dosdp_schema.yaml

$schema: "http://json-schema.org/draft-07/schema#"
#id: 'https://github.com/dosumis/dead_simple_owl_design_patterns/edit/master/spec/DOSDP_spec.json' # Use Purl?
title: DOSDP
type: object
additionalProperties: False


definitions:

  multi_clause_printf:
    required: [ 'clauses' ]
    additionalProperties: False
    properties:
      sep:
        type: string
        description: >
          A string used as clause separator while aggregating multiple clauses.
      clauses:
        type: array
        description: >
          List of optional clauses.  Rules for optional clauses:  list_vars may be passed,
          but only one list_var per multi-clause printf is permitted. If an empty list_var is passed,
          the clause, and any subclauses, are omitted. If list_var with length n is passed, the
          clause is repeated n times, using the specified separtor to join clauses.  There is no
          effect on the number of subclauses in this case.
        items: { $ref : '#/definitions/printf_clause' }

  printf_clause:
    required: [ 'text', 'vars' ]
    additionalProperties: False
    properties:
      text:
        description: A print format string.
        type: string
      vars:
        description: >
          An ordered list of variables for substitution into the accompanying
          print format string. Each entry must correspond to the name of a variable
          specified in either the 'vars', 'internal_vars' or the data_var field of the pattern.
          Where an OWL entity is specified, the label for the OWL entity should be
          used in the substitution.
          SPECIAL RULES FOR multi_clause_printf context: In this context, list_vars are permitted.
          If an list is empty, the clause and any subclauses must not be added.  for lists of
          length > 1, mutiple clauses should be added, using the specified separator
        type: array
        items: { type: string }
      sub_clauses:
        description: >
          List of clauses that depends on this clause. If parent clause cannot be printed,
          all sub_clauses are also discarded.
        type: array
        items: { $ref : '#/definitions/multi_clause_printf' }

  function:
    oneOf:
      - { $ref : "#/definitions/join" }
      - { $ref : "#/definitions/regex_sub" }

  join:
    properties:
      sep:
        type: string
        description: >
          A string used as value separator while joining list type (multi value) variables.

  printf_annotation:
    type: object
    additionalProperties: False
    oneOf:
      - required: [ annotationProperty, text ]
      - required: [ multi_clause ]
    properties:
      annotationProperty:
        description: >
         A string corresponding to the rdfs:label
         of an owl annotation property. If the annotation property has no label,
         the shortForm ID should be used. The annotation property must be listed
         in the annotation property dictionary.'
        type: string
      annotations:
        items: { $ref: "#/definitions/annotations" }
        type: array
      text:
        description: A print format string.
        type: string
      vars:
        description: >
         An ordered list of variables for substitution into the accompanying
         print format string. Each entry must correspond to the name of a variable
         specified in either the 'vars' field or the data_var field of the pattern.
         Where an OWL entity is specified, the label for the OWL entity should be
         used in the substitution.  An empty var list can be specified simply by
         leaving this field out.
        items: {type: string}
        type: array
      multi_clause:
        items: { $ref: '#/definitions/multi_clause_printf' }


  list_annotation:
    type: object
    additionalProperties: False
    required: [annotationProperty, value]
    properties:
      annotationProperty:
        description: >
         A string corresponding to the rdfs:label
         of an owl annotation property. If the annotation property has no label,
         the shortForm ID should be used. The annotation property must be listed
         in the annotation property dictionary.'
        type: string
      value:
        description: >
         A single list variable (list_var or data_list_var).  Each item in this list
         should be used to generate a separate annotation axiom.
        type: string

  iri_value_annotation:
    type: object
    additionalProperties: False
    required: [annotationProperty, var]
    properties:
      annotationProperty:
        description: A string corresponding to a key in the annotation property dictionary.
        type: string
      var:
        description: The name of a variable specified in the 'vars' field. The IRI of the variable value will be the object of the annotation axiom.
        type: string
      annotations:
        items: { $ref: "#/definitions/annotations" }
        type: array

  annotations:
   oneOf:
     - { $ref: "#/definitions/printf_annotation" }
     - { $ref: "#/definitions/list_annotation" }
     - { $ref: "#/definitions/iri_value_annotation" }

