT evaluate - the instance against this keyword, for either validation - or annotation collection purposes, in such cases. - -
-
- - This keyword specifies subschemas that are evaluated if the instance - is an object and contains a certain property. - - - This keyword's value MUST be an object. - Each value in the object MUST be a valid JSON Schema. - - - If the object key is a property in the instance, the entire - instance must validate against the subschema. Its use is - dependent on the presence of the property. - - - Omitting this keyword has the same behavior as an empty object. - -
-
- - This keyword specifies subschemas that are evaluated if the instance is - an object and contains a certain property with a certain string value. - - - This keyword's value MUST be an object. Each value in the object MUST be - an object whose values MUST be valid JSON Schemas. - - - If the outer object key is a property in the instance and the inner - object key is equal to the value of that property, the entire instance - must validate against the schema. Its use is dependent on the presence - and value of the property. - - - Omitting this keyword has the same behavior as an empty object. - -
-
-
-
- - 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. - -
-
- - 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 subschema at the same position, if any. This keyword - does not constrain the length of the array. Only array positions - present in both the keyword's value 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". - - - Omitting this keyword has the same assertion behavior as - an empty array. - -
- -
- - The value of "items" MUST be a valid JSON Schema. - - - This keyword applies its subschema to all instance elements - at indexes greater than the length of the "prefixItems" array - in the same schema object, as reported by the annotation result - of that "prefixItems" keyword. If no such annotation - result exists, "items" applies its subschema to all instance - array elements. - - Note that the behavior of "items" without "prefixItems" is - identical to that of the schema form of "items" in prior drafts. - When "prefixItems" is present, the behavior of "items" is - identical to the former "additionalItems" keyword. - - - - If the "items" subschema is applied to any - positions within the instance array, it produces an - annotation result of boolean true, indicating that all remaining array - elements have been evaluated against this keyword's subschema. - This annotation affects the behavior of "unevaluatedItems" in the - Unevaluated vocabulary. - - - Omitting this keyword has the same assertion behavior as - an empty schema. - - - Implementations MAY choose to implement or optimize this keyword - in another way that produces the same effect, such as by directly - checking for the presence and size of a "prefixItems" array. - Implementations that do not support annotation collection MUST do so. - -
-
- -
-
- - The value of "properties" MUST be an object. - Each value of this object MUST be a valid JSON Schema. - - - Validation succeeds if, for each name that appears in both - the instance and as a name within this keyword's value, the child - instance for that name successfully validates against the - corresponding schema. - - - The annotation result of this keyword is the set of instance - property names which are also present under this keyword. - This annotation affects the behavior of "additionalProperties" (in - this vocabulary) and "unevaluatedProperties" in the Unevaluated vocabulary. - - - Omitting this keyword has the same assertion behavior as - an empty object. - -
- -
- - 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 Schema. - - - Validation succeeds if, for each instance name that matches any - regular expressions that appear as a property name in this keyword's value, - the child instance for that name successfully validates against each - schema that corresponds to a matching regular expression. Recall: regular - expressions are not implicitly anchored. - - - The annotation result of this keyword is the set of instance - property names matched by at least one property under this keyword. - This annotation affects the behavior of "additionalProperties" (in this - vocabulary) and "unevaluatedProperties" (in the Unevaluated vocabulary). - - - Omitting this keyword has the same assertion behavior as - an empty object. - -
- -
- - The value of "additionalProperties" MUST be a valid JSON Schema. - - - The behavior of this keyword depends on the presence and - annotation results of "properties" and "patternProperties" - within the same schema object. - Validation with "additionalProperties" applies only to the child - values of instance names that do not appear in the annotation - results of either "properties" or "patternProperties". - - - For all such properties, validation succeeds if the child instance - validates against the "additionalProperties" schema. - - - The annotation result of this keyword is the set of instance - property names validated by this keyword's subschema. - This annotation affects the behavior of "unevaluatedProperties" - in the Unevaluated vocabulary. - - - Omitting this keyword has the same assertion behavior as - an empty schema. - - - Implementations MAY choose to implement or optimize this keyword - in another way that produces the same effect, such as by directly - checking the names in "properties" and the patterns in - "patternProperties" against the instance property set. - Implementations that do not support annotation collection MUST do so. - - In defining this option, it seems there is the potential for - ambiguity in the output format. The ambiguity does not affect validation results, - but it does affect the resulting output format. - The ambiguity allows for multiple valid output results depending on whether annotations - are used or a solution that "produces the same effect" as draft-07. It is understood - that annotations from failing schemas are dropped. - See our - [Decision Record](https://github.com/json-schema-org/json-schema-spec/tree/HEAD/adr/2022-04-08-cref-for-ambiguity-and-fix-later-gh-spec-issue-1172.md) - for further details. - - -
- -
- - The value of "propertyNames" MUST be a valid JSON Schema. - - - If the instance is an object, this keyword validates if every property name in - the instance validates against the provided schema. - Note the property name that the schema is testing will always be a string. - - - Omitting this keyword has the same behavior as an empty schema. - -
-
- -
-
- - The value of this keyword MUST be a non-negative integer. - - - This keyword modifies the behavior of "contains" within the same schema object, - 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. - -
- -
- - The value of this keyword MUST be a non-negative integer. - - - This keyword modifies the behavior of "contains" within the same schema object, - 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 , - 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. - -
- -
- - The value of this keyword MUST be a valid JSON Schema. - - - This keyword applies its subschema to array elements or object property values. - - - An instance is valid against "contains" if the number of elements or property - values that are valid against its subschema is with the inclusive range of - the minimum and (if any) maximum number of occurrences. - - - The maximum number of occurrences is provided by the "maxContains" keyword - within the same schema object as "contains". If "maxContains" is absent, - the maximum number of occurrences MUST be unbounded. - - - The minimum number of occurrences is provided by the "minContains" keyword - within the same schema object as "contains". If "minContains" is absent, - the minimum number of occurrences MUST be 1. - - - Implementations MAY implement the dependency on "minContians" and - "maxContains" by inspecting their values rather than reading annotations - produced by those keywords. - - - This keyword produces an annotation value which is an array of the - indexes or property names to which this keyword validates successfully - when applying its subschema, in ascending order. The value MAY be a - boolean "true" if the subschema validates successfully when applied to - every index or property value of the instance. The annotation MUST be - present if the instance array or object to which this keyword's schema - applies is empty. - - - This annotation affects the behavior of "unevaluatedItems" in the - Unevaluated vocabulary. - - - The subschema MUST be applied to every array element or object property - value even after the first match has been found, in order to collect - annotations for use by other keywords. This is to ensure that all possible - annotations are collected. - -
-
-
-
- -
- - 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. - - - These instance items or properties may have been unsuccessfully evaluated - against one or more adjacent keyword subschemas, such as when an assertion - in a branch of an "anyOf" fails. Such failed evaluations are not considered - to contribute to whether or not the item or property has been evaluated. - Only successful evaluations are considered. - - - If an item in an array or an object property is "successfully evaluated", it - is logically considered to be valid in terms of the representation of the - object or array that's expected. For example if a subschema represents a car, - which requires between 2-4 wheels, and the value of "wheels" is 6, the instance - object is not "evaluated" to be a car, and the "wheels" property is considered - "unevaluated (successfully as a known thing)", and does not retain any annotations. - - - Recall that adjacent keywords are keywords within the same schema object, - and that the dynamic-scope subschemas include reference targets as well as - lexical subschemas. - - - The behavior of these keywords depend on the annotation results of - adjacent keywords that apply to the instance location being validated. - - - 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. - - - The current IRI for this vocabulary, known as the Unevaluated Applicator - vocabulary, is: - <https://json-schema.org/draft/next/vocab/unevaluated>. - - - The current IRI for the corresponding meta-schema is: - . - - -
- - 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 -
    • -
  • - "unevaluatedProperties", whose behavior is defined in terms of - annotations from "properties", "patternProperties", - "additionalProperties", "contains", and itself -
    • -
-
- -
- - The value of "unevaluatedItems" MUST be a valid JSON Schema. - - - The behavior of this keyword depends on the annotation results of - adjacent 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 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 any of the relevant annotations, - "unevaluatedItems" MUST be ignored. Otherwise, the subschema - MUST be applied to any index greater than the largest annotation - value for "prefixItems", which does not appear in any annotation - value for "contains". - - - This means that "prefixItems", "items", "contains", and all in-place - applicators MUST be evaluated before this keyword can be evaluated. - Authors of extension keywords MUST NOT define an in-place applicator - that would need to be evaluated after this keyword. - - - If the "unevaluatedItems" subschema is applied to any - positions within the instance array, it produces an - annotation result of boolean true, analogous to the - behavior of "items". - This annotation affects the behavior of "unevaluatedItems" in parent schemas. - - - Omitting this keyword has the same assertion behavior as - an empty schema. - -
- -
- - The value of "unevaluatedProperties" MUST be a valid JSON Schema. - - - The behavior of this keyword depends on the annotation results of - adjacent keywords that apply to the instance location being validated. - Specifically, the 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 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", "additionalProperties", "contains", or - "unevaluatedProperties" annotation results that apply to the - instance location being validated. - - - For all such properties, validation succeeds if the child instance - validates against the "unevaluatedProperties" schema. - - - This means that "properties", "patternProperties", "additionalProperties", - "contains" and all in-place applicators MUST be evaluated before this keyword can - be evaluated. Authors of extension keywords MUST NOT define an in-place - applicator that would need to be evaluated after this keyword. - - - The annotation result of this keyword is the set of instance - property names validated by this keyword's subschema. - This annotation affects the behavior of "unevaluatedProperties" in parent schemas. - - - Omitting this keyword has the same assertion behavior as - an empty schema. - -
-
- -
- - 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. - - -
- - 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 output be - convertible to the JSON format defined herein via serialization or other means. - -
- -
- - This specification defines three output formats. See the "Output Structure" - section for the requirements of each format. - -
-
Flag
-
- A boolean which simply indicates the overall validation result - with no further details. -
-
List
-
- Provides validation information in a flat list structure. -
-
Hierarchical
-
- Provides validation information in a hierarchical - structure that follows the evaluation paths generated while processing - the schema. -
-
- - An implementation MUST provide the "flag" format and SHOULD provide at least one - of the "list" or "hierarchical" formats. Implementations SHOULD specify in - their documentation which formats they support. - - -
- -
- - 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. - - - A single object that contains all of these components is considered an - output unit. - - - Implementations MAY elect to provide additional information. - - -
- - 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 "$dynamicRef". - - The schema may not actually have a value at the location indicated - by this pointer. It is provided as an indication of the traversal - path only. - - - - - Note that this pointer may not be resolvable by the normal JSON Pointer process - due to the inclusion of these by-reference applicator keywords. - - - The JSON key for this information is "evaluationPath". - -
- -
- - The absolute, dereferenced location of the schema object that produced - the output unit. The value MUST be expressed using the canonical IRI of the - relevant schema resource plus a JSON Pointer fragment that indicates the schema - object that produced the output. It MUST NOT include by-reference applicators - such as "$ref" or "$dynamicRef". - - Note that "absolute" here is in the sense of "absolute filesystem path" - (meaning the complete location) rather than the "absolute-IRI" - terminology from RFC 3987 (meaning with scheme and without fragment). - Schema locations will have a fragment in order to identify the specific - schema object. - - - - - - The JSON key for this information is "schemaLocation". - -
- -
- - 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". - -
- -
- - 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 by the - associated keyword. - - - If the subschema itself is producing the error, that error MUST be - listed with an empty string key. - - Although there may be other cases where a subschema can produce - an error, the most common case is the "false" schema. In - cases like these, there is no keyword that produces the error, - so there is nothing to use as a key. Thus the empty string - is used instead. - - - - The specific wording for the message is not defined by this - specification. Implementations will need to provide this. - - - The JSON key for this information is "errors". - -
- -
- - Any annotations produced by the evaluation. This property MUST NOT - be included if the validation result of the containing subschema was - unsuccessful. - - - The value for this property MUST be an object where the - keys are the names of keywords and the values are the annotations - produced by the associated keyword. - - - Each keyword defines its own annotation data type (e.g. "properties" - produces a list of keywords, whereas "title" produces a string). - - - The JSON key for this information is "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. It MUST NOT be included if the local - validation result of the containing subschema was successful. - - - Implementations that wish to provide these annotations MUST NOT provide - them as their default behavior. These annotations MUST only be included - by explicitly configuring the implementation to do so. - - - The value for this property MUST be an object where the - keys are the names of keywords and the values are the annotations - produced by the associated keyword. - - - Each keyword defines its own annotation data type (e.g. "properties" - produces a list of keywords, whereas "title" produces a string). - - - The JSON key for this information is "droppedAnnotations". - -
- -
- - 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 - potentially multiple results, the value of this property MUST be an - array of output units, even if only a single output unit is produced. - - - For "list", this property will appear only at the root output unit - and will hold all output units in a flat list. - - - For "hierarchical", this property will contain results in a tree - structure where each output unit may itself have further nested results. - - - The sequence of output units within this list is not specified and - MAY be determined by the implementation. Sets of output units are - considered equivalent if they contain the same units, in any order. - - - The JSON key for these additional results is "details". - -
- -
- -
- - The output MUST be an object containing a boolean property named "valid". When - additional information about the result is required, the output MUST also contain - "details" as described below. - -
-
valid
-
a boolean value indicating the overall validation success or failure
- -
details
-
the collection of results produced by subschemas
-
- - For these examples, the following schema and instances will be used. - - - - 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". -
    • -
  • - 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. -
    • -
  • - The value at "/bar/bar-prop" - evaluated at "/$defs/bar/properties/bar-prop" - by following the path "/properties/bar/$ref/properties/bar-prop" - by the "type" keyword - is not a number. -
    • -
- - - "minimum" doesn't produce an error because it only operates on - instances that are numbers. - - - Note that the error message wording as depicted in the examples below is not a - requirement of this specification. Implementations SHOULD craft error messages - tailored for their audience or provide a templating mechanism that allows their - users to craft their own messages. - - - - The passing instance will produce the following annotations: - -
    -
  • - The keyword "title" - evaluated at "" - by following the path "" - will produce "root". -
    • -
  • - The keyword "properties" - evaluated at "" - by following the path "" - will produce ["foo", "bar"]. -
    • -
  • - The keyword "title" - evaluated at "/properties/foo" - by following the path "/properties/foo" - will produce "foo-title". -
    • -
  • - The keyword "properties" - evaluated at "/properties/foo/allOf/1" - by following the path "/properties/foo/allOf/1" - will produce ["foo-prop"]. -
    • -
  • - The keyword "additionalProperties" - evaluated at "/properties/foo/allOf/1" - by following the path "/properties/foo/allOf/1" - will produce ["unspecified-prop"]. -
    • -
  • - The keyword "title" - evaluated at "/properties/foo/allOf/1/properties/foo-prop" - by following the path "/properties/foo/allOf/1/properties/foo-prop" - will produce "foo-prop-title". -
    • -
  • - The keyword "title" - evaluated at "/$defs/bar" - by following the path "/properties/bar/$ref" - will produce "bar-title". -
    • -
  • - The keyword "properties" - evaluated at "/$defs/bar" - by following the path "/properties/var/$ref" - will produce ["bar-prop"]. -
    • -
  • - The keyword "title" - evaluated at "/$defs/bar/properties/bar-prop" - by following the path "/properties/bar/$ref/properties/bar-prop" - will produce "bar-prop-title". -
    • -
- -
- - 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. - - - - Because no errors or annotations are returned with this format, it is - RECOMMENDED that implementations use short-circuiting logic to return - failure or success as soon as the outcome can be determined. For example, - if an "anyOf" 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. - -
- -
- - The "List" structure is a flat list of output units contained within a - root output unit. - - - The root output unit contains "valid" for the overall result and "details" - for the list of specific results. All other information is explicitly - omitted from the root output unit. If the root schema produces errors or - annotations, then the output node for the root MUST be present within the - root output unit's "details" list with those errors or annotations. - - - Output units which do not contain errors or annotations SHOULD be excluded - from this format, however implementations MAY choose to include them for - completeness. - - -
- -
- - 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 keywords. - - - All output units are included in this format. - - - The location properties of the root output unit MAY be omitted. - - - -
- -
- - For convenience, JSON Schema has been provided to validate output generated - by implementations. Its IRI is: - . - -
- -
- -
- -
- - Both schemas and instances are JSON values. As such, all security considerations - defined in RFC 8259 apply. - - - Instances and schemas are both frequently written by untrusted third parties, to be - deployed on public Internet servers. - Implementations should take care that the parsing and evaluating against schemas - does not consume excessive system resources. - Implementations MUST NOT fall into an infinite loop. - - - A malicious party could cause an implementation to repeatedly collect a copy - of a very large value as an annotation. Implementations SHOULD guard against - excessive consumption of system resources in such a scenario. - - - Servers MUST ensure that malicious parties cannot change the functionality of - existing schemas by uploading a schema with a pre-existing or very similar "$id". - - - Individual JSON Schema vocabularies are liable to also have their own security - considerations. Consult the respective specifications for more information. - - - Schema authors should take care with "$comment" contents, as a malicious - implementation can display them to end-users in violation of a spec, or - fail to strip them if such behavior is expected. - - - A malicious schema author could place executable code or other dangerous - material within a "$comment". Implementations MUST NOT parse or otherwise - take action based on "$comment" contents. - -
- -
-
- - The proposed MIME media type for JSON Schema is defined as follows: - -
-
Type name:
-
application
- -
Subtype name:
-
schema+json
- -
Required parameters:
-
N/A
- -
Encoding considerations:
-
- Encoding considerations are - identical to those specified for the "application/json" - media type. See JSON. -
- -
Security considerations:
-
See above.
