From d769b1949fe921da9f1daad96013a8f1ce62b91b Mon Sep 17 00:00:00 2001 From: Charles Tapley Hoyt Date: Fri, 18 Oct 2024 08:08:31 +0200 Subject: [PATCH] Update JSON schema generation Closes #1209 --- src/bioregistry/schema/schema.json | 2380 +++++++++++++++++++--------- src/bioregistry/schema/struct.py | 27 +- tests/test_data.py | 4 +- 3 files changed, 1628 insertions(+), 783 deletions(-) diff --git a/src/bioregistry/schema/schema.json b/src/bioregistry/schema/schema.json index 3969f4217..c44c60130 100644 --- a/src/bioregistry/schema/schema.json +++ b/src/bioregistry/schema/schema.json @@ -1,89 +1,172 @@ { "$schema": "http://json-schema.org/draft-07/schema#", "$id": "https://bioregistry.io/schema.json", - "title": "Bioregistry JSON Schema", - "description": "The Bioregistry JSON Schema describes the shapes of the objects in the registry, metaregistry, collections, and their other related resources", - "definitions": { + "$defs": { + "Attributable": { + "description": "An upper-level metadata for a researcher.", + "properties": { + "name": { + "description": "The full name of the researcher", + "title": "Name", + "type": "string" + }, + "orcid": { + "anyOf": [ + { + "pattern": "^\\d{4}-\\d{4}-\\d{4}-\\d{3}(\\d|X)$", + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The Open Researcher and Contributor Identifier (ORCiD) provides researchers with an open, unambiguous identifier for connecting various digital assets (e.g., publications, reviews) across the semantic web. An account can be made in seconds at https://orcid.org.", + "title": "Open Researcher and Contributor Identifier" + }, + "email": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The email address specific to the researcher.", + "title": "Email address" + }, + "github": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The GitHub handle enables contacting the researcher on GitHub: the *de facto* version control in the computer sciences and life sciences.", + "title": "GitHub handle" + } + }, + "required": [ + "name" + ], + "title": "Attributable", + "type": "object" + }, "Author": { - "title": "Author", "description": "Metadata for an author.", - "type": "object", "properties": { "name": { - "title": "Name", "description": "The full name of the researcher", + "title": "Name", "type": "string" }, "orcid": { - "title": "Open Researcher and Contributor Identifier", "description": "The Open Researcher and Contributor Identifier (ORCiD) provides researchers with an open, unambiguous identifier for connecting various digital assets (e.g., publications, reviews) across the semantic web. An account can be made in seconds at https://orcid.org.", "pattern": "^\\d{4}-\\d{4}-\\d{4}-\\d{3}(\\d|X)$", + "title": "Open Researcher and Contributor Identifier", "type": "string" }, "email": { - "title": "Email address", + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, "description": "The email address specific to the researcher.", - "type": "string" + "title": "Email address" }, "github": { - "title": "GitHub handle", + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, "description": "The GitHub handle enables contacting the researcher on GitHub: the *de facto* version control in the computer sciences and life sciences.", - "type": "string" + "title": "GitHub handle" } }, "required": [ "name", "orcid" - ] + ], + "title": "Author", + "type": "object" }, "Collection": { - "title": "Collection", "description": "A collection of resources.", - "type": "object", "properties": { "identifier": { - "title": "Identifier", "description": "The collection's identifier", + "title": "Identifier", "type": "string" }, "name": { - "title": "Name", "description": "The name of the collection", + "title": "Name", "type": "string" }, "description": { - "title": "Description", "description": "A description of the collection", + "title": "Description", "type": "string" }, "resources": { - "title": "Resources", "description": "A list of prefixes of resources appearing in the collection", - "type": "array", "items": { "type": "string" - } + }, + "title": "Resources", + "type": "array" }, "authors": { - "title": "Authors", "description": "A list of authors/contributors to the collection", - "type": "array", "items": { - "$ref": "#/definitions/Author" - } + "$ref": "#/$defs/Author" + }, + "title": "Authors", + "type": "array" }, "context": { - "title": "Context", + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, "description": "The JSON-LD context's name", - "type": "string" + "title": "Context" }, "references": { - "title": "References", + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, "description": "URL references", - "type": "array", - "items": { - "type": "string" - } + "title": "References" } }, "required": [ @@ -92,561 +175,666 @@ "description", "resources", "authors" - ] + ], + "title": "Collection", + "type": "object" }, - "Provider": { - "title": "Provider", - "description": "A provider.", - "type": "object", + "Context": { + "description": "A prescriptive context contains configuration for generating fit-for-purpose\nprefix maps to serve various communities based on the standard Bioregistry\nprefix map, custom prefix remapping rules, custom URI prefix remapping rules,\ncustom prefix maps, and other community-specific logic.", "properties": { - "code": { - "title": "Code", - "description": "A locally unique code within the prefix for the provider", - "type": "string" - }, "name": { + "description": "The name of the context", "title": "Name", - "description": "Name of the provider", "type": "string" }, "description": { + "description": "A description of the context, can include Markdown", "title": "Description", - "description": "Description of the provider", "type": "string" }, - "homepage": { - "title": "Homepage", - "description": "Homepage of the provider", - "type": "string" + "maintainers": { + "description": "A list of maintainers for the context", + "items": { + "$ref": "#/$defs/Author" + }, + "title": "Maintainers", + "type": "array" }, - "uri_format": { - "title": "URI Format", - "description": "The URI format string, which must have at least one ``$1`` in it. Note that this field is generic enough to accept IRIs. See the URI specification (https://www.rfc-editor.org/rfc/rfc3986) and IRI specification (https://www.ietf.org/rfc/rfc3987.txt) for more information.", - "type": "string" + "prefix_priority": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "description": "This ordering of metaprefixes (i.e., prefixes for registries) is used to determine the priority of which registry's prefixes are used. By default, the canonical Bioregistry prefixes are highest priority. Add in \"preferred\" for explicitly using preferred prefixes or \"default\" for explicitly using Bioregistry canonical prefixes.", + "title": "Prefix Priority" }, - "first_party": { - "title": "First Party", - "description": "Annotates whether a provider is from the first-party organization", + "include_synonyms": { + "default": false, + "description": "Should synonyms be included in the prefix map?", + "title": "Include Synonyms", "type": "boolean" - } - }, - "required": [ - "code", - "name", - "description", - "homepage", - "uri_format" - ] - }, - "Attributable": { - "title": "Attributable", - "description": "An upper-level metadata for a researcher.", - "type": "object", - "properties": { - "name": { - "title": "Name", - "description": "The full name of the researcher", - "type": "string" }, - "orcid": { - "title": "Open Researcher and Contributor Identifier", - "description": "The Open Researcher and Contributor Identifier (ORCiD) provides researchers with an open, unambiguous identifier for connecting various digital assets (e.g., publications, reviews) across the semantic web. An account can be made in seconds at https://orcid.org.", - "pattern": "^\\d{4}-\\d{4}-\\d{4}-\\d{3}(\\d|X)$", - "type": "string" + "uri_prefix_priority": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "description": "This ordering of metaprefixes (i.e., prefixes for registries) is used to determine the priority of which registry's URI prefixes are used. By default, the canonical Bioregistry URI prefixes are highest priority.", + "title": "Uri Prefix Priority" }, - "email": { - "title": "Email address", - "description": "The email address specific to the researcher.", - "type": "string" + "prefix_remapping": { + "anyOf": [ + { + "additionalProperties": { + "type": "string" + }, + "type": "object" + }, + { + "type": "null" + } + ], + "description": "This is a mapping from