  printf_owl:
    type: object
    additionalProperties: False
    oneOf:
      - required: [ axiom_type, text, vars ]
      - required: [ multi_clause ]
    properties:
      annotations:
        items: {$ref: '#/definitions/annotations'}
        type: array
      axiom_type:
        description: >
         OWL axiom type expressed as manchester syntax: equivalentTo,
         subClassOf, disjointWith. GCI  - for general class inclusion axioms, is
         also valid (although missing from manchester syntax.) This specifies the
         axiom type to be generated from the text following substitution.'
        enum: [equivalentTo, subClassOf, disjointWith, GCI]
        type: string
      text:
        type: string
        description: >
         A print format string in OWL Manchester syntax. Each entry
         must correspond to an entry in o the name of a var in the var field of the
         pattern. Entries in single quotes must correspond to the labels of entries
         in owl_entity dictionaries (classes, relations, dataProperties)
      vars:
        description: >
         An ordered list of variables for substitution into the accompanying
         print format string. Each entry must correspond to the name of a variable
         specified in either the 'vars' field or the data_var field of the pattern.
         An empty var list can be specified simply by leaving this field out.
        items: {type: string}
        type: array
      multi_clause:
        items: { $ref: '#/definitions/multi_clause_printf' }

  printf_owl_convenience:
    type: object
    additionalProperties: False
    oneOf:
      - required: [ text, vars ]
      - required: [ multi_clause ]
    properties:
      annotations:
        items: {$ref: '#/definitions/annotations'}
        type: array
      text:
        type: string
        description: >
         A print format string in OWL Manchester syntax. Each entry
         must correspond to an entry in o the name of a var in the var field of the
         pattern. Entries in single quotes must correspond to the labels of entries
         in owl_entity dictionaries (classes, relations, dataProperties)
      vars:
        description: >
         An ordered list of variables for substitution into the accompanying
         print format string. Each entry must correspond to the name of a variable
          specified in either the 'vars' field or the data_var field of the pattern.
        items: {type: string}
        type: array
      multi_clause:
        items: { $ref: '#/definitions/multi_clause_printf' }

  regex_sub:
    additionalProperties: False
    required: [in, out, match, sub]
    type: object
    properties:
      in:
        type: string
        description: name of input var
      out:
        type: string
        description: >
          Name of output var.  If input var specified an OWL entity then
          readable identifier is used as input to substitution
      match:
        type: string
        description: perl style regex match
      sub:
        type: string
        description: perl style regex sub.  May include backreferences.

  opa:
    type: object
    additionalProperties: False
    required: [edge]
    properties:
      edge:
        description: >
          A triple specified as an ordered array with 3 elements
          [subject, rel, object]
          * rel must be the quoted name of a relation from the relations
          (object property) dictionary.
          * subject and object must be the name of an individual
          specified in the nodes field.
        type: array
        items: { type: string }
        minItems: 3
        maxItems: 3
      annotations:
        type: array
        items: { $ref: '#/definitions/annotations' }
      not:
        description: "Optional field for negated OPAs"
        type: boolean

  # TODO - split into separate schema file
  printf_annotation_obo:
    type: object
    additionalProperties: False
    oneOf:
      - required: [ text, vars ]
      - required: [ multi_clause ]
    properties:
      annotations:
        items: { $ref: "#/definitions/annotations" }
        type: array
      xrefs:
        description: >
         Takes the name of a single data_list_var specifying a list of database
         cross references.
        type: string
        mapping: "oboInOwl:hasDbXref"
      text:
        description: A print format string.
        type: string
      vars:
        description: >
         An ordered list of variables for substitution into the accompanying
         print format string. Each entry must correspond to the name of a variable
         specified in either the 'vars' field or the data_var field of the pattern.
         Where an OWL entity is specified, the label for the OWL entity should be
         used in the substitution.
        items: {type: string}
        type: array
      multi_clause:
        items: { $ref: '#/definitions/multi_clause_printf' }

  list_annotation_obo:
    type: object
    additionalProperties: False
    required: [value]
    properties:
      value:
        description: >
         A single list variable (list_var or data_list_var).  Each item in this list
         should be used to generate a separate annotation axiom.
        type: string
      xrefs:
        description: >
         Takes the name of a single data_list_var specifying a list of database
         cross references. Use of this field should add the same xref set to all
         annotation axioms generated.
        type: string
        mapping: "oboInOwl:hasDbXref"