- -
Interoperability considerations:
-
- See Sections - , - , and - above. -
- -
Fragment identifier considerations:
-
- See -
-
-
-
- - The proposed MIME media type for JSON Schema Instances that require - a JSON Schema-specific media type is defined as follows: - -
-
Type name:
-
application
- -
Subtype name:
-
schema-instance+json
- -
Required parameters:
-
N/A
- -
Encoding considerations:
-
- Encoding considerations are - identical to those specified for the "application/json" - media type. See JSON. -
- -
Security considerations:
-
See above.
- -
Interoperability considerations:
-
- See Sections - , - , and - above. -
- -
Fragment identifier considerations:
-
See
-
-
-
- - - - - - &RFC2119; - &RFC3986; - &RFC3987; - &RFC6839; - &RFC6901; - &RFC8259; - &ldp; - - - ECMA-262, 11th edition specification - - - - - - - - &RFC6596; - &RFC7049; - &RFC7231; - &RFC8288; - &fragid-best-practices; - &xptr-framework; - - - JSON Schema Validation: A Vocabulary for Structural Validation of JSON - - - - - - - - - - - - - - - - JSON Hyper-Schema: A Vocabulary for Hypermedia Annotation of JSON - - - - - - - - - - - - - Namespaces in XML 1.1 (Second Edition) - - Textuality -
- tbray@textuality.com -
- - - Contivo, Inc. -
- dmh@contivo.com -
- - - Microsoft -
- andrewl@microsoft.com -
- - - University of Edinburgh and Markup Technology Ltd -
- richard@cogsci.ed.ac.uk -
- - - - - - -
- - Consider the following schema, which shows "$id" being used to identify - both the root schema and various subschemas, and "$anchor" being used - to define plain name fragment identifiers. - - - - The schemas at the following IRI-encoded JSON - Pointers (relative to the root schema) have the following - base IRIs, and are identifiable by any listed IRI in accordance with - and above. - -
-
# (document root)
-
-
-
canonical (and base) IRI"
-
https://example.com/root.json
- -
canonical resource IRI plus pointer fragment"
-
https://example.com/root.json#
-
-
- -
#/$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/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
-
-
- -
#/$defs/B/$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/$defs/Y
-
-
- -
#/$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#/$defs/C
-
-
-
- - Note: The fragment part of the IRI does not make it canonical or non-canonical, - rather, the base IRI used (as part of the full IRI with any fragment) is what - determines the canonical nature of the resulting full IRI. - - Multiple "canonical" IRIs? We Acknowledge this is potentially confusing, and - direct you to read the CREF located in the - JSON Pointer fragments and embedded schema resources - section for futher comments. - - - -
- -
- - Various tools have been created to rearrange schema documents - based on how and where references ("$ref") appear. This appendix discusses - which use cases and actions are compliant with this specification. - -
- - 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. - - - Numerous tools exist to perform various sorts of reference removal. - A common case of this is producing a single file where all references - can be resolved within that file. This is typically done to simplify - distribution, or to simplify coding so that various invocations - of JSON Schema libraries do not have to keep track of and load - a large number of resources. - - - This transformation can be safely and reversibly done as long as - all static references (e.g. "$ref") use IRI-references that resolve - to IRIs using the canonical resource IRI as the base, and all schema - resources have an absolute-IRI as the "$id" in their root schema. - - - With these conditions met, each external resource can be copied - under "$defs", without breaking any references among the resources' - schema objects, and without changing any aspect of validation or - annotation results. The names of the schemas under "$defs" do - not affect behavior, assuming they are each unique, as they - do not appear in the canonical IRIs for the embedded resources. - -
-
- - 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. - - - Since "$ref" is now treated like any other keyword, with other keywords allowed - in the same schema objects, fully supporting non-recursive "$ref" removal in - all cases can require relatively complex schema manipulations. It is beyond - the scope of this specification to determine or provide a set of safe "$ref" - removal transformations, as they depend not only on the schema structure - but also on the intended usage. - -
-
- -
- - Consider the following two schemas describing a simple - recursive tree structure, where each node in the tree - can have a "data" field of any type. The first schema - allows and ignores other instance properties. The second is - more strict and only allows the "data" and "children" properties. - An example instance with "data" misspelled as "daat" is also shown. - - - - When we load these two schemas, we will notice the "$dynamicAnchor" - named "node" (note the lack of "#" as this is just the name) - present in each, resulting in the following full schema IRIs: -
    -
  • "https://example.com/tree#node"
    • -
  • "https://example.com/strict-tree#node"
    • -
- In addition, JSON Schema implementations keep track of the fact - that these fragments were created with "$dynamicAnchor". - - - If we apply the "strict-tree" schema to the instance, we will follow - the "$ref" to the "tree" schema, examine its "children" subschema, - and find the "$dynamicRef": to "#node" (note the "#" for IRI fragment syntax) - in its "items" subschema. That reference resolves to - "https://example.com/tree#node", which is a IRI with a fragment - created by "$dynamicAnchor". Therefore we must examine the dynamic - scope before following the reference. - - - At this point, the evaluation path is - "#/$ref/properties/children/items/$dynamicRef", with a dynamic scope - containing (from the outermost scope to the innermost): -
    -
  1. "https://example.com/strict-tree#"
    2. -
  2. "https://example.com/tree#"
    3. -
  3. "https://example.com/tree#/properties/children"
    4. -
  4. "https://example.com/tree#/properties/children/items"
    5. -
- - - Since we are looking for a plain name fragment, which can be - defined anywhere within a schema resource, the JSON Pointer fragments - are irrelevant to this check. That means that we can remove those - fragments and eliminate consecutive duplicates, producing: -
    -
  1. "https://example.com/strict-tree"
    2. -
  2. "https://example.com/tree"
    3. -
- - - In this case, the outermost resource also has a "node" fragment - defined by "$dynamicAnchor". Therefore instead of resolving the - "$dynamicRef" to "https://example.com/tree#node", we resolve it to - "https://example.com/strict-tree#node". - - - This way, the recursion in the "tree" schema recurses to the root - of "strict-tree", instead of only applying "strict-tree" to the - instance root, but applying "tree" to instance children. - - - This example shows both "$dynamicAnchor"s in the same place - in each schema, specifically the resource root schema. - Since plain-name fragments are independent of the JSON structure, - this would work just as well if one or both of the node schema objects - were moved under "$defs". It is the matching "$dynamicAnchor" values - which tell us how to resolve the dynamic reference, not any sort of - correlation in JSON structure. - -
- -
-
- - Vocabulary authors should - take care to avoid keyword name collisions if the vocabulary is intended - for broad use, and potentially combined with other vocabularies. JSON - Schema does not provide any formal namespacing system, but also does - not constrain keyword names, allowing for any number of namespacing - approaches. - - - Vocabularies may build on each other, such as by defining the behavior - of their keywords with respect to the behavior of keywords from another - vocabulary, or by using a keyword from another vocabulary with - a restricted or expanded set of acceptable values. Not all such - vocabulary re-use will result in a new vocabulary that is compatible - with the vocabulary on which it is built. Vocabulary authors should - clearly document what level of compatibility, if any, is expected. - - - Meta-schema authors should not use "$vocabulary" to combine multiple - vocabularies that define conflicting syntax or semantics for the same - keyword. As semantic conflicts are not generally detectable through - schema validation, implementations are not expected to detect such - conflicts. If conflicting vocabularies are declared, the resulting - behavior is undefined. - - - Vocabulary authors SHOULD provide a meta-schema that validates the - expected usage of the vocabulary's keywords on their own. Such meta-schemas - SHOULD not 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" 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, as can be seen in the JSON Hyper-Schema meta-schema - which extends the Validation meta-schema. - - - Meta-schemas may impose additional constraints, including describing - keywords not present in any vocabulary, beyond what the meta-schemas - associated with the declared vocabularies describe. This allows for - restricting usage to a subset of a vocabulary, and for validating - locally defined keywords not intended for re-use. - - - However, meta-schemas should not contradict any vocabularies that - they declare, such as by requiring a different JSON type than - the vocabulary expects. The 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. - -
- -
- - 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 - keywords in that vocabulary, is shown after the main example meta-schema. - - - The main example meta-schema also restricts the usage of the Unevaluated - vocabulary by forbidding the keywords prefixed with "unevaluated", which - are particularly complex to implement. This does not change the semantics - or set of keywords defined by the other vocabularies. It just ensures - that schemas using this meta-schema that attempt to use the keywords - prefixed with "unevaluated" will fail validation against this meta-schema. - - - Finally, this meta-schema describes the syntax of a keyword, "localKeyword", - that is not part of any vocabulary. Presumably, the implementors and users - of this meta-schema will understand the semantics of "localKeyword". - JSON Schema does not define any mechanism for expressing keyword semantics - outside of vocabularies, making them unsuitable for use except in a - specific environment in which they are understood. - - - This meta-schema combines several vocabularies for general use. - - - - This meta-schema describes only a single extension vocabulary. - - - - As shown above, even though each of the single-vocabulary meta-schemas - referenced in the general-use meta-schema's "allOf" declares its - corresponding vocabulary, this new meta-schema must re-declare them. - - - The standard meta-schemas that combine all vocabularies defined by - the Core and Validation specification, and that combine all vocabularies - defined by those specifications as well as the Hyper-Schema specification, - demonstrate additional complex combinations. These IRIs for these - meta-schemas may be found in the Validation and Hyper-Schema specifications, - respectively. - - - While the general-use meta-schema can validate the syntax of "minDate", - it is the vocabulary that defines the logic behind the semantic meaning - of "minDate". Without an understanding of the semantics (in this example, - that the instance value must be a date equal to or after the date - provided as the keyword's value in the schema), an implementation can - only validate the syntactic usage. In this case, that means validating - that it is a date-formatted string (using "pattern" to ensure that it is - validated even when "format" functions purely as an annotation, as explained - in the Validation specification. - -
-
- -
- - 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. - - - To make such use case-specific semantics explicit, the best practice - is to create an annotation keyword for use in the same - schema object alongside of a reference keyword such as "$ref". - - - For example, here is a hypothetical keyword for determining - whether a code generator should consider the reference - target to be a distinct class, and how those classes are related. - Note that this example is solely for illustrative purposes, and is - not intended to propose a functional code generation keyword. - - - - Here, this schema represents some sort of object-oriented class. - The first reference in the "allOf" is noted as the base class. - The second is not assigned a class relationship, meaning that the - code generator should combine the target's definition with this - one as if no reference were involved. - - - Looking at the properties, "foo" is flagged as object composition, - while the "date" property is not. It is simply a field with - sub-fields, rather than an instance of a distinct class. - - - This style of usage requires the annotation to be in the same object - as the reference, which must be recognizable as a reference. - -
- -
- - Thanks to - Gary Court, - Francis Galiegue, - Kris Zyp, - Geraint Luff, - and Henry Andrews - for their work on the initial drafts of JSON Schema. - - - Thanks to - Jason Desrosiers, - Daniel Perrett, - Erik Wilde, - Evgeny Poberezkin, - Brad Bowman, - Gowry Sankar, - Donald Pipowitch, - Dave Finlay, - Denis Laxalde, - Phil Sturgeon, - Shawn Silverman, - and Karen Etheridge - for their submissions and patches to the document. - -
- -
- - This section to be removed before leaving Internet-Draft status. - - -
-
    -
  • "contains" now applies to objects as well as arrays
    • -
  • Use IRIs instead of URIs
    • -
  • Remove bookending requirement for "$dynamicRef"
    • -
  • Add "propertyDependencies" keyword
    • -
-
- -
-
    -
  • Improve and clarify the "type", "contains", "unevaluatedProperties", and "unevaluatedItems" keyword explanations
    • -
  • Clarify various aspects of "canonical URIs"
    • -
  • Comment on ambiguity around annotations and "additionalProperties"
    • -
  • Clarify Vocabularies need not be formally defined
    • -
  • Remove references to remaining media-type parameters
    • -
  • Fix multiple examples
    • -
-
- -
-
    -
  • "$schema" MAY change for embedded resources
    • -
  • Array-value "items" functionality is now "prefixItems"
    • -
  • "items" subsumes the old function of "additionalItems"
    • -
  • "contains" annotation behavior, and "contains" and "unevaluatedItems" interactions now specified
    • -
  • Rename $recursive* to $dynamic*, with behavior modification
    • -
  • $dynamicAnchor defines a fragment like $anchor
    • -
  • $dynamic* (previously $recursive) no longer use runtime base URI determination
    • -
  • Define Compound Schema Documents (bundle) and processing
    • -
  • Reference ECMA-262, 11th edition for regular expression support
    • -
  • Regular expression should support unicode
    • -
  • Remove media type parameters
    • -
  • Specify Unknown keywords are collected as annotations
    • -
  • Moved "unevaluatedItems" and "unevaluatedProperties" from core into their own vocabulary
    • -
-
- -
-
    -
  • Update to RFC 8259 for JSON specification
    • -
  • Moved "definitions" from the Validation specification here as "$defs"
    • -
  • Moved applicator keywords from the Validation specification as their own vocabulary
    • -
  • Moved the schema form of "dependencies" from the Validation specification as "dependentSchemas"
    • -
  • Formalized annotation collection
    • -
  • Specified recommended output formats
    • -
  • Defined keyword interactions in terms of annotation and assertion results
    • -
  • Added "unevaluatedProperties" and "unevaluatedItems"
    • -
  • Define "$ref" behavior in terms of the assertion, applicator, and annotation model
    • -
  • Allow keywords adjacent to "$ref"
    • -
  • Note undefined behavior for "$ref" targets involving unknown keywords
    • -
  • Add recursive referencing, primarily for meta-schema extension
    • -
  • Add the concept of formal vocabularies, and how they can be recognized through meta-schemas
    • -
  • Additional guidance on initial base URIs beyond network retrieval
    • -
  • Allow "schema" media type parameter for "application/schema+json"
    • -
  • Better explanation of media type parameters and the HTTP Accept header
    • -
  • Use "$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
    • -
-
- -
-
    -
  • This draft is purely a clarification with no functional changes
    • -
  • Emphasized annotations as a primary usage of JSON Schema
    • -
  • Clarified $id by use cases
    • -
  • Exhaustive schema identification examples
    • -
  • Replaced "external referencing" with how and when an implementation might know of a schema from another document
    • -
  • Replaced "internal referencing" with how an implementation should recognized schema identifiers during parsing
    • -
  • Dereferencing the former "internal" or "external" references is always the same process
    • -
  • Minor formatting improvements
    • -
-
- -
-
    -
  • Make the concept of a schema keyword vocabulary more clear
    • -
  • Note that the concept of "integer" is from a vocabulary, not the data model
    • -
  • Classify keywords as assertions or annotations and describe their general behavior
    • -
  • Explain the boolean schemas in terms of generalized assertions
    • -
  • Reserve "$comment" for non-user-visible notes about the schema
    • -
  • Wording improvements around "$id" and fragments
    • -
  • Note the challenges of extending meta-schemas with recursive references
    • -
  • Add "application/schema-instance+json" media type
    • -
  • Recommend a "schema" link relation / parameter instead of "profile"
    • -
-
- -
-
    -
  • Updated intro
    • -
  • Allowed for any schema to be a boolean
    • -
  • "$schema" SHOULD NOT appear in subschemas, although that may change
    • -
  • 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
    • -
-
- -
-
    -
  • Updated references to JSON
    • -
  • Updated references to HTTP
    • -
  • Updated references to JSON Pointer
    • -
  • Behavior for "id" is now specified in terms of RFC3986
    • -
  • Aligned vocabulary usage for URIs with RFC3986
    • -
  • Removed reference to draft-pbryan-zyp-json-ref-03
    • -
  • Limited use of "$ref" to wherever a schema is expected
    • -
  • Added definition of the "JSON Schema data model"
    • -
  • Added additional security considerations
    • -
  • Defined use of subschema identifiers for "id"
    • -
  • Rewrote section on usage with HTTP
    • -
  • Rewrote section on usage with rel="describedBy" and rel="profile"
    • -
  • Fixed numerous invalid examples
    • -
-
- -
-
    -
  • Salvaged from draft v3.