canonical Bioregistry prefixes to custom prefixes used in this context.", + "title": "Prefix Remapping" }, - "github": { - "title": "GitHub handle", - "description": "The GitHub handle enables contacting the researcher on GitHub: the *de facto* version control in the computer sciences and life sciences.", - "type": "string" + "custom_prefix_map": { + "anyOf": [ + { + "additionalProperties": { + "type": "string" + }, + "type": "object" + }, + { + "type": "null" + } + ], + "description": "This is a custom prefix map (which contains custom URL/URI expansions) that is added after all other logic is applied. Keys must either be canonical Bioregistry prefixes, prefixes used based on the given prefix priority, or values in the given prefix remapping.", + "title": "Custom Prefix Map" + }, + "blacklist": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "description": "This is a list of canonical Bioregistry prefixes that should not be included in the context.", + "title": "Blacklist" } }, "required": [ - "name" - ] + "name", + "description", + "maintainers", + "prefix_priority", + "uri_prefix_priority", + "prefix_remapping", + "custom_prefix_map", + "blacklist" + ], + "title": "Context", + "type": "object" }, "Organization": { - "title": "Organization", "description": "Model for organizataions.", - "type": "object", "properties": { "ror": { - "title": "Research Organization Registry identifier", + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, "description": "ROR identifier for a record about the organization", - "type": "string" + "title": "Research Organization Registry identifier" }, "wikidata": { - "title": "Wikidata identifier", + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, "description": "Wikidata identifier for a record about the organization", - "type": "string" + "title": "Wikidata identifier" }, "name": { - "title": "Name", "description": "Name of the organization", + "title": "Name", "type": "string" }, "partnered": { - "title": "Partnered", - "description": "Has this organization made a specific connection with Bioregistry?", "default": false, + "description": "Has this organization made a specific connection with Bioregistry?", + "title": "Partnered", "type": "boolean" } }, "required": [ "name" - ] - }, - "Publication": { - "title": "Publication", - "description": "Metadata about a publication.", - "type": "object", - "properties": { - "pubmed": { - "title": "PubMed", - "description": "The PubMed identifier for the article", - "type": "string" - }, - "doi": { - "title": "DOI", - "description": "The DOI for the article. DOIs are case insensitive, so these are required by the Bioregistry to be standardized to their lowercase form.", - "type": "string" - }, - "pmc": { - "title": "PMC", - "description": "The PubMed Central identifier for the article", - "type": "string" - }, - "title": { - "title": "Title", - "description": "The title of the article", - "type": "string" - }, - "year": { - "title": "Year", - "description": "The year the article was published", - "type": "integer" - } - } + ], + "title": "Organization", + "type": "object" }, - "Resource": { - "title": "Resource", - "description": "Metadata about an ontology, database, or other resource.", - "type": "object", + "Provider": { + "description": "A provider.", "properties": { - "prefix": { - "title": "Prefix", - "description": "The prefix for this resource", + "code": { + "description": "A locally unique code within the prefix for the provider", + "title": "Code", "type": "string" }, "name": { + "description": "Name of the provider", "title": "Name", - "description": "The name of the resource", "type": "string" }, "description": { + "description": "Description of the provider", "title": "Description", - "description": "A description of the resource", "type": "string" }, - "pattern": { - "title": "Pattern", - "description": "The regular expression pattern for local unique identifiers in the resource", + "homepage": { + "description": "Homepage of the provider", + "title": "Homepage", "type": "string" }, "uri_format": { - "title": "URI format string", "description": "The URI format string, which must have at least one ``$1`` in it. Note that this field is generic enough to accept IRIs. See the URI specification (https://www.rfc-editor.org/rfc/rfc3986) and IRI specification (https://www.ietf.org/rfc/rfc3987.txt) for more information.", + "title": "URI Format", "type": "string" }, - "uri_format_resolvable": { - "title": "URI format string resolvable", - "description": "If false, denotes if the URI format string is known to be not resolvable", - "type": "boolean" - }, - "rdf_uri_format": { - "title": "RDF URI format string", - "description": "The RDF URI format string, which must have at least one ``$1`` in it. Note that this field is generic enough to accept IRIs. See the URI specification (https://www.rfc-editor.org/rfc/rfc3986) and IRI specification (https://www.ietf.org/rfc/rfc3987.txt) for more information.", - "type": "string" - }, - "providers": { - "title": "Providers", - "description": "Additional, non-default providers for the resource", - "type": "array", - "items": { - "$ref": "#/definitions/Provider" - } - }, - "homepage": { - "title": "Homepage", - "description": "The URL for the homepage of the resource, preferably using HTTPS", - "type": "string" - }, - "repository": { - "title": "Repository", - "description": "The URL for the repository of the resource", - "type": "string" - }, - "contact": { - "title": "Contact", - "description": "The contact email address for the resource. This must correspond to a specific person and not be a listserve nor a shared email account.", - "allOf": [ + "first_party": { + "anyOf": [ { - "$ref": "#/definitions/Attributable" + "type": "boolean" + }, + { + "type": "null" } - ] - }, - "owners": { - "title": "Owners", - "description": "The owner of the corresponding identifier space. See also https://github.com/biopragmatics/bioregistry/issues/755.", - "type": "array", - "items": { - "$ref": "#/definitions/Organization" - } - }, - "example": { - "title": "Example", - "description": "An example local identifier for the resource, explicitly excluding any redundant usage of the prefix in the identifier. For example, a GO identifier should only look like ``1234567`` and not like ``GO:1234567``", - "type": "string" - }, - "example_extras": { - "title": "Example Extras", - "description": "Extra example identifiers", - "type": "array", - "items": { - "type": "string" - } - }, - "example_decoys": { - "title": "Example Decoys", - "description": "Extra example identifiers that explicitly fail regex tests", - "type": "array", - "items": { - "type": "string" - } - }, - "license": { - "title": "License", - "description": "The license for the resource", - "type": "string" - }, - "version": { - "title": "Version", - "description": "The version for the resource", - "type": "string" + ], + "default": null, + "description": "Annotates whether a provider is from the first-party organization", + "title": "First Party" + } + }, + "required": [ + "code", + "name", + "description", + "homepage", + "uri_format" + ], + "title": "Provider", + "type": "object" + }, + "Publication": { + "description": "Metadata about a publication.", + "properties": { + "pubmed": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The PubMed identifier for the article", + "title": "PubMed" }, - "part_of": { - "title": "Part Of", - "description": "An annotation between this prefix and a super-prefix. For example, ``chembl.compound`` is a part of ``chembl``.", - "type": "string" + "doi": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The DOI for the article. DOIs are case insensitive, so these are required by the Bioregistry to be standardized to their lowercase form.", + "title": "DOI" }, - "provides": { - "title": "Provides", - "description": "An annotation between this prefix and a prefix for which it is redundant. For example, ``ctd.gene`` has been given a prefix by Identifiers.org, but it actually just reuses identifies from ``ncbigene``, so ``ctd.gene`` provides ``ncbigene``.", - "type": "string" + "pmc": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The PubMed Central identifier for the article", + "title": "PMC" }, - "download_owl": { - "title": "OWL Download URL", - "description": "The URL to download the resource as an ontology encoded in the OWL format. More information about this format can be found at https://www.w3.org/TR/owl2-syntax/.", - "type": "string" + "title": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The