# Generic properties

properties:
  pattern_name:
    type: string  # possible to specify ASCII?
    description: >
      The name of the pattern.  This must be an ASCII string with
      no spaces. The only special characters allowed are '_' and '-'.
      By convention, this is used as the file name of the
      pattern - with an appropriate extension.
    doc_type: root

  pattern_iri:
    type: string
    description: >
       A global identifier for the pattern. This can be a full IRI or a CURIE, using
       the same prefix mappings as other CURIEs in the pattern.
    doc_type: root

  base_IRI:  # not rqd, give JSON-LD base.
    type: string # how to spec IRI?
    description: "Specifies the base IRI to be used to generate new classes."
    doc_type: root

  contributors:
    type: array
    items: { type: string }
    description: >
       A list of authors of a pattern.
       Each author must be specified using a URL or Curie - we recommend ORCID.
       We do not recommend that this list is instantiated in terms generated using a pattern,
       but where it is it should be instantiated as a set of annotation axioms using dc:contributor.
    doc_type: root

  description:
    type: string # specify UTF-8 string?
    description: "A free text description of the pattern.  Must be UTF-8 encoded."
    doc_type: root

  examples:
    type: array
    items: { type: string }
    description:  "A list of example terms implementing this pattern."
    doc_type: root

  status:
    type: string
    description: "Implementation status of pattern."
    enum:
       - development
       - published
    doc_type: root

  tags:
    type: array
    items: { type: string }
    description: >
       A list of strings used to tag a pattern for the purposes of arbitrary,
       cross-cutting grouping of patterns.
    doc_type: root

  readable_identifiers:
    type: array
    items:  { type: string }
    description: "A list of annotation properties used as naming fields, in order of preference."
    doc_type: root

#### owl_entity Dictionaries

  classes:
    type: object
    description: "A dictionary of OWL classes. key :label; value : short form id"
    doc_type: owl_entity_dict
  objectProperties:
    type: object
    description: "A dictionary of OWL object properties. key : label; value : short form id"
    doc_type: owl_entity_dict
  relations:
    # Just an alternative name for the ObjectProperties dict
    type: object
    description: "A dictionary of OWL object properties. key : label; value : short form id"
    doc_type: owl_entity_dict
  dataProperties:
    type: object
    description: "A dictionary of OWL data properties key : label; value : short form id"
    doc_type: owl_entity_dict
  annotationProperties:
    type: object
    description: "A dictionary of OWL annotation properties key : label; value : short form id"
    doc_type: owl_entity_dict

# Var types

  vars:
    type: object
    propertyNames:
       pattern: "^[A-Za-z_][A-Za-z0-9_]*$"
    description: >
     A dictionary of variables ranging over OWL classes.
     Key = variable name, value = variable range as manchester syntax string.
    doc_type: var_types

  list_vars:
    type: object
    propertyNames:
       pattern: "^[A-Za-z_][A-Za-z0-9_]*$"
    description: >
     A dictionary of variables refering to lists of owl classes.
     Key = variable name, value = variable range of items in list specified as a valid OWL
     data-type.
    doc_type: var_types

  data_vars:
    type: object
    propertyNames:
       pattern: "^[A-Za-z_][A-Za-z0-9_]*$"
    description: >
     A dictionary of variables ranging over OWL data-types.
     Key = variable name, value = variable range specified as a valid OWL
     data-type.
    doc_type: var_types

  data_list_vars:
    type: object
    propertyNames:
       pattern: "^[A-Za-z_][A-Za-z0-9_]*$"
    description: >
        A dictionary of variables rrefering to lists of some specified OWL data-types.
        Key = variable name, value = variable range of all items in list,
        specified as a valid OWL data-type.
    doc_type: var_types

  internal_vars:
    type: array
    properties:
      var_name:
        pattern: "^[A-Za-z_][A-Za-z0-9_]*$"
        description: >
          Name of the internal variable to be defined. Expected naming pattern is ^[A-Za-z_][A-Za-z0-9_]*$
        type: string
      input:
        description: >
          A list_vars or data_list_vars variable to which the given function applied.
        type: string
      apply: { $ref: "#/definitions/function" }
    description: >
      List of internal variable construction definitions. Given function is applied to the given multi value input
      and the result is defined as a new internal variable.
    doc_type: var_types