    • -
  • Split validation keywords into separate document.
    • -
  • Split hypermedia keywords into separate document.
    • -
  • Initial post-split draft.
    • -
  • Mandate the use of JSON Reference, JSON Pointer.
    • -
  • Define the role of "id". Define URI resolution scope.
    • -
  • Add interoperability considerations.
    • -
-
- -
-
    -
  • Initial draft.
    • -
-
-
- - diff --git a/jsonschema-validation.md b/jsonschema-validation.md new file mode 100644 index 00000000..f22c50ec --- /dev/null +++ b/jsonschema-validation.md @@ -0,0 +1,1046 @@ +# 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 +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 +. + +For additional information, see . + +To provide feedback, use this issue tracker, the communication methods listed on +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 +defined to assist in interactive user interface instance generation. + +This specification will use the concepts, syntax, and terminology defined by the +[JSON Schema core](#json-schema) specification. + +## 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). + +This specification uses the term "container instance" to refer to both array and +object instances. It uses the term "children instances" to refer to array +elements or object member values. + +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 +metadata and usage hints. If all locations within the instance satisfy all +asserted constraints, then the instance is said to be valid against the schema. + +Each schema object is independently evaluated against each instance location to +which it applies. This greatly simplifies the implementation requirements for +validators by ensuring that they do not need to maintain state across the +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 [Section +7](#7-vocabularies-for-semantic-content-with-format) keyword is intended +primarily as an annotation, but can optionally be used as an assertion. The +[Section 8](#8-a-vocabulary-for-the-contents-of-string-encoded-data) 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 +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 +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 +specification and the JSON Schema Core specification, as well as two former +keywords which are reserved for a transitional period. Individual vocabulary and +vocabulary meta-schema IRIs are given for each section below. Certain +vocabularies are optional to support, which is explained in detail in the +relevant sections. + +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. + +## 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. + +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. + +The current IRI for this vocabulary, known as the Validation vocabulary, is: +`https://json-schema.org/draft/next/vocab/validation`. + +The current IRI for the corresponding meta-schema is: +`https://json-schema.org/draft/next/meta/validation`. + +### Validation Keywords for Any Instance Type + +#### 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. + +String values MUST be one of the six primitive types ("null", "boolean", +"object", "array", "number", or "string"), or "integer" which matches any number +with a zero fractional part. + +If the value of "type" is a string, then an instance validates successfully if +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 +The value of this keyword MUST be an array. This array SHOULD have at least one +element. Elements in the array SHOULD be unique. + +An instance validates successfully against this keyword if its value is equal to +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 +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) + +#### 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. + +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. + +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. + +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 + +#### 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 +equal to, the value of this keyword. + +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, +or equal to, the value of this keyword. + +The length of a string instance is defined as the number of its characters as +defined by [RFC 8259](#rfc8259). + +Omitting this keyword has the same behavior as a value of 0. + +#### 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. + +A string instance is considered valid if the regular expression matches the +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 +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 +it has boolean value true, the instance validates successfully if all of its +elements are unique. + +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 +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. + +An object instance is valid against this keyword if every item in the array is +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. + +This keyword specifies properties that are required if a specific other property +is present. Their requirement is dependent on the presence of the other +property. + +Validation succeeds if, for each name that appears in both the instance and as a +name within this keyword's value, every item in the corresponding array is also +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 + +### 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 +which are accurately described by authoritative resources, be they RFCs or other +external specifications. + +The value of this keyword is called a format attribute. It MUST be a string. A +format attribute can generally only validate a given set of instance types. If +the type of the instance to validate is not in this set, validation for this +format attribute and instance SHOULD succeed. All format attributes defined in +this section apply to strings, but a format attribute can be specified to apply +to any instance types defined in the data model defined in the [core JSON +Schema.](#json-schema)[^1] + +[^1]: Note that the `type` keyword in this specification defines an "integer" +type which is not part of the data model. Therefore a format attribute can be +limited to numbers, but not specifically to integers. However, a numeric format +can be used alongside the `type` keyword with a value of "integer", or could be +explicitly defined to always pass if the number is not an integer, which +produces essentially the same behavior as only applying to integers. + +The current IRI for this vocabulary, known as the Format-Annotation vocabulary, +is: `https://json-schema.org/draft/next/vocab/format-annotation`. The current +IRI for the corresponding meta-schema is: +`https://json-schema.org/draft/next/meta/format-annotation`. Implementing +support for this vocabulary is REQUIRED. + +In addition to the Format-Annotation vocabulary, a secondary vocabulary is +available for custom meta-schemas that defines `format` as an assertion. The IRI +for the Format-Assertion vocabulary, is: +`https://json-schema.org/draft/next/vocab/format-assertion`. The current IRI for +the corresponding meta-schema is: +`https://json-schema.org/draft/next/meta/format-assertion`. Implementing support +for the Format-Assertion vocabulary is OPTIONAL. + +Specifying both the Format-Annotation and the Format-Assertion vocabularies is +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. + +Implementations MAY still treat `format` as an assertion in addition to an +annotation and attempt to validate the value's conformance to the specified +semantics. The implementation MUST provide options to enable and disable such +evaluation and MUST be disabled by default. Implementations SHOULD document +their level of support for such validation.[^2] + +[^2]: Specifying the Format-Annotation vocabulary and enabling validation in an +implementation should not be viewed as being equivalent to specifying the +Format-Assertion vocabulary since implementations are not required to provide +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; +- MAY choose to implement validation of any or all format attributes as a no-op +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 +format attributes. It is also designed to encourage relying only on the +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 +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; +- 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 +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, +attempt to connect to a URL, or otherwise check the existence of an entity +identified by a format instance.[^4] + +[^4]: The expectation is that for simple formats such as date-time, syntactic +validation will be thorough. For a complex format such as email addresses, which +are the amalgamation of various standards and numerous adjustments over time, +with obscure and/or obsolete rules that may or may not be restricted by other +applications making use of the value, a minimal validation is sufficient. For +example, an instance string that does not contain an "@" is clearly not a valid +email address, and an "email" or "hostname" containing characters outside of +7-bit ASCII is likewise clearly invalid. + +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 +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 +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 +formats as annotations. When the Format-Assertion vocabulary is specified, +implementations MUST fail upon encountering unknown formats. + +Vocabularies do not support specifically declaring different value sets for +keywords. Due to this limitation, and the historically uneven implementation of +this keyword, it is RECOMMENDED to define additional keywords in a custom +vocabulary rather than additional format attributes if interoperability is +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). +The duration format is from the ISO 8601 ABNF as given in Appendix A of RFC +3339. + +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) +- *date:* A string instance is valid against this attribute if it is a valid +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) +- *duration:* A string instance is valid against this attribute if it is a valid +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 +corresponding short form ("date" or "time" respectively) MUST be implemented, +and MUST behave identically. Implementations SHOULD NOT define extension +attributes with any name matching an RFC 3339 format unless it validates +according to the rules of that format.[^5] + +[^5]: There is not currently consensus on the need for supporting all RFC 3339 +formats, so this approach of reserving the namespace will encourage +experimentation without committing to the entire set. Either the format +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 +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. + +#### 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). +- *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. + +#### 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). +- *ipv6:* An IPv6 address as defined in [RFC 4291, section 2.2](#rfc4291). + +#### 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). +- *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). +- *iri:* A string instance is valid against this attribute if it is a valid IRI, +according to [Appendix 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). +- *uuid:* A string instance is valid against this attribute if it is a valid +string representation of a UUID, according to [Appendix RFC4122](#rfc4122). + +Note that all valid URIs are valid IRIs, and all valid URI References are also +valid IRI References. + +Note also that the "uuid" format is for plain UUIDs, not UUIDs in URNs. An +example is "f81d4fae-7dec-11d0-a765-00a0c91e6bf6". For UUIDs as URNs, use the +"uri" format, with a "pattern" regular expression of "^urn:uuid:" to indicate +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). + +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). +- *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. + +#### 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. + +## A Vocabulary for the Contents of String-Encoded Data + +### Foreword +Annotations defined in this section indicate that an instance contains non-JSON +data encoded in a JSON string. + +These properties provide additional information required to interpret JSON data +as rich multimedia documents. They describe the type of content, how it is +encoded, and/or how it may be validated. They do not function as validation +assertions; a malformed string-encoded document MUST NOT cause the containing +instance to be considered invalid. + +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. + +The current IRI for this vocabulary, known as the Content vocabulary, is: +`https://json-schema.org/draft/next/vocab/content`. + +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 +annotations to invoke the appropriate libraries separately. + +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. + +Possible values indicating base 16, 32, and 64 encodings with several variations +are listed in [RFC 4648](#rfc4648). Additionally, sections 6.7 and 6.8 of [RFC +2045](#rfc2045) provide encodings used in MIME. This keyword is derived from +MIME's Content-Transfer-Encoding header, which was designed to map binary data +into ASCII characters. It is not related to HTTP's Content-Encoding header, +which is used to encode (e.g. compress or encrypt) the content of HTTP request +and responses. + +As "base64" is defined in both RFCs, the definition from RFC 4648 SHOULD be +assumed unless the string is specifically intended for use in a MIME context. +Note that all of these encodings result in strings consisting only of 7-bit +ASCII characters. Therefore, this keyword has no meaning for strings containing +characters outside of that range. + +If this keyword is absent, but `contentMediaType` is present, this indicates +that the encoding is the identity encoding, meaning that no transformation was +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. + +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. + +This keyword MAY be used with any media type that can be mapped into JSON +Schema's data model. Specifying such mappings is outside of the scope of this +specification. + +The value of this property MUST be a valid JSON schema. It SHOULD be ignored if +`contentMediaType` is not present. Accessing the schema through the schema +location IRI included as part of the annotation will ensure that it is correctly +processed as a subschema. Using the extracted annotation value directly is only +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`: + +```json +{ + "type": "string", + "contentEncoding": "base64", + "contentMediaType": "image/png" +} +``` + +Instances described by this schema are expected to be strings, and their values +should be interpretable as base64-encoded PNG images. + +Another example: + +```json +{ + "type": "string", + "contentMediaType": "text/html" +} +``` + +Instances described by this schema are expected to be strings containing HTML, +using whatever character set the JSON string was decoded into. Per section 8.1 +of [RFC 8259](#rfc8259), outside of an entirely closed system, this MUST be +UTF-8. + +This example describes a JWT that is MACed using the HMAC SHA-256 algorithm, and +requires the "iss" and "exp" fields in its claim set. + +```json +{ + "type": "string", + "contentMediaType": "application/jwt", + "contentSchema": { + "type": "array", + "minItems": 2, + "prefixItems": [ + { + "const": { + "typ": "JWT", + "alg": "HS256" + } + }, + { + "type": "object", + "required": ["iss", "exp"], + "properties": { + "iss": {"type": "string"}, + "exp": {"type": "integer"} + } + } + ] + } +} +``` + +Note that `contentEncoding` does not appear. While the `application/jwt` media +type makes use of base64url encoding, that is defined by the media type, which +determines how the JWT string is decoded into a list of two JSON data +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. + +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. + +The current IRI for this vocabulary, known as the Meta-Data vocabulary, is: +`https://json-schema.org/draft/next/vocab/meta-data`. + +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 +about the data produced by this user interface. A title will preferably be +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. + +This keyword can be used to supply a default JSON value associated with a +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. + +If `deprecated` has a value of boolean true, it indicates that applications +SHOULD refrain from usage of the declared property. It MAY mean the property is +going to be removed in the future. + +A root schema containing `deprecated` with a value of true indicates that the +entire resource being described MAY be removed in the future. + +The `deprecated` keyword applies to each instance location to which the schema +object containing the keyword successfully applies. This can result in scenarios +where every array item or object property is deprecated even though the +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 +SHOULD be as for a false value otherwise. + +If `readOnly` has a value of boolean true, it indicates that the value of the +instance is managed exclusively by the owning authority, and attempts by an +application to modify the value of this property are expected to be ignored or +rejected by that owning authority. + +An instance document that is marked as `readOnly` for the entire document MAY be +ignored if sent to the owning authority, or MAY result in an error, at the +authority's discretion. + +If `writeOnly` has a value of boolean true, it indicates that the value is never +present when the instance is retrieved from the owning authority. It can be +present when sent to the owning authority to update or create the document (or +the resource it represents), but it will not be included in any updated or newly +created version of the instance. + +An instance document that is marked as `writeOnly` for the entire document MAY +be returned as a blank document of some sort, or MAY produce an error upon +retrieval, or have the retrieval request ignored, at the authority's discretion. + +For example, `readOnly` would be used to mark a database-generated serial number +as read-only, while `writeOnly` would be used to mark a password input field. + +These keywords can be used to assist in user interface instance generation. In +particular, an application MAY choose to use a widget that hides input values as +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 +of all values rather than an array of arrays. + +This keyword can be used to provide sample JSON values associated with a +particular schema, for the purpose of illustrating usage. It is RECOMMENDED that +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 +JSON Schema validation defines a vocabulary for JSON Schema core and concerns +all the security considerations listed there. + +JSON Schema validation allows the use of Regular Expressions, which have +numerous different (often incompatible) implementations. Some implementations +allow the embedding of arbitrary code, which is outside the scope of JSON Schema +and MUST NOT be permitted. Regular expressions can often also be crafted to be +extremely expensive to compute (with so-called "catastrophic backtracking"), +resulting in a denial-of-service attack. + +Implementations that support validating or otherwise evaluating instance string +data based on `contentEncoding` and/or `contentMediaType` are at risk of +evaluating data in an unsafe way based on misleading information. Applications +can mitigate this risk by only performing such processing when a relationship +between the schema and instance is established (e.g., they share the same +authority). + +Processing a media type or encoding is subject to the security considerations of +that media type or encoding. For example, the security considerations of [RFC +4329 Scripting Media Types](#rfc4329) apply when processing JavaScript or +ECMAScript encoded within a JSON string. + +## References + +### Normative References + +#### [RFC2119] +Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", BCP 14, +RFC 2119, DOI 10.17487/RFC2119, March 1997, +<>. + +#### [RFC1123] +Braden, R., Ed., "Requirements for Internet Hosts - Application and Support", +STD 3, RFC 1123, DOI 10.17487/RFC1123, October 1989, +<>. + +#### [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] +Freed, N. and N. Borenstein, "Multipurpose Internet Mail Extensions (MIME) Part +Two: Media Types", RFC 2046, DOI 10.17487/RFC2046, November 1996, +<>. + +#### [RFC2673] +Crawford, M., "Binary Labels in the Domain Name System", RFC 2673, DOI +10.17487/RFC2673, August 1999, <>. + +#### [RFC3339] +Klyne, G. and C. Newman, "Date and Time on the Internet: Timestamps", RFC 3339, +DOI 10.17487/RFC3339, July 2002, <>. + +#### [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] +Duerst, M. and M. Suignard, "Internationalized Resource Identifiers (IRIs)", RFC +3987, DOI 10.17487/RFC3987, January 2005, +<>. + +#### [RFC4122] +Leach, P., Mealling, M., and R. Salz, "A Universally Unique IDentifier (UUID) +URN Namespace", RFC 4122, DOI 10.17487/RFC4122, July 2005, +<>. + +#### [RFC4291] +Hinden, R. and S. Deering, "IP Version 6 Addressing Architecture", RFC 4291, DOI +10.17487/RFC4291, February 2006, <>. + +#### [RFC4648] +Josefsson, S., "The Base16, Base32, and Base64 Data Encodings", RFC 4648, DOI +10.17487/RFC4648, October 2006, <>. + +#### [RFC5321] +Klensin, J., "Simple Mail Transfer Protocol", RFC 5321, DOI 10.17487/RFC5321, +October 2008, <>. + +#### [RFC5890] +Klensin, J., "Internationalized Domain Names for Applications (IDNA): +Definitions and Document Framework", RFC 5890, DOI 10.17487/RFC5890, August +2010, <>. + +#### [RFC5891] +Klensin, J., "Internationalized Domain Names in Applications (IDNA): Protocol", +RFC 5891, DOI 10.17487/RFC5891, August 2010, +<>. + +#### [RFC6570] +Gregorio, J., Fielding, R., Hadley, M., Nottingham, M., and D. Orchard, "URI +Template", RFC 6570, DOI 10.17487/RFC6570, March 2012, +<>. + +#### [RFC6531] + +Yao, J. and W. Mao, "SMTP Extension for Internationalized Email", RFC 6531, DOI +10.17487/RFC6531, February 2012, <>. + +#### [RFC6901] +Bryan, P., Ed., Zyp, K., and M. Nottingham, Ed., "JavaScript Object Notation +(JSON) Pointer", RFC 6901, DOI 10.17487/RFC6901, April 2013, +<>. + +#### [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, +<>. + +#### [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] +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, +<>. + +### Informative References + +#### [RFC4329] +Hoehrmann, B., "Scripting Media Types", RFC 4329, DOI 10.17487/RFC4329, April +2006, <>. + +## Appendix A. 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. +- *`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. +- *`maxContains`, `minContains`* These keywords modify the behavior of +`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. + +## Appendix B. Acknowledgments +Thanks to Gary Court, Francis Galiegue, Kris Zyp, Geraint Luff, and Henry +Andrews for their work on the initial drafts of JSON Schema. + +Thanks to Jason Desrosiers, Daniel Perrett, Erik Wilde, Evgeny Poberezkin, Brad +Bowman, Gowry Sankar, Donald Pipowitch, Dave Finlay, Denis Laxalde, Phil +Sturgeon, Shawn Silverman, and Karen Etheridge for their submissions and patches +to the document. + +## Appendix C. ChangeLog[^6] +[^6]: This section to be removed before leaving Internet-Draft status. + +- *draft-next* + - Use IRIs instead of URIs +- *draft-bhutton-json-schema-validation-01* + - Improve and clarify the `minContains` keyword explanation + - Remove the use of "production" in favour of "ABNF rule" +- *draft-bhutton-json-schema-validation-00* + - Correct email format RFC reference to 5321 instead of 5322 + - Clarified the set and meaning of `contentEncoding` values + - Reference ECMA-262, 11th edition for regular expression support + - Split `format` into an annotation only vocabulary and an assertion + vocabulary + - Clarify `deprecated` when applicable to arrays +- *draft-handrews-json-schema-validation-02* + - 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 + - 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 + - Renamed the array form of `dependencies` to `dependentRequired`, moved the +schema form to the core spec + - Specified all `content*` keywords as annotations, not assertions + - Added `contentSchema` to allow applying a schema to a string-encoded + document + - Also allow RFC 4648 encodings in `contentEncoding` + - Added `minContains` and `maxContains` + - Update RFC reference for nhostname" and "idn-hostname" + - Add "uuid" and "duration" formats +- *draft-handrews-json-schema-validation-01* + - This draft is purely a clarification with no functional changes + - Provided the general principle behind ignoring annotations under `not` and + similar cases + - Clarified `if`/`then`/`else` validation interactions + - Clarified `if`/`then`/`else` behavior for annotation + - Minor formatting and cross-referencing improvements +- *draft-handrews-json-schema-validation-00* + - Added `if`/`then`/`else` + - Classify keywords as assertions or annotations per the core spec + - Warn of possibly removing `dependencies` in the future + - Grouped validation keywords into sub-sections for readability + - Moved `readOnly` from hyper-schema to validation meta-data + - Added `writeOnly` + - Added string-encoded media section, with former hyper-schema `media` + keywords + - Restored "regex" format (removal was unintentional) + - Added "date" and "time" formats, and reserved additional RFC 3339 format + names + - I18N formats: "iri", "iri-reference", "idn-hostname", "idn-email" + - Clarify that "json-pointer" format means string encoding, not URI fragment + - Fixed typo that inverted the meaning of `minimum` and `exclusiveMinimum` + - Move format syntax references into Normative References + - JSON is a normative requirement +- *draft-wright-json-schema-validation-01* + - Standardized on hyphenated format names with full words ("uriref" becomes + "uri-reference") + - Add the formats "uri-template" and "json-pointer" + - Changed `exclusiveMaximum`/`exclusiveMinimum` from boolean modifiers of + `maximum`/`minimum` to independent numeric fields. + - Split the additionalItems/items into two sections + - Reworked properties/patternProperties/additionalProperties definition + - Added `examples` keyword + - Added `contains` keyword + - Allow empty `required` and `dependencies` arrays + - Fixed `type` reference to primitive types + - Added `const` keyword + - Added `propertyNames` keyword +- *draft-wright-json-schema-validation-00* + - Added additional security considerations + - Removed reference to "latest version" meta-schema, use numbered version + instead + - Rephrased many keyword definitions for brevity + - Added "uriref" format that also allows relative URI references +- *draft-fge-json-schema-validation-00* + - Initial draft. + - Salvaged from draft v3. + - Redefine the `required` keyword. + - Remove `extends`, `disallow` + - Add `anyOf`, `allOf`, `oneOf`, `not`, `definitions`, `minProperties`, + `maxProperties`. + - `dependencies` member values can no longer be single strings; at least one + element is required in a property dependency array. + - Rename `divisibleBy` to `multipleOf`. + - `type` arrays can no longer have schemas; remove `any` as a possible + value. + - Rework the `format` section; make support optional. + - `format": remove attributes "phone", "style", "color"; rename "ip-address" + to "ipv4"; add references for all attributes. + - Provide algorithms to calculate schema(s) for array/object instances. + - Add interoperability considerations. + +## Authors' Addresses + +### Austin Wright (*editor*) + +Email: + +### Ben Hutton (*editor*) + +Postman + +Email: + +URI: diff --git a/jsonschema-validation.xml b/jsonschema-validation.xml deleted file mode 100644 index 65902b4e..00000000 --- a/jsonschema-validation.xml +++ /dev/null @@ -1,1492 +0,0 @@ - - - - - - - - - - - - - - - - - - - - -]> - - - - - - - - - - - - JSON Schema Validation: A Vocabulary for Structural Validation of JSON - - - -
- aaa@bzfx.net -
- - - - Postman -
- ben@jsonschema.dev - https://jsonschema.dev -
- - - - Internet Engineering Task Force - JSON - Schema - validation - - - - 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 working with JSON data, and to make - assertions about what a valid document must look like. - - - - - - The issues list for this draft can be found at - . - - - For additional information, see . - - - To provide feedback, use this issue tracker, the communication methods listed on the - homepage, or email the document editors. - - - - - -
- - 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 defined to assist in interactive user interface instance generation. - - - This specification will use the concepts, syntax, and terminology defined - by the JSON Schema core specification. - -
- -
- - - - 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. - - - This specification uses the term "container instance" to refer to both array and - object instances. It uses the term "children instances" to refer to array elements - or object member values. - - - Elements in an array value are said to be unique if no two elements of this array - are equal. - -
- -
- - 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 metadata and usage hints. If all locations within - the instance satisfy all asserted constraints, then the instance is - said to be valid against the schema. - - - Each schema object is independently evaluated against each instance location - to which it applies. This greatly simplifies the implementation requirements - for validators by ensuring that they do not need to maintain state across - the 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 keyword is intended primarily - as an annotation, but can optionally be used as an assertion. The - keywords are annotations for working with documents - embedded as JSON strings. - -
- -
- -
- - 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. - -
- -
- - 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. - -
- -
- - 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 specification. - -
- -
- -
- - The current IRI for the default JSON Schema dialect meta-schema is - . - For schema author convenience, this meta-schema describes a dialect - consisting of all vocabularies - defined in this specification and the JSON Schema Core specification, - as well as two former keywords which are reserved for a transitional period. - Individual vocabulary and vocabulary meta-schema IRIs are given for - each section below. Certain vocabularies are optional to support, which - is explained in detail in the relevant sections. - - - 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. - -
- -
- - Validation keywords in a schema impose requirements for successful validation of an - instance. These keywords are all assertions without any annotation behavior. - - - 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. - - - The current IRI for this vocabulary, known as the Validation vocabulary, is: - <https://json-schema.org/draft/next/vocab/validation>. - - - The current IRI for the corresponding meta-schema is: - . - - -
-
- - 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. - - - String values MUST be one of the six primitive types - ("null", "boolean", "object", "array", "number", or "string"), - or "integer" which matches any number with a zero fractional part. - - - If the value of "type" is a string, then an instance validates successfully if - 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. - -
- -
- - The value of this keyword MUST be an array. This array SHOULD have at - least one element. Elements in the array SHOULD be unique. - - - An instance validates successfully against this keyword if its value is - equal to one of the elements in this keyword's array value. - - - Elements in the array might be of any type, including null. - -
- -
- - The value of this keyword MAY be of any type, including null. - - - Use of this keyword is functionally equivalent to an - "enum" with a single value. - - - An instance validates successfully against this keyword if its value is - equal to the value of the keyword. - -
-
- -
-
- - 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. - -
- -
- - The value of "maximum" MUST be a number, representing an inclusive upper limit - for a numeric instance. - - - If the instance is a number, then this keyword validates only if the instance is - less than or exactly equal to "maximum". - -
- -
- - The value of "exclusiveMaximum" MUST be a number, representing an exclusive upper - limit for a numeric instance. - - - If the instance is a number, then the instance is valid only if it has a value - strictly less than (not equal to) "exclusiveMaximum". - -
- -
- - The value of "minimum" MUST be a number, representing an inclusive lower limit - for a numeric instance. - - - If the instance is a number, then this keyword validates only if the instance is - greater than or exactly equal to "minimum". - -
- -
- - 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". - -
-
- -
-
- - 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 equal to, the value of this keyword. - - - The length of a string instance is defined as the number of its - characters as defined by RFC 8259. - -
- -
- - 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, or equal to, the value of this keyword. - - - - The length of a string instance is defined as the number of its - characters as defined by RFC 8259. - - - Omitting this keyword has the same behavior as a value of 0. - -
- -
- - 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. - - - A string instance is considered valid if the regular - expression matches the instance successfully. Recall: regular - expressions are not implicitly anchored. - -
-
- -
- -
- - 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. - -
- -
- - 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 equal to, the value of this keyword. - - - Omitting this keyword has the same behavior as a value of 0. - -
- -
- - The value of this keyword MUST be a boolean. - - - If this keyword has boolean value false, the instance validates - successfully. If it has boolean value true, the instance validates - successfully if all of its elements are unique. - - - Omitting this keyword has the same behavior as a value of false. - -
-
- -
-
- - 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. - -
- -
- - The value of this keyword MUST be a non-negative integer. - - - An object instance is valid against "minProperties" if its - number of properties is greater than, or equal to, the value of this - keyword. - - - Omitting this keyword has the same behavior as a value of 0. - -
- -
- - The value of this keyword MUST be an array. - Elements of this array, if any, MUST be strings, and MUST be unique. - - - An object instance is valid against this keyword if every item in the array is - the name of a property in the instance. - - - Omitting this keyword has the same behavior as an empty array. - -
- -
- - 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. - - - This keyword specifies properties that are required if a specific - other property is present. Their requirement is dependent on the - presence of the other property. - - - Validation succeeds if, for each name that appears in both - the instance and as a name within this keyword's value, every - item in the corresponding array is also the name of a property - in the instance. - - - Omitting this keyword has the same behavior as an empty object. - -
-
-
- -
- -
- - 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 which are - accurately described by authoritative resources, be they RFCs or other external - specifications. - - - - The value of this keyword is called a format attribute. It MUST be a string. A - format attribute can generally only validate a given set of instance types. If - the type of the instance to validate is not in this set, validation for this - format attribute and instance SHOULD succeed. All format attributes defined - in this section apply to strings, but a format attribute can be specified - to apply to any instance types defined in the data model defined in the - core JSON Schema. - - Note that the "type" keyword in this specification defines an "integer" type - which is not part of the data model. Therefore a format attribute can be - limited to numbers, but not specifically to integers. However, a numeric - format can be used alongside the "type" keyword with a value of "integer", - or could be explicitly defined to always pass if the number is not an integer, - which produces essentially the same behavior as only applying to integers. - - - - - The current IRI for this vocabulary, known as the Format-Annotation vocabulary, is: - <https://json-schema.org/draft/next/vocab/format-annotation>. The current - IRI for the corresponding meta-schema is: - . - Implementing support for this vocabulary is REQUIRED. - - - In addition to the Format-Annotation vocabulary, a secondary vocabulary is available - for custom meta-schemas that defines "format" as an assertion. The IRI for the - Format-Assertion vocabulary, is: - <https://json-schema.org/draft/next/vocab/format-assertion>. The current - IRI for the corresponding meta-schema is: - . - Implementing support for the Format-Assertion vocabulary is OPTIONAL. - - - Specifying both the Format-Annotation and the Format-Assertion vocabularies is functionally - equivalent to specifying only the Format-Assertion vocabulary since its requirements - are a superset of the Format-Annotation vocabulary. - -