title of the article", + "title": "Title" }, - "download_obo": { - "title": "OBO Download URL", - "description": "The URL to download the resource as an ontology encoded in the OBO format. More information about this format can be found at https://owlcollab.github.io/oboformat/doc/obo-syntax.html.", + "year": { + "anyOf": [ + { + "type": "integer" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The year the article was published", + "title": "Year" + } + }, + "title": "Publication", + "type": "object" + }, + "Registry": { + "description": "Metadata about a registry.", + "properties": { + "prefix": { + "description": "The metaprefix for the registry itself. For example, the metaprefix for Identifiers.org is `miriam`.", + "title": "Prefix", "type": "string" }, - "download_json": { - "title": "OBO Graph JSON Download URL", - "description": "The URL to download the resource as an ontology encoded in the OBO Graph JSON format. More information about this format can be found at https://github.com/geneontology/obographs.", + "name": { + "description": "The human-readable label for the registry", + "title": "Name", "type": "string" }, - "download_rdf": { - "title": "RDF Download URL", - "description": "The URL to download the resource as an RDF file, in one of many formats.", + "description": { + "description": "A full description of the registry.", + "title": "Description", "type": "string" }, - "banana": { - "title": "Banana", - "description": "The `banana` is a generalization of the concept of the \"namespace embedded in local unique identifier\". Many OBO foundry ontologies use the redundant uppercased name of the ontology in the local identifier, such as the Gene Ontology, which makes the prefixes have a redundant usage as in ``GO:GO:1234567``. The `banana` tag explicitly annotates the part in the local identifier that should be stripped, if found. While the Bioregistry automatically knows how to handle all OBO Foundry ontologies' bananas because the OBO Foundry provides the \"preferredPrefix\" field, the banana can be annotated on non-OBO ontologies to more explicitly write the beginning part of the identifier that should be stripped. This allowed for solving one of the long-standing issues with the Identifiers.org resolver (e.g., for ``oma.hog``; see https://github.com/identifiers-org/identifiers-org.github.io/issues/155) as well as better annotate new entries, such as SwissMap Lipids, which have the prefix ``swisslipid`` but have the redundant information ``SLM:`` in the beginning of identifiers. Therefore, ``SLM:`` is the banana.", + "homepage": { + "description": "The URL for the homepage of the registry.", + "title": "Homepage", "type": "string" }, - "banana_peel": { - "title": "Banana Peel", - "description": "Delimiter used in banana", + "example": { + "description": "An example prefix inside the registry.", + "title": "Example", "type": "string" }, - "deprecated": { - "title": "Deprecated", - "description": "A flag denoting if this resource is deprecated. Currently, this is a blanket term that covers cases when the prefix is no longer maintained, when it has been rolled into another resource, when the website related to the resource goes down, or any other reason that it's difficult or impossible to find full metadata on the resource. If this is set to true, please add a comment explaining why. This flag will override annotations from the OLS, OBO Foundry, and others on the deprecation status, since they often disagree and are very conservative in calling dead resources.", - "type": "boolean" - }, - "mappings": { - "title": "Mappings", - "description": "A dictionary of metaprefixes (i.e., prefixes for registries) to prefixes in external registries. These also correspond to the registry-specific JSON fields in this model like ``miriam`` field.", - "type": "object", - "additionalProperties": { - "type": "string" - } - }, - "synonyms": { - "title": "Synonyms", - "description": "A list of synonyms for the prefix of this resource. These are used in normalization of prefixes and are a useful reference tool for prefixes that are written many ways. For example, ``snomedct`` has many synonyms including typos like ``SNOWMEDCT``, lexical variants like ``SNOMED_CT``, version-variants like ``SNOMEDCT_2010_1_31``, and tons of other nonsense like ``SNOMEDCTCT``.", - "type": "array", - "items": { - "type": "string" - } - }, - "keywords": { - "title": "Keywords", - "description": "A list of keywords for the resource", - "type": "array", - "items": { - "type": "string" - } - }, - "references": { - "title": "References", - "description": "A list of URLs to also see, such as publications describing the resource", - "type": "array", - "items": { - "type": "string" - } + "bibtex": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Citation key used in BibTex for this registry.", + "title": "Bibtex" }, - "publications": { - "title": "Publications", - "description": "A list of URLs to also see, such as publications describing the resource", - "type": "array", - "items": { - "$ref": "#/definitions/Publication" - } + "availability": { + "allOf": [ + { + "$ref": "#/$defs/RegistrySchema" + } + ], + "description": "A structured description of the metadata that the registry collects" }, - "appears_in": { - "title": "Appears In", - "description": "A list of prefixes that use this resource for xrefs, provenance, etc.", - "type": "array", - "items": { - "type": "string" - } + "qualities": { + "allOf": [ + { + "$ref": "#/$defs/RegistryQualities" + } + ], + "description": "A structured description of the registry's qualities" }, - "depends_on": { - "title": "Depends On", - "description": "A list of prefixes that use this resource depends on, e.g., ontologies that import each other.", - "type": "array", - "items": { - "type": "string" - } + "governance": { + "allOf": [ + { + "$ref": "#/$defs/RegistryGovernance" + } + ], + "description": "A structured description of the governance for the registry" }, - "namespace_in_lui": { - "title": "Namespace Embedded in Local Unique Identifier", - "description": "A flag denoting if the namespace is embedded in the LUI (if this is true and it is not accompanied by a banana, assume that the banana is the prefix in all caps plus a colon, as is standard in OBO). Currently this flag is only used to override identifiers.org in the case of ``gramene.growthstage``, ``oma.hog``, and ``vario``.", - "type": "boolean" + "download": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A download link for the data contained in the registry", + "title": "Download" }, - "no_own_terms": { - "title": "No Own Terms", - "description": "A flag denoting if the resource mints its own identifiers. Omission or explicit marking as false means that the resource does have its own terms. This is most applicable to ontologies, specifically application ontologies, which only reuse terms from others. One example is ChIRO.", - "type": "boolean" + "provider_uri_format": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A URL with a $1 for a prefix to resolve in the registry", + "title": "Provider Uri Format" }, - "comment": { - "title": "Comment", - "description": "A field for a free text comment", - "type": "string" + "search_uri_format": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A URL with a $1 for a prefix or string for searching for prefixes", + "title": "Search Uri Format" }, - "contributor": { - "title": "Contributor", - "description": "The contributor of the prefix to the Bioregistry, including at a minimum their name and ORCiD and optional their email address and GitHub handle. All entries curated through the Bioregistry GitHub Workflow must contain this field.", - "allOf": [ + "resolver_uri_format": { + "anyOf": [ + { + "type": "string" + }, { - "$ref": "#/definitions/Author" + "type": "null" } - ] + ], + "default": null, + "description": "A URL with a $1 for a prefix and $2 for an identifier to resolve in the registry", + "title": "Resolver Uri Format" }, - "contributor_extras": { - "title": "Contributor Extras", - "description": "Additional contributors besides the original submitter.", - "type": "array", - "items": { - "$ref": "#/definitions/Author" - } + "resolver_type": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "An optional type annotation for what kind of resolver it is (i.e., redirect or lookup)", + "title": "Resolver Type" }, - "reviewer": { - "title": "Reviewer", - "description": "The reviewer of the prefix to the Bioregistry, including at a minimum