briard 2.8.2 → 2.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b82034f66939dab07cc20186304bcdbffdde06c43abc4c614ae2bae68e4d0f72
-  data.tar.gz: b8f5d74bff45e5f016e7ec094860c632b01b66df5f104501b3c4bae6fc4adc8c
+  metadata.gz: 630bdfe771252795f1d396dc2eb3da9fce76c3bf8c0281347be8c8e97e5ae1f4
+  data.tar.gz: e80734a4a4163ce8a6ff581aa9d49034ddff4b961953ab8740566d09e2886e73
 SHA512:
-  metadata.gz: 4d143feff904aef51b688359e9888d83ac627566febea50fcfd7d5dec001c0634f268a3918aa12c4813e4f2c2a8acbb190c75a9ff7d6bbb580e26925ca292c2f
-  data.tar.gz: 4185d017bb16a13ee4e10a5e0b9335178e8b8bf36b6d951cc82976814176d0a254818235570c6806812f5e7b01b3026492044ca7923964185221e860abfc3ed5
+  metadata.gz: 5dfce207ab441f813d69fb79fb0d354823234a8fced4566703de4cdb67f4522c99b4836e1e7d5abeedb7863ad82f082019d2a2289b019ddf56048b8afe959ecf
+  data.tar.gz: 07dfbff46d904dc090d640d8e8d26591d3d88ec6d841e6f781c2804946e679fc03c7d0407943e516af158d34a6e5ec0379d2f5d8f2799efad8c57d7b77ebbba9

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## [v2.8.2](https://github.com/front-matter/briard/tree/v2.8.2) (2022-11-23)
+
+[Full Changelog](https://github.com/front-matter/briard/compare/v2.8.0...v2.8.2)
+
 ## [v2.8.0](https://github.com/front-matter/briard/tree/v2.8.0) (2022-11-22)
 
 [Full Changelog](https://github.com/front-matter/briard/compare/v2.6.5...v2.8.0)

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    briard (2.8.2)
+    briard (2.9.0)
       activesupport (>= 4.2.5, < 8.0)
       base32-url (>= 0.5.0, < 1)
       benchmark_methods (~> 0.7)
@@ -18,6 +18,7 @@ PATH
       gender_detector (~> 0.1.2)
       iso8601 (~> 0.9.1)
       json-ld-preloaded (~> 3.1, >= 3.1.3)
+      json_schemer (~> 0.2.23)
       jsonlint (~> 0.3.0)
       loofah (~> 2.19)
       maremma (>= 4.9.7, < 5)
@@ -75,6 +76,8 @@ GEM
       scanf (~> 1.0)
       sxp (~> 1.2)
       unicode-types (~> 1.7)
+    ecma-re-validator (0.4.0)
+      regexp_parser (~> 2.2)
     edtf (3.1.0)
       activesupport (>= 3.0, < 8.0)
     excon (0.71.1)
@@ -99,6 +102,7 @@ GEM
     haml (5.2.2)
       temple (>= 0.8.0)
       tilt
+    hana (1.3.7)
     hashdiff (1.0.1)
     htmlentities (4.3.4)
     i18n (1.12.0)
@@ -116,6 +120,11 @@ GEM
     json-ld-preloaded (3.2.2)
       json-ld (~> 3.2)
       rdf (~> 3.2)
+    json_schemer (0.2.23)
+      ecma-re-validator (~> 0.3)
+      hana (~> 1.3)
+      regexp_parser (~> 2.0)
+      uri_template (~> 0.7)
     jsonlint (0.3.0)
       oj (~> 3)
       optimist (~> 3)
@@ -245,6 +254,7 @@ GEM
     unicode-display_width (2.3.0)
     unicode-types (1.8.0)
     unicode_utils (1.4.0)
+    uri_template (0.7.0)
     vcr (3.0.3)
     webmock (3.18.1)
       addressable (>= 2.8.0)

data/briard.gemspec

@@ -35,6 +35,7 @@ Gem::Specification.new do |s|
   s.add_dependency 'iso8601', '~> 0.9.1'
   s.add_dependency 'json-ld-preloaded', '~> 3.1', '>= 3.1.3'
   s.add_dependency 'jsonlint', '~> 0.3.0'
+  s.add_dependency 'json_schemer', '~> 0.2.23'
   s.add_dependency 'loofah', '~> 2.19'
   s.add_dependency 'maremma', '>= 4.9.7', '< 5'
   s.add_dependency 'namae', '~> 1.0'