- -
- - The "format" keyword functions as defined by the vocabulary which is referenced. - - -
- - 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 - semantics. The implementation MUST provide options to enable and disable such - evaluation and MUST be disabled by default. Implementations SHOULD document - their level of support for such validation. - - Specifying the Format-Annotation vocabulary and enabling validation in an - implementation should not be viewed as being equivalent to specifying - the Format-Assertion vocabulary since implementations are not required to - provide 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; - - - MAY choose to implement validation of any or all format attributes - as a no-op by always producing a validation result of true; - - - - This matches the current reality of implementations, which provide - widely varying levels of validation, including no validation at all, - for some or all format attributes. It is also designed to encourage - relying only on the annotation behavior and performing semantic - validation in the application, which is the recommended best practice. - - -
- -
- - 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 - 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; - - - 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 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, attempt to connect - to a URL, or otherwise check the existence of an entity identified by a format - instance. - - The expectation is that for simple formats such as date-time, syntactic - validation will be thorough. For a complex format such as email addresses, - which are the amalgamation of various standards and numerous adjustments - over time, with obscure and/or obsolete rules that may or may not be - restricted by other applications making use of the value, a minimal validation - is sufficient. For example, an instance string that does not contain - an "@" is clearly not a valid email address, and an "email" or "hostname" - containing characters outside of 7-bit ASCII is likewise clearly invalid. - - - - 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 - 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 increase code size and in some cases execution time, - and will not be appropriate for all implementations. - -
-
- - 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 formats - as annotations. When the Format-Assertion vocabulary is specified, implementations - MUST fail upon encountering unknown formats. - - - Vocabularies do not support specifically declaring different value sets for keywords. - Due to this limitation, and the historically uneven implementation of this keyword, - it is RECOMMENDED to define additional keywords in a custom vocabulary rather than - additional format attributes if interoperability is desired. - -
-
- -
- -
- - These attributes apply to string instances. - - - Date and time format names are derived from - RFC 3339, section 5.6. - The duration format is from the ISO 8601 ABNF as given - in Appendix A of RFC 3339. - - - Implementations supporting formats SHOULD implement support for - the following attributes: - - - A string instance is valid against this attribute if it is - a valid representation according to the "date-time' ABNF rule - (referenced above) - - - A string instance is valid against this attribute if it is - a valid representation according to the "full-date" ABNF rule - (referenced above) - - - A string instance is valid against this attribute if it is - a valid representation according to the "full-time" ABNF rule - (referenced above) - - - A string instance is valid against this attribute if it is - a valid 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 corresponding short form ("date" or "time" - respectively) MUST be implemented, and MUST behave identically. - Implementations SHOULD NOT define extension attributes - with any name matching an RFC 3339 format unless it validates - according to the rules of that format. - - There is not currently consensus on the need for supporting - all RFC 3339 formats, so this approach of reserving the - namespace will encourage experimentation without committing - to the entire set. Either the format implementation requirements - will become more flexible in general, or these will likely - either be promoted to fully specified attributes or dropped. - - -
- -
- - These attributes apply to string instances. - - - A string instance is valid against these attributes if it is a valid - Internet email address as follows: - - - As defined by the "Mailbox" ABNF rule in - RFC 5321, section 4.1.2. - - - As defined by the extended "Mailbox" ABNF rule in - RFC 6531, section 3.3. - - - Note that all strings valid against the "email" attribute are also - valid against the "idn-email" attribute. - -
-
- - 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: - - - As defined by RFC 1123, section 2.1, - including host names produced using the Punycode algorithm - specified in RFC 5891, section 4.4. - - - As defined by either RFC 1123 as for hostname, or an - internationalized hostname as defined by - RFC 5890, section 2.3.2.3. - - - Note that all strings valid against the "hostname" attribute are also - valid against the "idn-hostname" attribute. - -
- -
- - 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: - - - An IPv4 address according to the "dotted-quad" ABNF - syntax as defined in - RFC 2673, section 3.2. - - - An IPv6 address as defined in - RFC 4291, section 2.2. - - - -
- -
- - These attributes apply to string instances. - - - - - A string instance is valid against this attribute if it is - a valid IRI, according to . - - - A string instance is valid against this attribute if it is a valid URI - Reference (either a URI or a relative-reference), - according to . - - - A string instance is valid against this attribute if it is - a valid IRI, according to . - - - A string instance is valid against this attribute if it is a valid IRI - Reference (either an IRI or a relative-reference), - according to . - - - A string instance is valid against this attribute if it is a valid - string representation of a UUID, according to . - - - - - Note that all valid URIs are valid IRIs, and all valid URI References are - also valid IRI References. - - - Note also that the "uuid" format is for plain UUIDs, not UUIDs in URNs. An example - is "f81d4fae-7dec-11d0-a765-00a0c91e6bf6". For UUIDs as URNs, use the "uri" format, - with a "pattern" regular expression of "^urn:uuid:" to indicate the URI scheme and - URN namespace. - -
- -
- - 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 . - - - Note that URI Templates may be used for IRIs; there is no separate - IRI Template specification. - -
- -
- - These attributes apply to string instances. - - - - - 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. - - - A string instance is valid against this attribute if it is a valid - Relative JSON Pointer. - - - To allow for both absolute and relative JSON Pointers, use "anyOf" or - "oneOf" to indicate support for either format. - -
-
- - This attribute applies to string instances. - - - A regular expression, which SHOULD be valid according to the - ECMA-262 regular expression dialect. - - - Implementations that validate formats MUST accept at least the subset of - ECMA-262 defined in the Regular Expressions - section of this specification, and SHOULD accept all valid ECMA-262 expressions. - -
-
-
- -
- -
- - Annotations defined in this section indicate that an instance contains - non-JSON data encoded in a JSON string. - - - These properties provide additional information required to interpret JSON data - as rich multimedia documents. They describe the type of content, how it is encoded, - and/or how it may be validated. They do not function as validation assertions; - a malformed string-encoded document MUST NOT cause the containing instance - to be considered invalid. - - - 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. - - - The current IRI for this vocabulary, known as the Content vocabulary, is: - <https://json-schema.org/draft/next/vocab/content>. - - - The current IRI for the corresponding meta-schema is: - . - -
- -
- - 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 - annotations to invoke the appropriate libraries separately. - - - All keywords in this section apply only to strings, and have no - effect on other data types. - -
- -
- - - 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. - - - - Possible values indicating base 16, 32, and 64 encodings with several - variations are listed in RFC 4648. Additionally, - sections 6.7 and 6.8 of RFC 2045 provide - encodings used in MIME. This keyword is derived from MIME's - Content-Transfer-Encoding header, which was designed to map binary data - into ASCII characters. It is not related to HTTP's Content-Encoding header, - which is used to encode (e.g. compress or encrypt) - the content of HTTP request and responses. - - - As "base64" is defined in both RFCs, the definition - from RFC 4648 SHOULD be assumed unless the string is specifically intended - for use in a MIME context. Note that all of these encodings result in - strings consisting only of 7-bit ASCII characters. Therefore, this keyword - has no meaning for strings containing characters outside of that range. - - - - If this keyword is absent, but "contentMediaType" is present, this - indicates that the encoding is the identity encoding, meaning that - no transformation was needed in order to represent the content in - a UTF-8 string. - - - - The value of this property MUST be a string. - -
- -
- - 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. - - - The value of this property MUST be a string, which MUST be a media type, - as defined by RFC 2046. - -
- -
- - If the instance is a string, and if "contentMediaType" is present, this - property contains a schema which describes the structure of the string. - - - This keyword MAY be used with any media type that can be mapped into - JSON Schema's data model. Specifying such mappings is outside of the - scope of this specification. - - - The value of this property MUST be a valid JSON schema. It SHOULD be ignored if - "contentMediaType" is not present. Accessing the schema through the schema location - IRI included as part of the annotation will ensure that it is correctly processed - as a subschema. Using the extracted annotation value directly is only safe if - the schema is an embedded resource with both "$schema" and an absolute-IRI "$id". - -
- -
-
- - Here is an example schema, illustrating the use of "contentEncoding" and - "contentMediaType": - - - - - - Instances described by this schema are expected to be strings, - and their values should be interpretable as base64-encoded PNG images. - -
- -
- - Another example: - - - - - - Instances described by this schema are expected to be strings containing HTML, - using whatever character set the JSON string was decoded into. - Per section 8.1 of - RFC 8259, outside of an entirely closed - system, this MUST be UTF-8. - -
- -
- - This example describes a JWT that is MACed using the HMAC SHA-256 - algorithm, and requires the "iss" and "exp" fields in its claim set. - - - - - - Note that "contentEncoding" does not appear. While the "application/jwt" - media type makes use of base64url encoding, that is defined by the media - type, which determines how the JWT string is decoded into a list of two - JSON data 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. - -
-
- -
- -
- - 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. - - - The current IRI for this vocabulary, known as the Meta-Data vocabulary, is: - <https://json-schema.org/draft/next/vocab/meta-data>. - - - The current IRI for the corresponding meta-schema is: - . - - -
- - 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 about the data produced by this user interface. A title will - preferably be short, whereas a description will provide explanation about - the purpose of the instance described by this schema. - -
- -
- - 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. - - - This keyword can be used to supply a default JSON value associated with a - particular schema. It is RECOMMENDED that a default value be valid against - the associated schema. - -
- -
- - 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. - - - If "deprecated" has a value of boolean true, it indicates that applications - SHOULD refrain from usage of the declared property. It MAY mean the property - is going to be removed in the future. - - - A root schema containing "deprecated" with a value of true indicates that - the entire resource being described MAY be removed in the future. - - - The "deprecated" keyword applies to each instance location to which the - schema object containing the keyword successfully applies. This can - result in scenarios where every array item or object property - is deprecated even though the containing array or object is not. - - - Omitting this keyword has the same behavior as a value of false. - -
- -
- - 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 SHOULD be as for a false value otherwise. - - - If "readOnly" has a value of boolean true, it indicates that the value - of the instance is managed exclusively by the owning authority, and - attempts by an application to modify the value of this property are - expected to be ignored or rejected by that owning authority. - - - An instance document that is marked as "readOnly" for the entire document - MAY be ignored if sent to the owning authority, or MAY result in an - error, at the authority's discretion. - - - If "writeOnly" has a value of boolean true, it indicates that the value - is never present when the instance is retrieved from the owning authority. - It can be present when sent to the owning authority to update or create - the document (or the resource it represents), but it will not be included - in any updated or newly created version of the instance. - - - An instance document that is marked as "writeOnly" for the entire document - MAY be returned as a blank document of some sort, or MAY produce an error - upon retrieval, or have the retrieval request ignored, at the authority's - discretion. - - - For example, "readOnly" would be used to mark a database-generated serial - number as read-only, while "writeOnly" would be used to mark a password - input field. - - - These keywords can be used to assist in user interface instance generation. - In particular, an application MAY choose to use a widget that hides - input values as they are typed for write-only fields. - - - Omitting these keywords has the same behavior as values of false. - -
- -
- - 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 of all - values rather than an array of arrays. - - - This keyword can be used to provide sample JSON values associated with a - particular schema, for the purpose of illustrating usage. It is - RECOMMENDED that 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. - -
-
- -
- - JSON Schema validation defines a vocabulary for JSON Schema core and concerns all - the security considerations listed there. - - - JSON Schema validation allows the use of Regular Expressions, which have numerous - different (often incompatible) implementations. - Some implementations allow the embedding of arbitrary code, which is outside the - scope of JSON Schema and MUST NOT be permitted. - Regular expressions can often also be crafted to be extremely expensive to compute - (with so-called "catastrophic backtracking"), resulting in a denial-of-service - attack. - - - Implementations that support validating or otherwise evaluating instance - string data based on "contentEncoding" and/or "contentMediaType" are at - risk of evaluating data in an unsafe way based on misleading information. - Applications can mitigate this risk by only performing such processing - when a relationship between the schema and instance is established - (e.g., they share the same authority). - - - Processing a media type or encoding is subject to the security considerations - of that media type or encoding. For example, the security considerations - of RFC 4329 Scripting Media Types apply when - processing JavaScript or ECMAScript encoded within a JSON string. - -
- - - - - - - - &RFC2119; - &RFC1123; - &RFC2045; - &RFC2046; - &RFC2673; - &RFC3339; - &RFC3986; - &RFC3987; - &RFC4122; - &RFC4291; - &RFC4648; - &RFC5321; - &RFC5890; - &RFC5891; - &RFC6570; - &RFC6531; - &RFC6901; - &RFC8259; - - - ECMA-262, 11th edition specification - - - - - - - Relative JSON Pointers - - - - - Cloudflare, Inc. - - - - - - - - - - JSON Schema: A Media Type for Describing JSON Documents - - - - - - - - - - - - - - - - - - - - &RFC4329; - - -
- - Several keywords have been moved from this document into the - Core Specification starting with draft 2019-09, - in some cases with re-naming or other changes. This affects the following former - validation keywords: - - - 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. - - - 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. - - - These keywords modify the behavior of "contains", and are therefore - grouped with it in the applicator vocabulary. - - - 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. - - - -
- -
- - Thanks to - Gary Court, - Francis Galiegue, - Kris Zyp, - Geraint Luff, - and Henry Andrews - for their work on the initial drafts of JSON Schema. - - - Thanks to - Jason Desrosiers, - Daniel Perrett, - Erik Wilde, - Evgeny Poberezkin, - Brad Bowman, - Gowry Sankar, - Donald Pipowitch, - Dave Finlay, - Denis Laxalde, - Phil Sturgeon, - Shawn Silverman, - and Karen Etheridge - for their submissions and patches to the document. - -
- -