their name and ORCiD and optional their email address and GitHub handle. All entries curated through the Bioregistry GitHub Workflow should contain this field pointing to the person who reviewed it on GitHub.", + "contact": { "allOf": [ { - "$ref": "#/definitions/Author" + "$ref": "#/$defs/Attributable" } - ] - }, - "proprietary": { - "title": "Proprietary", - "description": "A flag to denote if this database is proprietary and therefore can not be included in normal quality control checks nor can it be resolved. Omission or explicit marking as false means that the resource is not proprietary.", - "type": "boolean" + ], + "description": "The contact for the registry." }, - "has_canonical": { - "title": "Has Canonical", - "description": "If this shares an IRI with another entry, maps to which should be be considered as canonical", - "type": "string" + "bioregistry_prefix": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The prefix for this registry in the Bioregistry", + "title": "Bioregistry Prefix" }, - "preferred_prefix": { - "title": "Preferred Prefix", - "description": "An annotation of stylization of the prefix. This appears in OBO ontologies like FBbt as well as databases like NCBIGene. If it's not given, then assume that the normalized prefix used in the Bioregistry is canonical.", - "type": "string" + "logo_url": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The URL for the logo of the resource", + "title": "Logo Url" }, - "twitter": { - "title": "Twitter", - "description": "The twitter handle for the project", - "type": "string" + "license": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The license under which the resource is redistributed", + "title": "License" }, - "mastodon": { - "title": "Mastodon", - "description": "The mastodon handle for the project", - "type": "string" - }, - "github_request_issue": { - "title": "Github Request Issue", - "description": "The GitHub issue for the new prefix request", - "type": "integer" - }, - "logo": { - "title": "Logo", - "description": "The URL of the logo for the project/resource", + "short_name": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A short name for the resource, e.g., for use in charts", + "title": "Short Name" + } + }, + "required": [ + "prefix", + "name", + "description", + "homepage", + "example", + "availability", + "qualities", + "governance", + "contact" + ], + "title": "Registry", + "type": "object" + }, + "RegistryGovernance": { + "description": "Metadata about a registry's governance.", + "properties": { + "curation": { + "enum": [ + "private", + "import", + "community", + "opaque-review", + "open-review" + ], + "title": "Curation", "type": "string" }, - "miriam": { - "title": "Miriam", - "type": "object" - }, - "n2t": { - "title": "N2T", - "type": "object" - }, - "prefixcommons": { - "title": "Prefixcommons", - "type": "object" - }, - "wikidata": { - "title": "Wikidata", - "type": "object" - }, - "go": { - "title": "Go", - "type": "object" - }, - "obofoundry": { - "title": "Obofoundry", - "type": "object" - }, - "bioportal": { - "title": "Bioportal", - "type": "object" - }, - "ecoportal": { - "title": "Ecoportal", - "type": "object" - }, - "agroportal": { - "title": "Agroportal", - "type": "object" - }, - "cropoct": { - "title": "Cropoct", - "type": "object" - }, - "ols": { - "title": "Ols", - "type": "object" - }, - "aberowl": { - "title": "Aberowl", - "type": "object" - }, - "ncbi": { - "title": "Ncbi", - "type": "object" - }, - "uniprot": { - "title": "Uniprot", - "type": "object" - }, - "biolink": { - "title": "Biolink", - "type": "object" - }, - "cellosaurus": { - "title": "Cellosaurus", - "type": "object" - }, - "ontobee": { - "title": "Ontobee", - "type": "object" + "curates": { + "description": "This field denotes if the registry's maintainers and potentially contributors curate novel prefixes.", + "title": "Curates", + "type": "boolean" }, - "cheminf": { - "title": "Cheminf", - "type": "object" + "imports": { + "description": "This field denotes if the registry imports and aligns prefixes from other registries.", + "title": "Imports", + "type": "boolean" }, - "fairsharing": { - "title": "Fairsharing", - "type": "object" + "scope": { + "description": "This field denotes the scope of prefixes which the registry covers. For example, some registries are limited to ontologies, some have a full scope over the life sciences, and some are general purpose.", + "title": "Scope", + "type": "string" }, - "biocontext": { - "title": "Biocontext", - "type": "object" + "comments": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Optional additional comments about the registry's governance model", + "title": "Comments" }, - "edam": { - "title": "Edam", - "type": "object" + "accepts_external_contributions": { + "description": "This field denotes if the registry (in theory) accepts external contributions, either via suggestion or proactive improvement. This field does not pass judgement on the difficult of this process from the perspective of the submitter nor the responsiveness of the registry. This field does not consider the ability for insiders (i.e., people with private relationships to the maintainers) to affect change.", + "title": "Accepts External Contributions", + "type": "boolean" }, - "re3data": { - "title": "Re3Data", - "type": "object" + "public_version_controlled_data": { + "description": "This field denotes if the registry stores its data in publicly available version control system, such as GitHub or GitLab", + "title": "Public Version-Controlled Data", + "type": "boolean" }, - "hl7": { - "title": "Hl7", - "type": "object" + "data_repository": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "This field denotes the address of the registry's data version control repository.", + "title": "Data Repository" }, - "bartoc": { - "title": "BARTOC", - "type": "object" + "code_repository": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "This field denotes the address of the registry's code version control repository.", + "title": "Code Repository" }, - "rrid": { - "title": "RRID", - "type": "object" + "review_team": { + "description": "This field denotes if the registry's reviewers/moderators for external contributions known? If there's a well-defined, maintained listing, then it can be marked as public. If it can be inferred, e.g. from reading the commit history on a version control system, then it can be marked as inferrable. A closed review team, e.g., like for Identifiers.org can be marked as private. Resources that do not accept external contributions can be marked with N/A. An unmoderated regitry like Prefix.cc is marked with 'democratic'.", + "enum": [ + "public", + "inferrable", + "private", + "democratic", + "n/a" + ], + "title": "Review Team", + "type": "string" }, - "lov": { - "title": "LOV", - "type": "object" + "status": { + "description": "This field denotes the maitenance status of the repository. An active repository is still being maintained and also is responsive to external requests for improvement. An unresponsive repository is still being maintained in some capacity but is not responsive to external requests for improvement. An inactive repository is no longer being proactively maintained (though may receive occasional patches).", + "enum": [ + "active", + "unresponsive", + "inactive" + ], + "title": "Status", + "type": "string" }, - "zazuko": { - "title": "Zazuko", - "type": "object" + "issue_tracker": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "This field denotes the public issue tracker for issues related to the code and data of the repository.", + "title": "Issue Tracker" + } + }, + "required": [ + "curation", + "curates", + "imports", + "scope", + "accepts_external_contributions", + "public_version_controlled_data", + "review_team", + "status" + ], + "title": "RegistryGovernance", + "type": "object" + }, + "RegistryQualities": { + "description": "Qualities about a registry.", + "properties": { + "structured_data": { + "description": "This field denotes if the registry provides structured access to its data? For example, this can be through an API (e.g., FAIRsharing, OLS) or a bulk download (e.g., OBO Foundry) in a structured file format. A counter-example is a site that must be scraped to acquire its content (e.g, the NCBI GenBank).", + "title": "Structured Data", + "type": "boolean" }, - "togoid": { - "title": "Togoid", - "type": "object" + "bulk_data": { + "description": "This field denotes if the registry provides a bulk dump of its data? For