data/lib/briard/metadata.rb

@@ -163,9 +163,11 @@ module Briard
       exists? && errors.nil?
     end
 
-    # validate against DataCite schema, unless already errors in the reader
+    # Catch errors in the reader
+    # Then validate against JSON schema for internal metadata format
+    # Then validate against DataCite schema, unless already errors in the reader
     def errors
-      meta.fetch('errors', nil) || datacite_errors(xml: datacite, schema_version: schema_version)
+      meta.fetch('errors', nil) || json_schema_errors || datacite_errors(xml: datacite, schema_version: schema_version)
     end
 
     def descriptions

data/lib/briard/metadata_utils.rb

@@ -4,6 +4,7 @@ require_relative 'doi_utils'
 require_relative 'author_utils'
 require_relative 'crossref_utils'
 require_relative 'datacite_utils'
+require_relative 'schema_utils'
 require_relative 'utils'
 
 require_relative 'readers/bibtex_reader'
@@ -42,6 +43,7 @@ module Briard
     include Briard::AuthorUtils
     include Briard::CrossrefUtils
     include Briard::DataciteUtils
+    include Briard::SchemaUtils
     include Briard::Utils
 
     include Briard::Readers::BibtexReader

data/lib/briard/readers/datacite_reader.rb

@@ -310,7 +310,7 @@ module Briard
           'container' => set_container(meta),
           'publisher' => parse_attributes(meta.fetch('publisher', nil),
                                           first: true).to_s.strip.presence,
-          'agency' => 'datacite',
+          'agency' => 'DataCite',
           'funding_references' => funding_references,
           'dates' => dates,
           'publication_year' => parse_attributes(meta.fetch('publicationYear', nil),

data/lib/briard/schema_utils.rb

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+require 'json_schemer'
+require 'pathname'
+
+module Briard
+  module SchemaUtils
+    JSON_SCHEMA = schema = File.read(File.expand_path('../../resources/json-schema/briard_schema.json', __dir__))
+    
+    def json_schema_errors
+      schemer = JSONSchemer.schema(JSON_SCHEMA)
+      errors = schemer.validate(self.meta).to_a
+      errors.map {|err| JSONSchemer::Errors.pretty err }.presence
+    end
+  end
+end

data/lib/briard/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Briard
-  VERSION = '2.8.2'
+  VERSION = '2.9.0'
 end