- - This section to be removed before leaving Internet-Draft status. - - - - - - Use IRIs instead of URIs - - - - - Improve and clarify the "minContains" keyword explanation - Remove the use of "production" in favour of "ABNF rule" - - - - - Correct email format RFC reference to 5321 instead of 5322 - Clarified the set and meaning of "contentEncoding" values - Reference ECMA-262, 11th edition for regular expression support - Split "format" into an annotation only vocabulary and an assertion vocabulary - Clarify "deprecated" when applicable to arrays - - - - - 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 - 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 - Renamed the array form of "dependencies" to "dependentRequired", moved the schema form to the core spec - Specified all "content*" keywords as annotations, not assertions - Added "contentSchema" to allow applying a schema to a string-encoded document - Also allow RFC 4648 encodings in "contentEncoding" - Added "minContains" and "maxContains" - Update RFC reference for "hostname" and "idn-hostname" - Add "uuid" and "duration" formats - - - - - This draft is purely a clarification with no functional changes - Provided the general principle behind ignoring annotations under "not" and similar cases - Clarified "if"/"then"/"else" validation interactions - Clarified "if"/"then"/"else" behavior for annotation - Minor formatting and cross-referencing improvements - - - - - Added "if"/"then"/"else" - Classify keywords as assertions or annotations per the core spec - Warn of possibly removing "dependencies" in the future - Grouped validation keywords into sub-sections for readability - Moved "readOnly" from hyper-schema to validation meta-data - Added "writeOnly" - Added string-encoded media section, with former hyper-schema "media" keywords - Restored "regex" format (removal was unintentional) - Added "date" and "time" formats, and reserved additional RFC 3339 format names - I18N formats: "iri", "iri-reference", "idn-hostname", "idn-email" - Clarify that "json-pointer" format means string encoding, not URI fragment - Fixed typo that inverted the meaning of "minimum" and "exclusiveMinimum" - Move format syntax references into Normative References - JSON is a normative requirement - - - - - Standardized on hyphenated format names with full words ("uriref" becomes "uri-reference") - Add the formats "uri-template" and "json-pointer" - Changed "exclusiveMaximum"/"exclusiveMinimum" from boolean modifiers of "maximum"/"minimum" to independent numeric fields. - Split the additionalItems/items into two sections - Reworked properties/patternProperties/additionalProperties definition - Added "examples" keyword - Added "contains" keyword - Allow empty "required" and "dependencies" arrays - Fixed "type" reference to primitive types - Added "const" keyword - Added "propertyNames" keyword - - - - - Added additional security considerations - Removed reference to "latest version" meta-schema, use numbered version instead - Rephrased many keyword definitions for brevity - Added "uriref" format that also allows relative URI references - - - - - Initial draft. - Salvaged from draft v3. - Redefine the "required" keyword. - Remove "extends", "disallow" - Add "anyOf", "allOf", "oneOf", "not", "definitions", "minProperties", - "maxProperties". - "dependencies" member values can no longer be single strings; at - least one element is required in a property dependency array. - Rename "divisibleBy" to "multipleOf". - "type" arrays can no longer have schemas; remove "any" as a possible - value. - Rework the "format" section; make support optional. - "format": remove attributes "phone", "style", "color"; rename - "ip-address" to "ipv4"; add references for all attributes. - Provide algorithms to calculate schema(s) for array/object - instances. - Add interoperability considerations. - - - - -
- - diff --git a/package.json b/package.json new file mode 100644 index 00000000..866e2d8c --- /dev/null +++ b/package.json @@ -0,0 +1,33 @@ +{ + "name": "json-schema-org/json-schema-spec", + "version": "1.0.0", + "description": "The JSON Schema Specification", + "type": "module", + "main": "index.js", + "scripts": { + "lint": "eslint *.js", + "build": "npm run build-core && npm run build-validation", + "build-core": "node build/build.js < jsonschema-core.md > jsonschema-core.html", + "build-validation": "node build/build.js < jsonschema-validation.md > jsonschema-validation.html" + }, + "license": "MIT", + "dependencies": { + "rehype-autolink-headings": "^6.1.1", + "rehype-slug": "^5.1.0", + "rehype-stringify": "^9.0.3", + "remark": "^14.0.3", + "remark-flexible-containers": "^1.0.6", + "remark-gfm": "^3.0.1", + "remark-preset-lint-markdown-style-guide": "^5.1.3", + "remark-rehype": "^10.1.0", + "remark-toc": "^8.0.1", + "remark-torchlight": "^0.0.5", + "vfile-reporter": "^8.0.0" + }, + "devDependencies": { + "dotenv": "^16.3.1", + "eslint": "*", + "eslint-import-resolver-node": "*", + "eslint-plugin-import": "*" + } +} From 2c7b8c4baad5cff50f4cdfa8e171d1ca61b3669e Mon Sep 17 00:00:00 2001 From: Jason Desrosiers Date: Fri, 28 Jul 2023 16:06:39 -0700 Subject: [PATCH 02/11] Auto number appendices and other cleanup --- README.md | 2 ++ build/build.js | 30 ++++++++++------ build/remark-number-headings.js | 26 ++++++++++---- jsonschema-core.md | 63 ++++++++++++++------------------- jsonschema-validation.md | 22 ++++-------- package.json | 7 ++-- 6 files changed, 76 insertions(+), 74 deletions(-) diff --git a/README.md b/README.md index 73a6da2d..c8e013e7 100644 --- a/README.md +++ b/README.md @@ -38,6 +38,8 @@ features they make available to you. - [remark-lint](https://github.com/remarkjs/remark-lint) -- Enforce markdown styles guide. +- [remark-validate-links](https://github.com/remarkjs/remark-validate-links) -- + Check for broken links. - [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. diff --git a/build/build.js b/build/build.js index 403d7660..8f888480 100644 --- a/build/build.js +++ b/build/build.js @@ -1,18 +1,18 @@ -/* eslint-disable no-console */ import dotenv from "dotenv"; import { readFileSync, writeFileSync } from "node:fs"; import { reporter } from "vfile-reporter"; import { remark } from "remark"; -import remarkPresetLintMarkdownStyleGuide from "remark-preset-lint-markdown-style-guide"; -import remarkGfm from "remark-gfm"; -import remarkToc from "remark-toc"; -import torchLight from "remark-torchlight"; -import remarkRehype from "remark-rehype"; -import rehypeSlug from "rehype-slug"; import rehypeAutolinkHeadings from "rehype-autolink-headings"; +import rehypeSlug from "rehype-slug"; import rehypeStringify from "rehype-stringify"; -import remarkNumberHeadings from "./remark-number-headings.js"; import remarkFlexibleContainers from "remark-flexible-containers"; +import remarkGfm from "remark-gfm"; +import remarkNumberHeadings from "./remark-number-headings.js"; +import remarkPresetLintMarkdownStyleGuide from "remark-preset-lint-markdown-style-guide"; +import remarkRehype from "remark-rehype"; +import remarkToc from "remark-toc"; +import remarkValidateLinks from "remark-validate-links"; +import torchLight from "remark-torchlight"; dotenv.config(); @@ -22,10 +22,20 @@ dotenv.config(); const html = await remark() .use(remarkPresetLintMarkdownStyleGuide) .use(remarkGfm) - .use(remarkNumberHeadings, { startDepth: 2, skip: ["Abstract", "Note to Readers", "Table of Contents"] }) - .use(remarkToc, { tight: true, heading: "Table of Contents" }) .use(torchLight) .use(remarkFlexibleContainers) + .use(remarkNumberHeadings, { + startDepth: 2, + skip: ["Abstract", "Note to Readers", "Table of Contents", "Authors' Addresses", "\\[.*\\]", "draft-.*"], + appendixToken: "[Appendix]", + appendixPrefix: "Appendix" + }) + .use(remarkToc, { + tight: true, + heading: "Table of Contents", + skip: "\\[.*\\]|draft-.*" + }) + .use(remarkValidateLinks) .use(remarkRehype) .use(rehypeSlug) .use(rehypeAutolinkHeadings, { behavior: "wrap" }) diff --git a/build/remark-number-headings.js b/build/remark-number-headings.js index 8517e042..30800774 100644 --- a/build/remark-number-headings.js +++ b/build/remark-number-headings.js @@ -8,6 +8,7 @@ const defaultOptions = { const remarkNumberHeadings = (options) => (tree) => { options = { ...defaultOptions, ...options }; + options.skip = new RegExp(`^(${options.skip.join("|")})$`, "u"); let sectionNumbers = []; @@ -17,17 +18,28 @@ const remarkNumberHeadings = (options) => (tree) => { } visit(node, "text", (textNode) => { - const text = textNode.value ? textNode.value.trim() : ""; + let text = textNode.value ? textNode.value.trim() : ""; - if (options.skip.includes(text)) { + if (options.skip.test(text)) { return; } - sectionNumbers[node.depth] = (sectionNumbers[node.depth] ?? 0) + 1; - sectionNumbers = sectionNumbers.slice(0, node.depth + 1); - - const sectionNumber = sectionNumbers.slice(options.startDepth, node.depth + 1).join("."); - textNode.value = `${sectionNumber}. ${text}`; + if (text.startsWith(options.appendixToken)) { + const currentIndex = typeof sectionNumbers[node.depth] === "string" + ? sectionNumbers[node.depth] + : "@"; + sectionNumbers[node.depth] = String.fromCharCode(currentIndex.charCodeAt(0) + 1); + sectionNumbers = sectionNumbers.slice(0, node.depth + 1); + + const sectionNumber = sectionNumbers.slice(options.startDepth, node.depth + 1).join("."); + textNode.value = `${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}. ${text}`; + } }); }); }; diff --git a/jsonschema-core.md b/jsonschema-core.md index 09ee2bcb..b75e4405 100644 --- a/jsonschema-core.md +++ b/jsonschema-core.md @@ -2768,7 +2768,7 @@ Bray, T., Ed., Hollander, D., Ed., Layman, A., Ed., and R. Tobin, Ed., "Namespaces in XML 1.1 (Second Edition)", August 2006, <>. -## Appendix A. Schema identification examples +## [Appendix] Schema identification examples Consider the following schema, which shows `$id` being used to identify both the root schema and various subschemas, and `$anchor` being used to define plain name fragment identifiers. @@ -2841,12 +2841,12 @@ embedded schema resources](#921-json-pointer-fragments-and-embedded-schema-resources) section for futher comments. -## Appendix B. Manipulating schema documents and references +## [Appendix] Manipulating schema documents and references Various tools have been created to rearrange schema documents based on how and where references (`$ref`) appear. This appendix discusses which use cases and actions are compliant with this specification. -### B.1. Bundling schema resources into a single document +### 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. @@ -2868,7 +2868,7 @@ changing any aspect of validation or annotation results. The names of the schemas under `$defs` do not affect behavior, assuming they are each unique, as they do not appear in the canonical IRIs for the embedded resources. -### B.2. Reference removal is not always safe +### Reference removal is not always safe Attempting to remove all references and produce a single schema document does not, in all cases, produce a schema with identical behavior to the original form. @@ -2880,7 +2880,7 @@ scope of this specification to determine or provide a set of safe `$ref` removal transformations, as they depend not only on the schema structure but also on the intended usage. -## Appendix C. Example of recursive schema extension +## [Appendix] Example of recursive schema extension 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 @@ -2976,9 +2976,9 @@ of the node schema objects were moved under `$defs`. It is the matching `$dynamicAnchor` values which tell us how to resolve the dynamic reference, not any sort of correlation in JSON structure. -## Appendix D. Working with vocabularies +## [Appendix] Working with vocabularies -### D.1. Best practices for vocabulary and meta-schema authors +### Best practices for vocabulary and meta-schema authors 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 @@ -3026,7 +3026,7 @@ resulting behavior is undefined. Meta-schemas intended for local use, with no need to test for vocabulary support in arbitrary implementations, can safely omit `$vocabulary` entirely. -### D.2. Example meta-schema with vocabulary declarations +### Example meta-schema with vocabulary declarations This meta-schema explicitly declares both the Core and Applicator vocabularies, together with an extension vocabulary, and combines their meta-schemas with an `allOf`. The extension vocabulary's meta-schema, which describes only the @@ -3118,7 +3118,7 @@ to ensure that it is validated even when `format` functions purely as an annotation, as explained in the [Validation specification](#json-schema-validation). -## Appendix E. References and generative use cases +## [Appendix] References and generative use cases While the presence of references is expected to be transparent to validation results, generative use cases such as code generators and UI renderers often consider references to be semantically significant. @@ -3167,7 +3167,7 @@ instance of a distinct class. This style of usage requires the annotation to be in the same object as the reference, which must be recognizable as a reference. -## Appendix F. Acknowledgments +## [Appendix] Acknowledgments Thanks to Gary Court, Francis Galiegue, Kris Zyp, Geraint Luff, and Henry Andrews for their work on the initial drafts of JSON Schema. @@ -3176,16 +3176,16 @@ Bowman, Gowry Sankar, Donald Pipowitch, Dave Finlay, Denis Laxalde, Phil Sturgeon, Shawn Silverman, and Karen Etheridge for their submissions and patches to the document. -## Appendix G. Change Log[^19] +## [Appendix] Change Log[^19] [^19]: This section to be removed before leaving Internet-Draft status. -### G.1. draft-bhutton-json-schema-next +### draft-bhutton-json-schema-next - `contains` now applies to objects as well as arrays - Use IRIs instead of URIs - Remove bookending requirement for `$dynamicRef` - Add `propertyDependencies` keyword -### G.2. draft-bhutton-json-schema-01 +### draft-bhutton-json-schema-01 - Improve and clarify the `type`, `contains`, `unevaluatedProperties`, and `unevaluatedItems` keyword explanations - Clarify various aspects of "canonical URIs" @@ -3194,7 +3194,7 @@ to the document. - Remove references to remaining media-type parameters - Fix multiple examples -### G.3. draft-bhutton-json-schema-00 +### draft-bhutton-json-schema-00 - `$schema` MAY change for embedded resources - Array-value `items` functionality is now `prefixItems` - `items` subsumes the old function of `additionalItems` @@ -3211,7 +3211,7 @@ interactions now specified - Moved `unevaluatedItems` and `unevaluatedProperties` from core into their own vocabulary -### G.4. draft-handrews-json-schema-02 +### draft-handrews-json-schema-02 - Update to RFC 8259 for JSON specification - Moved `definitions` from the Validation specification here as `$defs` - Moved applicator keywords from the Validation specification as their own @@ -3237,7 +3237,7 @@ meta-schemas - Clarified that the behavior of JSON Pointers across `$id` boundary is unreliable -### G.5. draft-handrews-json-schema-01 +### draft-handrews-json-schema-01 - This draft is purely a clarification with no functional changes - Emphasized annotations as a primary usage of JSON Schema - Clarified $id by use cases @@ -3250,7 +3250,7 @@ schema identifiers during parsing same process - Minor formatting improvements -### G.6. draft-handrews-json-schema-00 +### draft-handrews-json-schema-00 - Make the concept of a schema keyword vocabulary more clear - Note that the concept of "integer" is from a vocabulary, not the data model - Classify keywords as assertions or annotations and describe their general @@ -3262,7 +3262,7 @@ behavior - Add `application/schema-instance+json` media type - Recommend a "schema" link relation / parameter instead of "profile" -### G.7. draft-wright-json-schema-01 +### draft-wright-json-schema-01 - Updated intro - Allowed for any schema to be a boolean - `$schema` SHOULD NOT appear in subschemas, although that may change @@ -3271,7 +3271,7 @@ behavior - Note applicability to formats such as CBOR that can be represented in the JSON data model -### G.8. draft-wright-json-schema-00 +### draft-wright-json-schema-00 - Updated references to JSON - Updated references to HTTP - Updated references to JSON Pointer @@ -3286,7 +3286,7 @@ data model - Rewrote section on usage with rel="describedBy" and rel="profile" - Fixed numerous invalid examples -### G.9. draft-zyp-json-schema-04 +### draft-zyp-json-schema-04 - Salvaged from draft v3. - Split validation keywords into separate document. - Split hypermedia keywords into separate document. @@ -3295,23 +3295,12 @@ data model - Define the role of `id`. Define URI resolution scope. - Add interoperability considerations. -### G.10. draft-zyp-json-schema-00 +### draft-zyp-json-schema-00 - Initial draft. ## Authors' Addresses - -### Austin Wright (*editor*) -Email: - -### Ben Hutton (*editor*) -Postman - -Email: - -URI: - -### Greg Dennis - -Email: - -URI: +| Author | Company | Email | URI | +|--------------------------|---------|-------------------------|----------------------------------| +| Austin Wright (*editor*) | | | | +| Ben Hutton (*editor*) | Postman | | | +| Greg Dennis | | | | diff --git a/jsonschema-validation.md b/jsonschema-validation.md index f22c50ec..7a4777b3 100644 --- a/jsonschema-validation.md +++ b/jsonschema-validation.md @@ -895,7 +895,7 @@ draft-bhutton-json-schema-01, June 2022, Hoehrmann, B., "Scripting Media Types", RFC 4329, DOI 10.17487/RFC4329, April 2006, <>. -## Appendix A. Keywords Moved from Validation to Core +## [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 @@ -928,7 +928,7 @@ 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 B. Acknowledgments +## [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. @@ -937,7 +937,7 @@ Bowman, Gowry Sankar, Donald Pipowitch, Dave Finlay, Denis Laxalde, Phil Sturgeon, Shawn Silverman, and Karen Etheridge for their submissions and patches to the document. -## Appendix C. ChangeLog[^6] +## [Appendix] ChangeLog[^6] [^6]: This section to be removed before leaving Internet-Draft status. - *draft-next* @@ -1032,15 +1032,7 @@ schema form to the core spec - Add interoperability considerations. ## Authors' Addresses - -### Austin Wright (*editor*) - -Email: - -### Ben Hutton (*editor*) - -Postman - -Email: - -URI: +| Author | Company | Email | URI | +|--------------------------|---------|----------------------|--------------------------| +| Austin Wright (*editor*) | | | | +| Ben Hutton (*editor*) | Postman | | | diff --git a/package.json b/package.json index 866e2d8c..fcf5d44f 100644 --- a/package.json +++ b/package.json @@ -5,7 +5,6 @@ "type": "module", "main": "index.js", "scripts": { - "lint": "eslint *.js", "build": "npm run build-core && npm run build-validation", "build-core": "node build/build.js < jsonschema-core.md > jsonschema-core.html", "build-validation": "node build/build.js < jsonschema-validation.md > jsonschema-validation.html" @@ -22,12 +21,10 @@ "remark-rehype": "^10.1.0", "remark-toc": "^8.0.1", "remark-torchlight": "^0.0.5", + "remark-validate-links": "^12.1.1", "vfile-reporter": "^8.0.0" }, "devDependencies": { - "dotenv": "^16.3.1", - "eslint": "*", - "eslint-import-resolver-node": "*", - "eslint-plugin-import": "*" + "dotenv": "^16.3.1" } } From b03c4b2ac21e2803c18ea930f5a05dca9cc12444 Mon Sep 17 00:00:00 2001 From: Jason Desrosiers Date: Fri, 28 Jul 2023 23:08:22 -0700 Subject: [PATCH 03/11] Add markdown syntax for section links --- build/build.js | 6 ++ build/remark-section-links.js | 43 ++++++++++++++ jsonschema-core.md | 105 ++++++++++++++++------------------ jsonschema-validation.md | 9 ++- package.json | 2 + 5 files changed, 105 insertions(+), 60 deletions(-) create mode 100644 build/remark-section-links.js diff --git a/build/build.js b/build/build.js index 8f888480..ddc39d7c 100644 --- a/build/build.js +++ b/build/build.js @@ -7,9 +7,12 @@ 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 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 remarkValidateLinks from "remark-validate-links"; import torchLight from "remark-torchlight"; @@ -24,12 +27,15 @@ dotenv.config(); .use(remarkGfm) .use(torchLight) .use(remarkFlexibleContainers) + .use(remarkHeadingId) .use(remarkNumberHeadings, { startDepth: 2, skip: ["Abstract", "Note to Readers", "Table of Contents", "Authors' Addresses", "\\[.