example, the OBO Foundry provides its bulk data in a file and Identifiers.org provides its bulk data in an API endpoint. A counterexample is FAIRsharing, which requires slow, expensive pagination through its data. Another counterexample is HL7 which requires manually navigating a form to download its content. While GenBank is not structured, it is still bulk downloadable.", + "title": "Bulk Data", + "type": "boolean" }, - "integbio": { - "title": "Integbio", - "type": "object" + "no_authentication": { + "description": "This field denotes if the registry provides access to its data without an API key? For example, Identifiers.org. As a counter-example, BioPortal requires an API key for access to its structured data.", + "title": "No Authentication", + "type": "boolean" }, - "pathguide": { - "title": "Pathguide", - "type": "object" + "automatable_download": { + "default": true, + "description": "This field denotes if the registry makes its data available downloadable in an automated way?This includes websites that have bulk downloads, paginated API downloads, or even require scraping.A counter example is HL7, whose download can not be automated due to the need to interact with a web form.", + "title": "Automatable Download", + "type": "boolean" } }, "required": [ - "prefix" - ] + "structured_data", + "bulk_data", + "no_authentication" + ], + "title": "RegistryQualities", + "type": "object" }, "RegistrySchema": { - "title": "RegistrySchema", "description": "Metadata about a registry's schema.", - "type": "object", "properties": { "name": { - "title": "Name", "description": "This field denotes if a name is required, optional, or never captured for each record in the registry.", "enum": [ "required", @@ -655,10 +843,10 @@ "present*", "missing" ], + "title": "Name", "type": "string" }, "homepage": { - "title": "Homepage", "description": "This field denotes if a homepage is required, optional, or never captured for each record in the registry.", "enum": [ "required", @@ -667,10 +855,10 @@ "present*", "missing" ], + "title": "Homepage", "type": "string" }, "description": { - "title": "Description", "description": "This field denotes if a description is required, optional, or never captured for each record in the registry.", "enum": [ "required", @@ -679,10 +867,10 @@ "present*", "missing" ], + "title": "Description", "type": "string" }, "example": { - "title": "Example", "description": "This field denotes if an example local unique identifier is required, optional, or never captured for each record in the registry.", "enum": [ "required", @@ -691,10 +879,10 @@ "present*", "missing" ], + "title": "Example", "type": "string" }, "pattern": { - "title": "Pattern", "description": "This field denotes if a regular expression pattern for matching local unique identifiers is required, optional, or never captured for each record in the registry.", "enum": [ "required", @@ -703,10 +891,10 @@ "present*", "missing" ], + "title": "Pattern", "type": "string" }, "provider": { - "title": "Provider", "description": "This field denotes if a URI format string for converting local unique identifiers into URIs is required, optional, or never captured for each record in the registry.", "enum": [ "required", @@ -715,28 +903,28 @@ "present*", "missing" ], + "title": "Provider", "type": "string" }, "alternate_providers": { - "title": "Alternate Providers", "description": "This field denotes if additional/secondary URI format strings for converting local unique identifiers into URIs is required, optional, or never captured for each record in the registry.", "enum": [ "present", "missing" ], + "title": "Alternate Providers", "type": "string" }, "synonyms": { - "title": "Synonyms", "description": "This field denotes if alternative prefixes (e.g., taxonomy for NCBITaxon) is required, optional, or never captured for each record in the registry.", "enum": [ "present", "missing" ], + "title": "Synonyms", "type": "string" }, "license": { - "title": "License", "description": "This field denotes if capturing the data license is required, optional, or never captured for each record in the registry.", "enum": [ "required", @@ -745,10 +933,10 @@ "present*", "missing" ], + "title": "License", "type": "string" }, "version": { - "title": "Version", "description": "This field denotes if capturing the current data version is required, optional, or never captured for each record in the registry.", "enum": [ "required", @@ -757,10 +945,10 @@ "present*", "missing" ], + "title": "Version", "type": "string" }, "contact": { - "title": "Contact", "description": "This field denotes if capturing the primary responsible person's contact information (e.g., name, ORCID, email) is required, optional, or never captured for each record in the registry.", "enum": [ "required", @@ -769,11 +957,12 @@ "present*", "missing" ], + "title": "Contact", "type": "string" }, "search": { - "title": "Prefix Search", "description": "This field denotes if the registry provides either a dedicated page for searching for prefixes (e.g. AberOWL has a dedicated search page) OR a contextual search (e.g., AgroPortal has a prefix search built in its homepage).", + "title": "Prefix Search", "type": "boolean" } }, @@ -790,345 +979,1004 @@ "version", "contact", "search" - ] + ], + "title": "RegistrySchema", + "type": "object" }, - "RegistryQualities": { - "title": "RegistryQualities", - "description": "Qualities about a registry.", - "type": "object", + "Resource": { + "description": "Metadata about an ontology, database, or other resource.", "properties": { - "structured_data": { - "title": "Structured Data", - "description": "This field denotes if the registry provides structured access to its data? For example, this can be through an API (e.g., FAIRsharing, OLS) or a bulk download (e.g., OBO Foundry) in a structured file format. A counter-example is a site that must be scraped to acquire its content (e.g, the NCBI GenBank).", - "type": "boolean" + "prefix": { + "description": "The prefix for this resource", + "title": "Prefix", + "type": "string" }, - "bulk_data": { - "title": "Bulk Data", - "description": "This field denotes if the registry provides a bulk dump of its data? For example, the OBO Foundry provides its bulk data in a file and Identifiers.org provides its bulk data in an API endpoint. A counterexample is FAIRsharing, which requires slow, expensive pagination through its data. Another counterexample is HL7 which requires manually navigating a form to download its content. While GenBank is not structured, it is still bulk downloadable.", - "type": "boolean" + "name": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The name of the resource", + "title": "Name" }, - "no_authentication": { - "title": "No Authentication", - "description": "This field denotes if the registry provides access to its data without an API key? For example, Identifiers.org. As a counter-example, BioPortal requires an API key for access to its structured data.", - "type": "boolean" + "description": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A description of the resource", + "title": "Description" }, - "automatable_download": { - "title": "Automatable Download", - "description": "This field denotes if the registry makes its data available downloadable in an automated way?This includes websites that have bulk downloads, paginated API downloads, or even require scraping.A counter example is HL7, whose download can not be automated due to the need to interact with a web form.", - "default": true, - "type": "boolean" - } - }, - "required": [ - "structured_data", - "bulk_data", - "no_authentication" - ] - }, - "RegistryGovernance": { - "title": "RegistryGovernance", - "description": "Metadata about a registry's governance.", - "type": "object", - "properties": { - "curation": { - "title": "Curation", - "enum": [ - "private", - "import", - "community", - "opaque-review", - "open-review" + "pattern": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } ], - "type": "string" + "default": null, + "description": "The regular expression pattern for local unique identifiers in the resource", + "title": "Pattern" }, - "curates": { - "title": "Curates", - "description": "This field denotes if the registry's maintainers and potentially contributors curate novel prefixes.", - "type": "boolean" + "uri_format": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The URI format string, which must have at least one ``$1`` in it. Note that this field is generic enough to accept IRIs. See the URI specification (https://www.rfc-editor.org/rfc/rfc3986) and IRI specification (https://www.ietf.org/rfc/rfc3987.txt) for more information.", + "title": "URI format string" }, - "imports": { - "title": "Imports", - "description": "This field denotes if the registry imports and aligns prefixes from other registries.", - "type": "boolean" + "uri_format_resolvable": { + "anyOf": [ + { + "type": "boolean" + }, + { + "type": "null" + } + ], + "default": null, + "description": "If false, denotes if the URI format string is known to be not resolvable", + "title": "URI format string resolvable" }, - "scope": { - "title": "Scope", - "description": "This field denotes the scope of prefixes which the registry covers. For example, some registries are limited to ontologies, some have a full scope over the life sciences, and some are general purpose.", - "type": "string" + "rdf_uri_format": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The RDF URI format string, which must have at least one ``$1`` in it. Note that this field is generic enough to accept IRIs. See the URI specification (https://www.rfc-editor.org/rfc/rfc3986) and IRI specification (https://www.ietf.org/rfc/rfc3987.txt) for more information.", + "title": "RDF URI format string" }, - "comments": { - "title": "Comments", - "description": "Optional additional comments about the registry's governance model", - "type": "string" + "providers": { + "anyOf": [ + { + "items": { + "$ref": "#/$defs/Provider" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Additional, non-default providers for the resource", + "title": "Providers" }, - "accepts_external_contributions": { - "title": "Accepts External Contributions", - "description": "This field denotes if the registry (in theory) accepts external contributions, either via suggestion or proactive improvement. This field does not pass judgement on the difficult of this process from the perspective of the submitter nor the responsiveness of the registry. This field does not consider the ability for insiders (i.e., people with private relationships to the maintainers) to affect change.", - "type": "boolean" + "homepage": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The URL for the homepage of the resource, preferably using HTTPS", + "title": "Homepage" }, - "public_version_controlled_data": { - "title": "Public Version-Controlled Data", - "description": "This field denotes if the registry stores its data in publicly available version control system, such as GitHub or GitLab", - "type": "boolean" + "repository": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The URL for the repository of the resource", + "title": "Repository" }, - "data_repository": { - "title": "Data Repository", - "description": "This field denotes the address of the registry's data version control repository.", - "type": "string" + "contact": { + "anyOf": [ + { + "$ref": "#/$defs/Attributable" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The contact email address for the resource. This must correspond to a specific person and not be a listserve nor a shared email account." }, - "code_repository": { - "title": "Code Repository", - "description": "This field denotes the address of the registry's code version control repository.", - "type": "string" + "owners": { + "anyOf": [ + { + "items": { + "$ref": "#/$defs/Organization" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The owner of the corresponding identifier space. See also https://github.com/biopragmatics/bioregistry/issues/755.", + "title": "Owners" }, - "review_team": { - "title": "Review Team", - "description": "This field denotes if the registry's reviewers/moderators for external contributions known? If there's a well-defined, maintained listing, then it can be marked as public. If it can be inferred, e.g. from reading the commit history on a version control system, then it can be marked as inferrable. A closed review team, e.g., like for Identifiers.org can be marked as private. Resources that do not accept external contributions can be marked with N/A. An unmoderated regitry like Prefix.cc is marked with 'democratic'.", - "enum": [ - "public", - "inferrable", - "private", - "democratic", - "n/a" + "example": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } ], - "type": "string" + "default": null, + "description": "An example local identifier for the resource, explicitly excluding any redundant usage of the prefix in the identifier. For example, a GO identifier should only look like ``1234567`` and not like ``GO:1234567``", + "title": "Example" }, - "status": { - "title": "Status", - "description": "This field denotes the maitenance status of the repository. An active repository is still being maintained and also is responsive to external requests for improvement. An unresponsive repository is still being maintained in some capacity but is not responsive to external requests for improvement. An inactive repository is no longer being proactively maintained (though may receive occasional patches).", - "enum": [ - "active", - "unresponsive", - "inactive" + "example_extras": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } ], - "type": "string" + "default": null, + "description": "Extra example identifiers", + "title": "Example Extras" }, - "issue_tracker": { - "title": "Issue Tracker", - "description": "This field denotes the public issue tracker for issues related to the code and data of the repository.", - "type": "string" - } - }, - "required": [ - "curation", - "curates", - "imports", - "scope", - "accepts_external_contributions", - "public_version_controlled_data", - "review_team", - "status" - ] - }, - "Registry": { - "title": "Registry", - "description": "Metadata about a registry.", - "type": "object", - "properties": { - "prefix": { - "title": "Prefix", - "description": "The metaprefix for the registry itself. For example, the metaprefix for Identifiers.org is `miriam`.", - "type": "string" + "example_decoys": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Extra example identifiers that explicitly fail regex tests", + "title": "Example Decoys" + }, + "license": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The license for the resource", + "title": "License" + }, + "version": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The version for the resource", + "title": "Version" + }, + "part_of": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "An annotation between this prefix and a super-prefix. For example, ``chembl.compound`` is a part of ``chembl``.", + "title": "Part Of" + }, + "provides": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "An annotation between this prefix and a prefix for which it is redundant. For example, ``ctd.gene`` has been given a prefix by Identifiers.org, but it actually just reuses identifies from ``ncbigene``, so ``ctd.gene`` provides ``ncbigene``.", + "title": "Provides" + }, + "download_owl": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The URL to download the resource as an ontology encoded in the OWL format. More information about this format can be found at https://www.w3.org/TR/owl2-syntax/.", + "title": "OWL Download URL" + }, + "download_obo": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The URL to download the resource as an ontology encoded in the OBO format. More information about this format can be found at https://owlcollab.github.io/oboformat/doc/obo-syntax.html.", + "title": "OBO Download URL" + }, + "download_json": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The URL to download the resource as an ontology encoded in the OBO Graph JSON format. More information about this format can be found at https://github.com/geneontology/obographs.", + "title": "OBO Graph JSON Download URL" + }, + "download_rdf": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The URL to download the resource as an RDF file, in one of many formats.", + "title": "RDF Download URL" + }, + "banana": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The `banana` is a generalization of the concept of the \"namespace embedded in local unique identifier\". Many OBO foundry ontologies use the redundant uppercased name of the ontology in the local identifier, such as the Gene Ontology, which makes the prefixes have a redundant usage as in ``GO:GO:1234567``. The `banana` tag explicitly annotates the part in the local identifier that should be stripped, if found. While the Bioregistry automatically knows how to handle all OBO Foundry ontologies' bananas because the OBO Foundry provides the \"preferredPrefix\" field, the banana can be annotated on non-OBO ontologies to more explicitly write the beginning part of the identifier that should be stripped. This allowed for solving one of the long-standing issues with the Identifiers.org resolver (e.g., for ``oma.hog``; see https://github.com/identifiers-org/identifiers-org.github.io/issues/155) as well as better annotate new entries, such as SwissMap Lipids, which have the prefix ``swisslipid`` but have the redundant information ``SLM:`` in the beginning of identifiers. Therefore, ``SLM:`` is the banana.", + "title": "Banana" + }, + "banana_peel": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Delimiter used in banana", + "title": "Banana Peel" + }, + "deprecated": { + "anyOf": [ + { + "type": "boolean" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A flag denoting if this resource is deprecated. Currently, this is a blanket term that covers cases when the prefix is no longer maintained, when it has been rolled into another resource, when the website related to the resource goes down, or any other reason that it's difficult or impossible to find full metadata on the resource. If this is set to true, please add a comment explaining why. This flag will override annotations from the OLS, OBO Foundry, and others on the deprecation status, since they often disagree and are very conservative in calling dead resources.", + "title": "Deprecated" + }, + "mappings": { + "anyOf": [ + { + "additionalProperties": { + "type": "string" + }, + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A dictionary of metaprefixes (i.e., prefixes for registries) to prefixes in external registries. These also correspond to the registry-specific JSON fields in this model like ``miriam`` field.", + "title": "Mappings" + }, + "synonyms": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A list of synonyms for the prefix of this resource. These are used in normalization of prefixes and are a useful reference tool for prefixes that are written many ways. For example, ``snomedct`` has many synonyms including typos like ``SNOWMEDCT``, lexical variants like ``SNOMED_CT``, version-variants like ``SNOMEDCT_2010_1_31``, and tons of other nonsense like ``SNOMEDCTCT``.", + "title": "Synonyms" + }, + "keywords": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A list of keywords for the resource", + "title": "Keywords" + }, + "references": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A list of URLs to also see, such as publications describing the resource", + "title": "References" + }, + "publications": { + "anyOf": [ + { + "items": { + "$ref": "#/$defs/Publication" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A list of URLs to also see, such as publications describing the resource", + "title": "Publications" + }, + "appears_in": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A list of prefixes that use this resource for xrefs, provenance, etc.", + "title": "Appears In" + }, + "depends_on": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A list of prefixes that use this resource depends on, e.g., ontologies that import each other.", + "title": "Depends On" + }, + "namespace_in_lui": { + "anyOf": [ + { + "type": "boolean" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A flag denoting if the namespace is embedded in the LUI (if this is true and it is not accompanied by a banana, assume that the banana is the prefix in all caps plus a colon, as is standard in OBO). Currently this flag is only used to override identifiers.org in the case of ``gramene.growthstage``, ``oma.hog``, and ``vario``.", + "title": "Namespace Embedded in Local Unique Identifier" + }, + "no_own_terms": { + "anyOf": [ + { + "type": "boolean" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A flag denoting if the resource mints its own identifiers. Omission or explicit marking as false means that the resource does have its own terms. This is most applicable to ontologies, specifically application ontologies, which only reuse terms from others. One example is ChIRO.", + "title": "No Own Terms" + }, + "comment": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A field for a free text comment", + "title": "Comment" + }, + "contributor": { + "anyOf": [ + { + "$ref": "#/$defs/Author" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The contributor of the prefix to the Bioregistry, including at a minimum their name and ORCiD and optional their email address and GitHub handle. All entries curated through the Bioregistry GitHub Workflow must contain this field." + }, + "contributor_extras": { + "anyOf": [ + { + "items": { + "$ref": "#/$defs/Author" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Additional contributors besides the original submitter.", + "title": "Contributor Extras" + }, + "reviewer": { + "anyOf": [ + { + "$ref": "#/$defs/Author" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The reviewer of the prefix to the Bioregistry, including at a minimum their name and ORCiD and optional their email address and GitHub handle. All entries curated through the Bioregistry GitHub Workflow should contain this field pointing to the person who reviewed it on GitHub." + }, + "proprietary": { + "anyOf": [ + { + "type": "boolean" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A flag to denote if this database is proprietary and therefore can not be included in normal quality control checks nor can it be resolved. Omission or explicit marking as false means that the resource is not proprietary.", + "title": "Proprietary" + }, + "has_canonical": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "If this shares an IRI with another entry, maps to which should be be considered as canonical", + "title": "Has Canonical" + }, + "preferred_prefix": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "An annotation of stylization of the prefix. This appears in OBO ontologies like FBbt as well as databases like NCBIGene. If it's not given, then assume that the normalized prefix used in the Bioregistry is canonical.", + "title": "Preferred Prefix" + }, + "twitter": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The twitter handle for the project", + "title": "Twitter" + }, + "mastodon": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The mastodon handle for the project", + "title": "Mastodon" + }, + "github_request_issue": { + "anyOf": [ + { + "type": "integer" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The GitHub issue for the new prefix request", + "title": "Github Request Issue" + }, + "logo": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The URL of the logo for the project/resource", + "title": "Logo" + }, + "miriam": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Miriam" + }, + "n2t": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "N2T" }, - "name": { - "title": "Name", - "description": "The human-readable label for the registry", - "type": "string" + "prefixcommons": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Prefixcommons" }, - "description": { - "title": "Description", - "description": "A full description of the registry.", - "type": "string" + "wikidata": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Wikidata" }, - "homepage": { - "title": "Homepage", - "description": "The URL for the homepage of the registry.", - "type": "string" + "go": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Go" }, - "example": { - "title": "Example", - "description": "An example prefix inside the registry.", - "type": "string" + "obofoundry": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Obofoundry" }, - "bibtex": { - "title": "Bibtex", - "description": "Citation key used in BibTex for this registry.", - "type": "string" + "bioportal": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Bioportal" }, - "availability": { - "title": "Availability", - "description": "A structured description of the metadata that the registry collects", - "allOf": [ + "ecoportal": { + "anyOf": [ { - "$ref": "#/definitions/RegistrySchema" + "type": "object" + }, + { + "type": "null" } - ] + ], + "default": null, + "title": "Ecoportal" }, - "qualities": { - "title": "Qualities", - "description": "A structured description of the registry's qualities", - "allOf": [ + "agroportal": { + "anyOf": [ + { + "type": "object" + }, { - "$ref": "#/definitions/RegistryQualities" + "type": "null" } - ] + ], + "default": null, + "title": "Agroportal" }, - "governance": { - "title": "Governance", - "description": "A structured description of the governance