# Var munging

  substitutions:
    type: array
    items: { $ref : '#/definitions/regex_sub' }
    doc_type: var_munging

# Specifying axioms:

  annotations:
    items: { $ref: "#/definitions/annotations" }
    type: array
    doc_type: axioms

  logical_axioms:
    items: { $ref: '#/definitions/printf_owl'}
    type: array
    doc_type: axioms

# logical convenience fields.
# Where only one of any OWL axiom type is present, these convenience fields may be used.

  equivalentTo:
    $ref: '#/definitions/printf_owl_convenience'
    doc_type: convenience

  subClassOf:
    $ref: '#/definitions/printf_owl_convenience'
    doc_type: convenience

  GCI:
    $ref: '#/definitions/printf_owl_convenience'
    doc_type: convenience

  disjointWith:
    $ref: '#/definitions/printf_owl_convenience'
    doc_type: convenience

# OBO fields - TODO split to a separate file with import statement.

  name:
    $ref: '#/definitions/printf_annotation_obo'
    mapping: "rdfs:label"
    doc_type: obo
  comment:
    $ref: '#/definitions/printf_annotation_obo'
    mapping: "rdfs:comment"
    doc_type: obo
  def:
    $ref: '#/definitions/printf_annotation_obo'
    mapping: "obo:IAO_0000115"
    doc_type: obo
  namespace:
    $ref: '#/definitions/printf_annotation_obo'
    mapping: "oboInOwl:hasOBONamespace"
    doc_type: obo

  # TODO: make all these into list_annotations
  exact_synonym:
    $ref: '#/definitions/list_annotation_obo'
    mapping: "oboInOwl:hasExactSynonym"
    doc_type: obo
  narrow_synonym:
    $ref: '#/definitions/list_annotation_obo'
    mapping: "oboInOwl:hasNarrowSynonym"
    doc_type: obo
  related_synonym:
    $ref: '#/definitions/list_annotation_obo'
    mapping: "oboInOwl:hasRelatedSynonym"
    doc_type: obo
  broad_synonym:
    $ref: '#/definitions/list_annotation_obo'
    mapping: "oboInOwl:hasBroadSynonym"
    doc_type: obo
  xref:
    $ref: '#/definitions/list_annotation_obo'
    mapping: "oboInOwl:hasDbXref"
    doc_type: obo

  generated_synonyms:
    description: >
      An OBO convenience field to allow the specification of exact synonyms
      generated by interpolation of OWL entity names into printf text.
      Each entry may be annotated.
    type: array
    items:
      $ref: '#/definitions/printf_annotation_obo'
      mapping: "oboInOwl:hasExactSynonym"
    doc_type: obo

  generated_narrow_synonyms:
    description: >
      An OBO convenience field to allow the specification of narrow synonyms
      generated by interpolation of OWL entity names into printf text.
      Each entry may be annotated.
    type: array
    items:
      $ref: '#/definitions/printf_annotation_obo'
      mapping: "oboInOwl:hasNarrowSynonym"
    doc_type: obo

  generated_broad_synonyms:
    description: >
      An OBO convenience field to allow the specification of broad synonyms
      generated by interpolation of OWL entity names into printf text.
      Each entry may be annotated.
    type: array
    items:
      $ref: '#/definitions/printf_annotation_obo'
      mapping: "oboInOwl:hasBroadSynonym"
    doc_type: obo

  generated_related_synonyms:
    description: >
      An OBO convenience field to allow the specification of related synonyms
      generated by interpolation of OWL entity names into printf text.
      Each entry may be annotated.
    type: array
    items:
      $ref: '#/definitions/printf_annotation_obo'
      mapping: "oboInOwl:hasBroadSynonym"
    doc_type: obo

# instance graph spec - TODO be split to a separate file

  instance_graph:
    type: object
    additionalProperties: False
    required: [nodes, edges]
    properties:
      nodes:
        description: >
                       Key = name of individual within this pattern doc
                       Value = Type of individual specified using either
                       the quoted name of a class in the class dictionary of this pattern
                       or a var name.  This field does not support typing via
                       anonymous class expressions
        type: object
      edges:
        type: array
        items: { $ref : '#/definitions/opa' }
    doc_type: instance_graph