*\\]", "draft-.*"], appendixToken: "[Appendix]", appendixPrefix: "Appendix" }) + .use(remarkHeadings) + .use(remarkSectionLinks) .use(remarkToc, { tight: true, heading: "Table of Contents", diff --git a/build/remark-section-links.js b/build/remark-section-links.js new file mode 100644 index 00000000..1c41e042 --- /dev/null +++ b/build/remark-section-links.js @@ -0,0 +1,43 @@ +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/jsonschema-core.md b/jsonschema-core.md index b75e4405..83997d53 100644 --- a/jsonschema-core.md +++ b/jsonschema-core.md @@ -92,7 +92,7 @@ A JSON document is an information resource (series of octets) described by the In JSON Schema, the terms "JSON document", "JSON text", and "JSON value" are interchangeable because of the data model it defines in -[Section 4.2.1](#421-instance-data-model). +{{instance-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 +109,7 @@ 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} JSON Schema interprets documents according to a data model. A JSON value interpreted according to this data model is called an "instance". @@ -219,7 +219,7 @@ 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 -[Section 6.5.2](#652-handling-of-unrecognized-or-unsupported-keywords). +{{unknown-keywords}}. An empty schema is a JSON Schema with no properties. @@ -281,7 +281,7 @@ 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 [Section 9.1.1](#911-initial-base-iri).[^1] +determined as described in {{initial-base-iri}}.[^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 @@ -303,7 +303,7 @@ schema titled "root" is the root schema. As with the root schema, a subschema is either an object or a boolean. -As discussed in [Section 8.2.1](#821-the-id-keyword), a 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 @@ -313,7 +313,7 @@ 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} 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 @@ -420,7 +420,7 @@ 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 +#### Handling of unrecognized or unsupported keywords {#unknown-keywords} 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 @@ -445,9 +445,9 @@ 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. The interactions of those keyword results to produce the schema object results -are governed by [Section 7.7.1.2](#7712-annotations-and-assertions), while the +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 [Section 7.5](#75-applicators). +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 @@ -507,7 +507,7 @@ 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). -### Default Behaviors +### 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 @@ -546,7 +546,7 @@ care not to disrupt the functioning of core keywords. For example, the to the matching `$dynamicRef` keyword, leaving the behavior of `$ref` undisturbed. -### Applicators +### 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 @@ -567,12 +567,12 @@ 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 [Section 7.7.1](#771-collecting-annotations) so that +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. #### Referenced and Referencing Schemas -As noted in [Section 7.5](#75-applicators), an applicator keyword may refer to a +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 @@ -657,7 +657,7 @@ 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} 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. @@ -752,7 +752,7 @@ 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} Schema objects that produce a false assertion result MUST NOT produce any annotation results, whether from their own keywords or from keywords in subschemas. @@ -787,10 +787,10 @@ re-use. These keywords do not affect validation or annotation results. Their 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 [Section -9.4.2](#942-references-to-possible-non-schemas) unrecognized extension keywords -that reserve locations for re-usable schemas may have undesirable interactions -with references in certain circumstances. +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. ### Loading Instance Data While none of the vocabularies defined as part of this or the associated @@ -803,7 +803,7 @@ 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 +## The JSON Schema Core Vocabulary {#core-vocabulary} Keywords declared in this section, which all begin with "$", make up the JSON Schema Core vocabulary. These keywords are either required in order to process any schema or meta-schema, including those split across multiple documents, or @@ -919,7 +919,7 @@ through `$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 `$vocabulary`, the set of vocabularies in use is determined according to -[Section 8.1.2.4](#8124-default-vocabularies). +{{default-vocabularies}}. Any vocabulary in use by a schema and understood by the implementation MUST be processed in a manner consistent with the semantic definitions contained within @@ -927,22 +927,20 @@ the vocabulary, regardless of whether that vocabulary is required or optional. Any vocabulary that is not present in `$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 [Section -8](#8-the-json-schema-core-vocabulary). +as specified by the introduction to {{core-vocabulary}}. 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 [Section -6.5.2](#652-handling-of-unrecognized-or-unsupported-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 +{{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. ##### Vocabularies are schema resource-scoped The `$vocabulary` keyword SHOULD be used in the root schema of any schema @@ -967,7 +965,7 @@ extension vocabularies. Guidance regarding vocabularies with identically-named keywords is provided in [Appendix D.1](#d1-best-practices-for-vocabulary-and-meta-schema-authors). -##### Default vocabularies +##### Default vocabularies {#default-vocabularies} If `$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 @@ -1012,7 +1010,7 @@ Several keywords can accept a relative [IRI-reference](#rfc3987), or a value 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 +#### The $id Keyword {#id-keyword} The `$id` keyword identifies a schema resource with its [canonical](#rfc6596) IRI. @@ -1037,11 +1035,11 @@ a relative IRI-reference, the base IRI for resolving that reference is the IRI of the parent schema resource. Note that an `$id` consisting of an empty IRI or of the empty fragment only will result in the embedded resource having the same IRI as the encapsulating resource, which SHOULD be considered an error per -[Section 8.2.3](#823-duplicate-schema-identifiers). +{{duplicate-identifiers}}. If no parent schema object explicitly identifies itself as a resource with `$id`, the base IRI is that of the entire document, as established by the steps -given in the [previous section.](#911-initial-base-iri) +given in the [previous section.](initial-base-iri) ##### Identifying the root schema The root schema of a JSON Schema document SHOULD contain an `$id` keyword with @@ -1076,14 +1074,14 @@ Therefore it is RECOMMENDED that `$anchor` be used to create plain name fragments unless there is a clear need for `$dynamicAnchor`. If present, the value of these keywords MUST be a string and MUST conform to the -plain name fragment identifier syntax defined in [Section -5](#5-fragment-identifiers).[^4] +plain name fragment identifier syntax defined in +{{fragment-identifiers}}.[^4] [^4]: Note that the anchor string does not include the "#" character, as it is not a IRI-reference. An `$anchor`: "foo" becomes the fragment `#foo` when used in a IRI. See below for full examples. -#### Duplicate schema identifiers +#### Duplicate schema identifiers {#duplicate-identifiers} 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`, `$dynamicAnchor`, or any @@ -1200,7 +1198,7 @@ MUST NOT be collected as an annotation result. ### Loading a Schema -#### Initial Base IRI +#### Initial Base IRI {#initial-base-iri} [RFC 3987 Section 6.5](#rfc3987) and [RFC 3986 Section 5.1](#rfc3986) defines how to determine the default base IRI of a document. @@ -1306,7 +1304,7 @@ described by Hyper-Schema, it is expected that new schemas will be added to the system dynamically, so placing an absolute requirement of pre-loading schema documents is not feasible. -#### JSON Pointer fragments and embedded schema resources +#### JSON Pointer fragments and embedded schema resources {#json-pointer-embedded} Since JSON Pointer IRI fragments are constructed based on the structure of the schema document, an embedded schema resource and its subschemas can be identified by JSON Pointer fragments relative to either its own canonical IRI, @@ -1478,7 +1476,7 @@ the other, a naive validator might get stuck in an infinite recursive loop trying to validate the instance. Schemas SHOULD NOT make use of infinite recursive nesting like this; the behavior is undefined. -#### References to Possible Non-Schemas +#### References to Possible Non-Schemas {#non-schema-references} Subschema objects (or booleans) are recognized by their use with known applicator keywords or with location-reserving keywords such as [`$defs`](#825-schema-re-use-with-defs) that take one or more subschemas as a @@ -1851,10 +1849,9 @@ 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 [Section 7.3](#73-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. @@ -2605,7 +2602,7 @@ Passing results (annotations) For convenience, JSON Schema has been provided to validate output generated by implementations. Its IRI is: . -## Security Considerations +## Security Considerations {#security-considerations} Both schemas and instances are JSON values. As such, all security considerations defined in [RFC 8259](#rfc8259) apply. @@ -2647,13 +2644,13 @@ 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 [Section 13](#13-security-considerations) above. +Security considerations:: See {{security-considerations}} above. Interoperability considerations:: See Sections [6.2](#62-programming-language-independence), [6.3](#63-mathematical-integers), and [6.4](#64-regular-expressions) above. -Fragment identifier considerations:: See [Section 5](#5-fragment-identifiers) +Fragment identifier considerations:: See {{fragment-identifiers}} ### application/schema-instance+json The proposed MIME media type for JSON Schema Instances that require a JSON @@ -2668,13 +2665,13 @@ 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 [Section 13](#13-security-considerations) above. +Security considerations:: See {{security-considerations}} above. Interoperability considerations:: See Sections [6.2](#62-programming-language-independence), [6.3](#63-mathematical-integers), and [6.4](#64-regular-expressions) above. -Fragment identifier considerations:: See [Section 5](#5-fragment-identifiers) +Fragment identifier considerations:: See {{fragment-identifiers}} ## References @@ -2797,8 +2794,8 @@ 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 [Section 5](#5-fragment-identifiers) and [Section -9.2.1](#921-json-pointer-fragments-and-embedded-schema-resources) above. +listed IRI in accordance with {{fragment-identifiers}} and +#section(json-pointer-embedded) above. `#` (document root): canonical (and base) IRI: `https://example.com/root.json` canonical resource IRI plus pointer fragment: `https://example.com/root.json#` @@ -2837,9 +2834,7 @@ 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](#921-json-pointer-fragments-and-embedded-schema-resources) section -for futher comments. +embedded schema resources](#json-pointer-embedded) section for further comments. ## [Appendix] Manipulating schema documents and references Various tools have been created to rearrange schema documents based on how and diff --git a/jsonschema-validation.md b/jsonschema-validation.md index 7a4777b3..60ead15a 100644 --- a/jsonschema-validation.md +++ b/jsonschema-validation.md @@ -53,10 +53,9 @@ 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 [Section -7](#7-vocabularies-for-semantic-content-with-format) keyword is intended +with useful information. The {{format-vocabulary}} keyword is intended primarily as an annotation, but can optionally be used as an assertion. The -[Section 8](#8-a-vocabulary-for-the-contents-of-string-encoded-data) keywords +{{content-vocabulary}} keywords are annotations for working with documents embedded as JSON strings. ## Interoperability Considerations @@ -269,7 +268,7 @@ 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 +## Vocabularies for Semantic Content With format {#format-vocabulary} ### Foreword Structural validation alone may be insufficient to allow an application to @@ -519,7 +518,7 @@ 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. -## A Vocabulary for the Contents of String-Encoded Data +## A Vocabulary for the Contents of String-Encoded Data {#content-vocabulary} ### Foreword Annotations defined in this section indicate that an instance contains non-JSON diff --git a/package.json b/package.json index fcf5d44f..d54300d9 100644 --- a/package.json +++ b/package.json @@ -11,12 +11,14 @@ }, "license": "MIT", "dependencies": { + "@vcarl/remark-headings": "^0.1.0", "rehype-autolink-headings": "^6.1.1", "rehype-slug": "^5.1.0", "rehype-stringify": "^9.0.3", "remark": "^14.0.3", "remark-flexible-containers": "^1.0.6", "remark-gfm": "^3.0.1", + "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", From 563526da78bd42bdfbdef1ba3182861d4f2b7984 Mon Sep 17 00:00:00 2001 From: Jason Desrosiers Date: Sun, 30 Jul 2023 19:55:06 -0700 Subject: [PATCH 04/11] Add eslint --- .eslintrc | 34 ++++++++++++++++++++++++++++++++++ .gitignore | 2 ++ package.json | 6 +++++- 3 files changed, 41 insertions(+), 1 deletion(-) create mode 100644 .eslintrc diff --git a/.eslintrc b/.eslintrc new file mode 100644 index 00000000..5b6c9f31 --- /dev/null +++ b/.eslintrc @@ -0,0 +1,34 @@ +{ + "root": true, + "env": { + "es6": true, + "node": true + }, + "parserOptions": { + "ecmaVersion": 2020, + "sourceType": "module" + }, + "extends": [ + "eslint:recommended", + "plugin:import/recommended" + ], + "plugins": ["import"], + "rules": { + "array-bracket-spacing": "error", + "arrow-parens": "error", + "comma-dangle": "error", + "dot-location": ["error", "property"], + "eol-last": "error", + "generator-star-spacing": ["error", { "before": false, "after": true }], + "indent": ["error", 2, { "ignoreComments": true, "SwitchCase": 1 }], + "linebreak-style": "error", + "no-trailing-spaces": "error", + "no-unused-vars": ["error", { "argsIgnorePattern": "_.*" }], + "prefer-const": ["error", { "destructuring": "all" }], + "semi": "error", + "quotes": ["error", "double", { "allowTemplateLiterals": true }] + }, + "settings": { + "import/resolver": "node" + } +} diff --git a/.gitignore b/.gitignore index dc05e9da..2a6a4349 100644 --- a/.gitignore +++ b/.gitignore @@ -10,3 +10,5 @@ relative-json-pointer.txt package-lock.json node_modules/ + +.env diff --git a/package.json b/package.json index d54300d9..36b667b9 100644 --- a/package.json +++ b/package.json @@ -5,6 +5,7 @@ "type": "module", "main": "index.js", "scripts": { + "lint": "eslint build/", "build": "npm run build-core && npm run build-validation", "build-core": "node build/build.js < jsonschema-core.md > jsonschema-core.html", "build-validation": "node build/build.js < jsonschema-validation.md > jsonschema-validation.html" @@ -27,6 +28,9 @@ "vfile-reporter": "^8.0.0" }, "devDependencies": { - "dotenv": "^16.3.1" + "dotenv": "*", + "eslint": "*", + "eslint-import-resolver-node": "*", + "eslint-plugin-import": "*" } } From c59dd4a68ae5f18a79f29afafb316234e518159a Mon Sep 17 00:00:00 2001 From: Jason Desrosiers Date: Sun, 30 Jul 2023 19:59:22 -0700 Subject: [PATCH 05/11] Use custom toc and heading-links remark plugins --- .eslintrc => .eslintrc.json | 1 + README.md | 36 +- 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, 827 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..00646e62 100644 --- a/README.md +++ b/README.md @@ -43,19 +43,37 @@ 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": { From d16b3007857f4e1b3469380332ee9240a593e490 Mon Sep 17 00:00:00 2001 From: Jason Desrosiers Date: Tue, 1 Aug 2023 17:51:51 -0700 Subject: [PATCH 06/11] Fix some markdown bugs and style issues --- jsonschema-core.md | 115 ++++++++++++++++++--------------------- jsonschema-validation.md | 82 +++++++++++++++------------- 2 files changed, 97 insertions(+), 100 deletions(-) diff --git a/jsonschema-core.md b/jsonschema-core.md index 58898e59..23eda176 100644 --- a/jsonschema-core.md +++ b/jsonschema-core.md @@ -122,19 +122,14 @@ interpreted according to this data model is called an "instance". An instance has one of six primitive types, and a range of possible values depending on the type: -null: A JSON "null" value - -boolean: A "true" or "false" value, from the JSON "true" or "false" value - -object: An unordered set of properties mapping a string to an instance, from the -JSON "object" value - -array: An ordered list of instances, from the JSON "array" value - -number: An arbitrary-precision, base-10 decimal number value, from the JSON -"number" value - -string: A string of Unicode code points, from the JSON "string" value +- *null*: A JSON "null" value +- boolean: A "true" or "false" value, from the JSON "true" or "false" value +- *object*: An unordered set of properties mapping a string to an instance, from + the JSON "object" value +- *array*: An ordered list of instances, from the JSON "array" value +- *number*: An arbitrary-precision, base-10 decimal number value, from the JSON + "number" value +- *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 @@ -201,18 +196,14 @@ A JSON Schema MUST be an object or a boolean. 