for the registry", - "allOf": [ + "cropoct": { + "anyOf": [ { - "$ref": "#/definitions/RegistryGovernance" + "type": "object" + }, + { + "type": "null" } - ] + ], + "default": null, + "title": "Cropoct" }, - "download": { - "title": "Download", - "description": "A download link for the data contained in the registry", - "type": "string" + "ols": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Ols" }, - "provider_uri_format": { - "title": "Provider Uri Format", - "description": "A URL with a $1 for a prefix to resolve in the registry", - "type": "string" + "aberowl": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Aberowl" }, - "search_uri_format": { - "title": "Search Uri Format", - "description": "A URL with a $1 for a prefix or string for searching for prefixes", - "type": "string" + "ncbi": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Ncbi" }, - "resolver_uri_format": { - "title": "Resolver Uri Format", - "description": "A URL with a $1 for a prefix and $2 for an identifier to resolve in the registry", - "type": "string" + "uniprot": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Uniprot" }, - "resolver_type": { - "title": "Resolver Type", - "description": "An optional type annotation for what kind of resolver it is (i.e., redirect or lookup)", - "type": "string" + "biolink": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Biolink" }, - "contact": { - "title": "Contact", - "description": "The contact for the registry.", - "allOf": [ + "cellosaurus": { + "anyOf": [ { - "$ref": "#/definitions/Attributable" + "type": "object" + }, + { + "type": "null" } - ] + ], + "default": null, + "title": "Cellosaurus" }, - "bioregistry_prefix": { - "title": "Bioregistry Prefix", - "description": "The prefix for this registry in the Bioregistry", - "type": "string" + "ontobee": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Ontobee" }, - "logo_url": { - "title": "Logo Url", - "description": "The URL for the logo of the resource", - "type": "string" + "cheminf": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Cheminf" }, - "license": { - "title": "License", - "description": "The license under which the resource is redistributed", - "type": "string" + "fairsharing": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Fairsharing" }, - "short_name": { - "title": "Short Name", - "description": "A short name for the resource, e.g., for use in charts", - "type": "string" - } - }, - "required": [ - "prefix", - "name", - "description", - "homepage", - "example", - "availability", - "qualities", - "governance", - "contact" - ] - }, - "Context": { - "title": "Context", - "description": "A prescriptive context contains configuration for generating fit-for-purpose\nprefix maps to serve various communities based on the standard Bioregistry\nprefix map, custom prefix remapping rules, custom URI prefix remapping rules,\ncustom prefix maps, and other community-specific logic.", - "type": "object", - "properties": { - "name": { - "title": "Name", - "description": "The name of the context", - "type": "string" + "biocontext": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Biocontext" }, - "description": { - "title": "Description", - "description": "A description of the context, can include Markdown", - "type": "string" + "edam": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Edam" }, - "maintainers": { - "title": "Maintainers", - "description": "A list of maintainers for the context", - "type": "array", - "items": { - "$ref": "#/definitions/Author" - } + "re3data": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Re3Data" }, - "prefix_priority": { - "title": "Prefix Priority", - "description": "This ordering of metaprefixes (i.e., prefixes for registries) is used to determine the priority of which registry's prefixes are used. By default, the canonical Bioregistry prefixes are highest priority. Add in \"preferred\" for explicitly using preferred prefixes or \"default\" for explicitly using Bioregistry canonical prefixes.", - "type": "array", - "items": { - "type": "string" - } + "hl7": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Hl7" }, - "include_synonyms": { - "title": "Include Synonyms", - "description": "Should synonyms be included in the prefix map?", - "default": false, - "type": "boolean" + "bartoc": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "BARTOC" }, - "uri_prefix_priority": { - "title": "Uri Prefix Priority", - "description": "This ordering of metaprefixes (i.e., prefixes for registries) is used to determine the priority of which registry's URI prefixes are used. By default, the canonical Bioregistry URI prefixes are highest priority.", - "type": "array", - "items": { - "type": "string" - } + "rrid": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "RRID" }, - "prefix_remapping": { - "title": "Prefix Remapping", - "description": "This is a mapping from canonical Bioregistry prefixes to custom prefixes used in this context.", - "type": "object", - "additionalProperties": { - "type": "string" - } + "lov": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "LOV" }, - "custom_prefix_map": { - "title": "Custom Prefix Map", - "description": "This is a custom prefix map (which contains custom URL/URI expansions) that is added after all other logic is applied. Keys must either be canonical Bioregistry prefixes, prefixes used based on the given prefix priority, or values in the given prefix remapping.", - "type": "object", - "additionalProperties": { - "type": "string" - } + "zazuko": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Zazuko" }, - "blacklist": { - "title": "Blacklist", - "description": "This is a list of canonical Bioregistry prefixes that should not be included in the context.", - "type": "array", - "items": { - "type": "string" - } + "togoid": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Togoid" + }, + "integbio": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Integbio" + }, + "pathguide": { + "anyOf": [ + { + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "title": "Pathguide" } }, "required": [ - "name", - "description", - "maintainers", - "prefix_priority", - "uri_prefix_priority", - "prefix_remapping", - "custom_prefix_map", - "blacklist" - ] + "prefix" + ], + "title": "Resource", + "type": "object" } - } + }, + "title": "Bioregistry JSON Schema", + "description": "The Bioregistry JSON Schema describes the shapes of the objects in the registry, metaregistry, collections, and their other related resources" } \ No newline at end of file diff --git a/src/bioregistry/schema/struct.py b/src/bioregistry/schema/struct.py index 97f4042e0..da0eca716 100644 --- a/src/bioregistry/schema/struct.py +++ b/src/bioregistry/schema/struct.py @@ -36,6 +36,7 @@ EMAIL_RE, ORCID_PATTERN, PATTERN_KEY, + PYDANTIC_1, URI_FORMAT_KEY, ) from bioregistry.license_standardizer import standardize_license @@ -2789,6 +2790,9 @@ def _allowed_uri_format(rv: str) -> bool: @lru_cache(maxsize=1) def get_json_schema(): """Get the JSON schema for the bioregistry.""" + if PYDANTIC_1: + raise NotImplementedError + rv = { "$schema": "http://json-schema.org/draft-07/schema#", "$id": "https://bioregistry.io/schema.json", @@ -2811,21 +2815,14 @@ def get_json_schema(): " resources" ) - try: - # see https://docs.pydantic.dev/latest/usage/json_schema/#general-notes-on-json-schema-generation - from pydantic.json_schema import models_json_schema - except ImportError: - schema_dict = pydantic.schema.schema( - models, - title=title, - description=description, - ) - else: - _, schema_dict = models_json_schema( - [(model, "validation") for model in models], - title=title, - description=description, - ) + # see https://docs.pydantic.dev/latest/usage/json_schema/#general-notes-on-json-schema-generation + from pydantic.json_schema import models_json_schema + + _, schema_dict = models_json_schema( + [(model, "validation") for model in models], + title=title, + description=description, + ) rv.update(schema_dict) return rv diff --git a/tests/test_data.py b/tests/test_data.py index 3496a674a..ebf8d7256 100644 --- a/tests/test_data.py +++ b/tests/test_data.py @@ -34,9 +34,9 @@ def setUp(self) -> None: self.registry = bioregistry.read_registry() self.metaregistry = bioregistry.read_metaregistry() - @unittest.skipUnless( + @unittest.skipIf( PYDANTIC_1, - reason="Only run this test on Pydantic 1, until feature parity is simple enough.", + reason="Only run this test on Pydantic 2, since the schema slightly changed", ) def test_schema(self): """Test the schema is up-to-date."""