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 - -assertions: produce a boolean result when applied to an instance - -annotations: attach information to an instance for application use - -applicators: apply one or more subschemas to a particular location in the -instance, and combine or modify their results - -reserved locations: do not directly affect results, but reserve a place for a -specific purpose to ensure interoperability +- *identifiers*: control schema identification through setting a IRI for the + schema and/or changing how the base IRI is determined +- *assertions*: produce a boolean result when applied to an instance +- *annotations*: attach information to an instance for application use +- *applicators*: apply one or more subschemas to a particular location in the + instance, and combine or modify their results +- *reserved locations*: do not directly affect results, but reserve a place for + a specific purpose to ensure interoperability Keywords may fall into multiple categories, although applicators SHOULD only produce assertion results based on their subschemas' results. They should not @@ -241,9 +232,8 @@ 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 `{}` - -`false`: Always fails validation, as if the schema `{ "not": {} }` +- `true`: Always passes validation, as if the empty schema `{}` +- `false`: Always fails validation, as if the schema `{ "not": {} }` While the empty schema object is unambiguous, there are many possible equivalents to the `false` schema. Using the boolean values ensures that the @@ -890,7 +880,7 @@ 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 $schema Keyword {#keyword-schema} +#### The `$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 @@ -917,7 +907,7 @@ the following options: Values for this property are defined elsewhere in this and other documents, and by other parties. -#### The $vocabulary Keyword +#### The `$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 @@ -1048,7 +1038,7 @@ Several keywords can accept a relative [IRI-reference](#rfc3987), or a value 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 {#id-keyword} The `$id` keyword identifies a schema resource with its [canonical](#rfc6596) IRI. @@ -1128,10 +1118,11 @@ as the same IRI through the use of `$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 {#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 @@ -1143,7 +1134,7 @@ 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 $ref {#ref} +##### Direct References with `$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] @@ -1156,7 +1147,7 @@ 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 $dynamicRef {#dynamic-ref} +##### Dynamic References with `$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 @@ -1182,7 +1173,7 @@ 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 $defs {#defs} +#### Schema Re-Use With `$defs` {#defs} The `$defs` keyword reserves a location for schema authors to inline re-usable JSON Schemas into a more general schema. The keyword does not directly affect @@ -1207,7 +1198,7 @@ the positive integer constraint is a subschema in `$defs`: } ``` -### Comments With $comment +### Comments With `$comment` This keyword reserves a location for comments from schema authors to readers or maintainers of the schema. @@ -1650,7 +1641,7 @@ 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` {#allof} This keyword's value MUST be a non-empty array. Each item of the array MUST be a valid JSON Schema. @@ -1658,7 +1649,7 @@ valid JSON Schema. An instance validates successfully against this keyword if it validates successfully against all schemas defined by this keyword's value. -##### anyOf +##### `anyOf` This keyword's value MUST be a non-empty array. Each item of the array MUST be a valid JSON Schema. @@ -1668,7 +1659,7 @@ successfully against at least one schema defined by this keyword's value. Note that when annotations are being collected, all subschemas MUST be examined so that annotations are collected from each subschema that validates successfully. -##### oneOf +##### `oneOf` This keyword's value MUST be a non-empty array. Each item of the array MUST be a valid JSON Schema. @@ -1676,7 +1667,7 @@ 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` {#not} This keyword's value MUST be a valid JSON Schema. @@ -1698,7 +1689,7 @@ present. In particular, they MUST NOT be treated as if present with an empty schema, and when `if` is not present, both `then` and `else` MUST be entirely ignored. -##### if +##### `if` This keyword's value MUST be a valid JSON Schema. @@ -1716,7 +1707,7 @@ 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 +##### `then` This keyword's value MUST be a valid JSON Schema. @@ -1729,7 +1720,7 @@ validate against its subschema. Implementations MUST NOT evaluate the instance against this keyword, for either validation or annotation collection purposes, in such cases. -##### else +##### `else` This keyword's value MUST be a valid JSON Schema. @@ -1742,7 +1733,7 @@ successfully validates against its subschema. Implementations MUST NOT evaluate the instance against this keyword, for either validation or annotation collection purposes, in such cases. -##### dependentSchemas +##### `dependentSchemas` This keyword specifies subschemas that are evaluated if the instance is an object and contains a certain property. @@ -1756,7 +1747,7 @@ property. Omitting this keyword has the same behavior as an empty object. -##### propertyDependencies +##### `propertyDependencies` This keyword specifies subschemas that are evaluated if the instance is an object and contains a certain property with a certain string value. @@ -1779,7 +1770,7 @@ results. #### Keywords for Applying Subschemas to Arrays -##### prefixItems +##### `prefixItems` The value of "prefixItems` MUST be a non-empty array of valid JSON Schemas. @@ -1795,7 +1786,7 @@ 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` {#items} The value of `items` MUST be a valid JSON Schema. @@ -1825,7 +1816,7 @@ collection MUST do so. #### Keywords for Applying Subschemas to Objects -##### properties +##### `properties` The value of `properties` MUST be an object. Each value of this object MUST be a valid JSON Schema. @@ -1841,7 +1832,7 @@ the Unevaluated vocabulary. Omitting this keyword has the same assertion behavior as an empty object. -##### patternProperties +##### `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 @@ -1861,7 +1852,7 @@ behavior of `additionalProperties` (in this vocabulary) and Omitting this keyword has the same assertion behavior as an empty object. -##### additionalProperties {#additionalproperties} +##### `additionalProperties` {#additionalproperties} The value of `additionalProperties` MUST be a valid JSON Schema. @@ -1895,7 +1886,7 @@ failing schemas are dropped. See our [Decision Record](https://github.com/json-schema-org/json-schema-spec/tree/HEAD/adr/2022-04-08-cref-for-ambiguity-and-fix-later-gh-spec-issue-1172.md) for further details. -##### propertyNames +##### `propertyNames` The value of `propertyNames` MUST be a valid JSON Schema. @@ -1907,7 +1898,7 @@ Omitting this keyword has the same behavior as an empty schema. #### Other Keywords for Applying Subschemas -##### maxContains +##### `maxContains` The value of this keyword MUST be a non-negative integer. @@ -1917,7 +1908,7 @@ 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. -##### minContains +##### `minContains` The value of this keyword MUST be a non-negative integer. @@ -1931,7 +1922,7 @@ 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 +##### `contains` The value of this keyword MUST be a valid JSON Schema. @@ -2015,7 +2006,7 @@ outcomes. However, the keywords in this vocabulary are notable exceptions: from `properties`, `patternProperties`, `additionalProperties`, `contains`, and itself -### unevaluatedItems {#unevaluateditems} +### `unevaluatedItems` {#unevaluateditems} The value of `unevaluatedItems` MUST be a valid JSON Schema. @@ -2046,7 +2037,7 @@ 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` {#unevaluatedproperties} The value of `unevaluatedProperties` MUST be a valid JSON Schema. @@ -2238,7 +2229,7 @@ if they contain the same units, in any order. The JSON key for these additional results is "details". -### 12.4. Output Structure +### Output Structure The output MUST be an object containing a boolean property named "valid". When additional information about the result is required, the output MUST also @@ -2728,7 +2719,7 @@ action based on `$comment` contents. ## IANA Considerations -### application/schema+json +### `application/schema+json` The proposed MIME media type for JSON Schema is defined as follows: @@ -2748,7 +2739,7 @@ Interoperability considerations:: See Sections [6.2](#language), Fragment identifier considerations:: See {{fragments}} -### application/schema-instance+json +### `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: diff --git a/jsonschema-validation.md b/jsonschema-validation.md index 3d5ed61f..840f73e3 100644 --- a/jsonschema-validation.md +++ b/jsonschema-validation.md @@ -115,7 +115,7 @@ The current IRI for the corresponding meta-schema is: ### Validation Keywords for Any Instance Type {#general} -#### type +#### `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. @@ -125,11 +125,12 @@ String values MUST be one of the six primitive types ("null", "boolean", with a zero fractional part. If the value of "type" is a string, then an instance validates successfully if -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. +its type matches the type represented by the value of the string. -#### enum {#enum} +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} The value of this keyword MUST be an array. This array SHOULD have at least one element. Elements in the array SHOULD be unique. @@ -139,7 +140,7 @@ one of the elements in this keyword's array value. Elements in the array might be of any type, including null. -#### const +#### `const` The value of this keyword MAY be of any type, including null. @@ -151,14 +152,14 @@ the value of the keyword. ### Validation Keywords for Numeric Instances (number and integer) {#numeric} -#### multipleOf +#### `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 +#### `maximum` The value of `maximum` MUST be a number, representing an inclusive upper limit for a numeric instance. @@ -166,7 +167,7 @@ for a numeric instance. If the instance is a number, then this keyword validates only if the instance is less than or exactly equal to `maximum`. -#### exclusiveMaximum +#### `exclusiveMaximum` The value of `exclusiveMaximum` MUST be a number, representing an exclusive upper limit for a numeric instance. @@ -174,7 +175,7 @@ upper limit for a numeric instance. 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 +#### `minimum` The value of `minimum` MUST be a number, representing an inclusive lower limit for a numeric instance. @@ -182,7 +183,7 @@ for a numeric instance. If the instance is a number, then this keyword validates only if the instance is greater than or exactly equal to `minimum`. -#### exclusiveMinimum +#### `exclusiveMinimum` The value of `exclusiveMinimum` MUST be a number, representing an exclusive lower limit for a numeric instance. @@ -192,7 +193,7 @@ strictly greater than (not equal to) `exclusiveMinimum`. ### Validation Keywords for Strings {#string} -#### maxLength +#### `maxLength` The value of this keyword MUST be a non-negative integer. @@ -202,7 +203,7 @@ equal to, the value of this keyword. The length of a string instance is defined as the number of its characters as defined by [RFC 8259](#rfc8259). -#### minLength +#### `minLength` The value of this keyword MUST be a non-negative integer. @@ -214,7 +215,7 @@ defined by [RFC 8259](#rfc8259). Omitting this keyword has the same behavior as a value of 0. -#### pattern {#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. @@ -224,14 +225,14 @@ instance successfully. Recall: regular expressions are not implicitly anchored. ### Validation Keywords for Arrays -#### maxItems +#### `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 +#### `minItems` The value of this keyword MUST be a non-negative integer. @@ -240,7 +241,7 @@ equal to, the value of this keyword. Omitting this keyword has the same behavior as a value of 0. -#### uniqueItems +#### `uniqueItems` The value of this keyword MUST be a boolean. @@ -252,14 +253,14 @@ Omitting this keyword has the same behavior as a value of false. ### Validation Keywords for Objects -#### maxProperties +#### `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 +#### `minProperties` The value of this keyword MUST be a non-negative integer. @@ -268,7 +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 +#### `required` The value of this keyword MUST be an array. Elements of this array, if any, MUST be strings, and MUST be unique. @@ -278,7 +279,7 @@ the name of a property in the instance. Omitting this keyword has the same behavior as an empty array. -#### dependentRequired +#### `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 @@ -294,7 +295,7 @@ 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} +## Vocabularies for Semantic Content With `format` {#format} ### Foreword @@ -341,10 +342,11 @@ its requirements are a superset of the Format-Annotation vocabulary. 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 @@ -378,13 +380,16 @@ defined by this specificaion. Implementations that cannot provide full 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; - 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 + 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, @@ -465,9 +470,10 @@ likely either be promoted to fully specified attributes or dropped. These attributes apply to string instances. A string instance is valid against these attributes if it is a valid Internet -email address as follows: - *email:* As defined by the "Mailbox" ABNF rule in -[RFC 5321, section 4.1.2](#rfc5321). +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. @@ -586,7 +592,7 @@ annotations to invoke the appropriate libraries separately. All keywords in this section apply only to strings, and have no effect on other data types. -### contentEncoding +### `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 @@ -612,7 +618,7 @@ needed in order to represent the content in a UTF-8 string. The value of this property MUST be a string. -### contentMediaType +### `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 @@ -621,7 +627,7 @@ the decoded string. The value of this property MUST be a string, which MUST be a media type, as defined by [RFC 2046](#rfc2046). -### contentSchema +### `contentSchema` If the instance is a string, and if `contentMediaType` is present, this property contains a schema which describes the structure of the string. @@ -719,7 +725,7 @@ The current IRI for this vocabulary, known as the Meta-Data vocabulary, is: The current IRI for the corresponding meta-schema is: `https://json-schema.org/draft/next/meta/meta-data`. -### title and description +### `title` and `description` The value of both of these keywords MUST be a string. @@ -728,7 +734,7 @@ about the data produced by this user interface. A title will preferably be short, whereas a description will provide explanation about the purpose of the instance described by this schema. -### default +### `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, @@ -738,7 +744,7 @@ This keyword can be used to supply a default JSON value associated with a particular schema. It is RECOMMENDED that a default value be valid against the associated schema. -### deprecated +### `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 @@ -758,7 +764,7 @@ containing array or object is not. Omitting this keyword has the same behavior as a value of false. -### readOnly and writeOnly +### `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 @@ -793,7 +799,7 @@ they are typed for write-only fields. Omitting these keywords has the same behavior as values of false. -### examples +### `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 From a5e139ac32536baf16f8df10d4aaa38f15f7808f Mon Sep 17 00:00:00 2001 From: Jason Desrosiers Date: Wed, 2 Aug 2023 17:46:27 -0700 Subject: [PATCH 07/11] Fix bugs --- jsonschema-core.md | 7 +++---- jsonschema-validation.md | 4 ++-- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/jsonschema-core.md b/jsonschema-core.md index 23eda176..d3ad7d56 100644 --- a/jsonschema-core.md +++ b/jsonschema-core.md @@ -2089,10 +2089,9 @@ other means. This specification defines three output formats. See the "Output Structure" section for the requirements of each format. -Flag: A boolean which simply indicates the overall validation result with no -further details. - -List: Provides validation information in a flat list structure. +- *Flag*: A boolean which simply indicates the overall validation result with no + further details. +- *List*: Provides validation information in a flat list structure. Hierarchical: Provides validation information in a hierarchical structure that follows the evaluation paths generated while processing the schema. diff --git a/jsonschema-validation.md b/jsonschema-validation.md index 840f73e3..2804b26b 100644 --- a/jsonschema-validation.md +++ b/jsonschema-validation.md @@ -124,10 +124,10 @@ String values MUST be one of the six primitive types ("null", "boolean", "object", "array", "number", or "string"), or "integer" which matches any number with a zero fractional part. -If the value of "type" is a string, then an instance validates successfully if +If the value of `type` is a string, then an instance validates successfully if 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 +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} From 3f815abf3f30096470dc5c5d4eaf7880516e3f6d Mon Sep 17 00:00:00 2001 From: Jason Desrosiers Date: Wed, 2 Aug 2023 22:09:49 -0700 Subject: [PATCH 08/11] Add code-titles plugin --- README.md | 14 +++++++- build/build.js | 43 ++++++++++++++++++++---- build/remark-code-titles.js | 65 +++++++++++++++++++++++++++++++++++++ jsonschema-core.md | 59 ++++++++++++++------------------- jsonschema-validation.md | 6 ++-- 5 files changed, 143 insertions(+), 44 deletions(-) create mode 100644 build/remark-code-titles.js diff --git a/README.md b/README.md index 00646e62..44e55482 100644 --- a/README.md +++ b/README.md @@ -69,11 +69,23 @@ features they make available to you. - [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-code-titles](/json-schema-org/json-schema-spec/blob/main/remark-code-titles.js) + -- Add titles to code blocks + - Example: + ```markdown + \`\`\`jsonschema "My Fun Title" + { "type": "string" } + \`\`\` + ``` + - The languages `jsonschema` and `json` have special styling + - The title will be parsed as a JSON string, but you have to double escape + escaped characters. So, to get `My "quoted" title`, you would need to be + `"My \\\\"quoted\\\\" title"`. - [remark-torchlight](https://github.com/torchlight-api/remark-torchlight) -- Syntax highlighting and more using https://torchlight.dev. Features include line numbers and line highlighting. - [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 6fce20ab..e8b3f0ef 100644 --- a/build/build.js +++ b/build/build.js @@ -2,6 +2,7 @@ import dotenv from "dotenv"; import { readFileSync, writeFileSync } from "node:fs"; import { reporter } from "vfile-reporter"; import { remark } from "remark"; +import remarkCodeTitles from "./remark-code-titles.js"; import remarkFlexibleContainers from "remark-flexible-containers"; import remarkGfm from "remark-gfm"; import remarkHeadingId from "remark-heading-id"; @@ -29,6 +30,7 @@ dotenv.config(); }) .use(remarkReferenceLinks) .use(remarkFlexibleContainers) + .use(remarkCodeTitles) .use(remarkTorchLight) .use(remarkTableOfContents, { startDepth: 2, @@ -43,7 +45,6 @@ dotenv.config(); -