data/resources/json-schema/briard_schema.json

@@ -0,0 +1,367 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "Briard Schema",
+  "definitions": {
+    "affiliations": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "affiliation": {
+            "type": "string"
+          }
+        },
+        "required": ["affiliation"]
+      },
+      "uniqueItems": true
+    },
+    "contributorType": {
+      "type": "string",
+      "enum": [
+        "ContactPerson",
+        "DataCollector",
+        "DataCurator",
+        "DataManager",
+        "Distributor",
+        "Editor",
+        "HostingInstitution",
+        "Producer",
+        "ProjectLeader",
+        "ProjectManager",
+        "ProjectMember",
+        "RegistrationAgency",
+        "RegistrationAuthority",
+        "RelatedPerson",
+        "Researcher",
+        "ResearchGroup",
+        "RightsHolder",
+        "Sponsor",
+        "Supervisor",
+        "WorkPackageLeader",
+        "Other"
+      ]
+    },
+    "descriptionType": {
+      "type": "string",
+      "enum": [
+        "Abstract",
+        "Methods",
+        "SeriesInformation",
+        "TableOfContents",
+        "TechnicalInfo",
+        "Other"
+      ]
+    },
+    "funderIdentifierType": {
+      "type": "string",
+      "enum": ["ISNI", "GRID", "Crossref Funder ID", "Other"]
+    },
+    "nameIdentifiers": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "nameIdentifier": {
+            "type": "string"
+          },
+          "nameIdentifierScheme": {
+            "type": "string"
+          },
+          "schemeURI": {
+            "type": "string",
+            "format": "uri"
+          }
+        },
+        "required": ["nameIdentifier", "nameIdentifierScheme"]
+      },
+      "uniqueItems": true
+    },
+    "nameType": {
+      "type": "string",
+      "enum": ["Organizational", "Personal"]
+    },
+    "noEmptyString": {
+        "type": "string",
+        "minLength": 1
+    },
+    "resourceTypeGeneral": {
+      "type": "string",
+      "enum": [
+        "Audiovisual",
+        "Collection",
+        "DataPaper",
+        "Dataset",
+        "Event",
+        "Image",
+        "InteractiveResource",
+        "Model",
+        "PhysicalObject",
+        "Service",
+        "Software",
+        "Sound",
+        "Text",
+        "Workflow",
+        "Other"
+      ]
+    },
+    "titleType": {
+      "type": "string",
+      "enum": ["AlternativeTitle", "Subtitle", "TranslatedTitle", "Other"]
+    }
+  },
+  "prefixItems": {
+    "id": {
+      "type": "string",
+      "format": "uri"
+    },
+    "types": {
+      "type": "object",
+      "properties": {
+        "resourceType": {
+          "type": "string"
+        },
+        "resourceTypeGeneral": {
+          "$ref": "#/definitions/resourceTypeGeneral"
+        },
+        "schemaOrg": {
+          "type": "string"
+        },
+        "citeproc": {
+          "type": "string"
+        },
+        "bibtex": {
+          "type": "string"
+        },
+        "ris": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "resourceType",
+        "resourceTypeGeneral",
+        "schemaOrg",
+        "citeproc",
+        "bibtex",
+        "ris"
+      ]
+    },
+    "doi": {
+      "type": "string",
+      "format": "uri"
+    },
+    "url": {
+      "type": "string",
+      "format": "uri"
+    },
+    "titles": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "title": {
+            "type": "string"
+          },
+          "titleType": {
+            "$ref": "#/definitions/titleType"
+          },
+          "lang": {
+            "type": "string"
+          }
+        },
+        "required": ["title"]
+      },
+      "minItems": 1,
+      "uniqueItems": true
+    },
+    "creators": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string"
+          },
+          "nameType": {
+            "$ref": "#/definitions/nameType"
+          },
+          "givenName": {
+            "type": "string"
+          },
+          "familyName": {
+            "type": "string"
+          },
+          "nameIdentifiers": {
+            "$ref": "#/definitions/nameIdentifiers"
+          },
+          "affiliations": {
+            "$ref": "#/definitions/affiliations"
+          },
+          "lang": {
+            "type": "string"
+          }
+        },
+        "required": ["name"]
+      },
+      "minItems": 1,
+      "uniqueItems": true
+    },
+    "contributors": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "contributorType": {
+            "$ref": "#/definitions/contributorType"
+          },
+          "name": {
+            "type": "string"
+          },
+          "nameType": {
+            "$ref": "#/definitions/nameType"
+          },
+          "givenName": {
+            "type": "string"
+          },
+          "familyName": {
+            "type": "string"
+          },
+          "nameIdentifiers": {
+            "$ref": "#/definitions/nameIdentifiers"
+          },
+          "affiliations": {
+            "$ref": "#/definitions/affiliations"
+          },
+          "lang": {
+            "type": "string"
+          }
+        },
+        "required": ["contributorType", "name"]
+      },
+      "uniqueItems": true
+    },
+    "funding_references": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "funderName": {
+            "type": "string"
+          },
+          "funderIdentifier": {
+            "type": "string"
+          },
+          "funderIdentifierType": {
+            "$ref": "#/definitions/funderIdentifierType"
+          },
+          "awardNumber": {
+            "type": "string"
+          },
+          "awardURI": {
+            "type": "string",
+            "format": "uri"
+          },
+          "awardTitle": {
+            "type": "string"
+          }
+        },
+        "required": ["funderName"]
+      },
+      "uniqueItems": true
+    },
+    "publisher": {
+      "$ref": "#/definitions/noEmptyString"
+    },
+    "publication_year": {
+      "$ref": "#/definitions/noEmptyString"
+    },
+    "language": {
+      "type": "string",
+      "$comment": "Primary language of the resource. Allowed values are taken from  IETF BCP 47, ISO 639-1 language codes."
+    },
+    "sizes": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      },
+      "uniqueItems": true
+    },
+    "formats": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      },
+      "uniqueItems": true
+    },
+    "version_info": {
+      "type": "string"
+    },
+    "rights_list": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "rights": {
+            "type": "string"
+          },
+          "rightsURI": {
+            "type": "string",
+            "format": "uri"
+          },
+          "rightsIdentifier": {
+            "type": "string"
+          },
+          "rightsIdentifierScheme": {
+            "type": "string"
+          },
+          "schemeURI": {
+            "type": "string",
+            "format": "uri"
+          },
+          "lang": {
+            "type": "string"
+          }
+        }
+      },
+      "uniqueItems": true
+    },
+    "descriptions": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "$ref": "#/definitions/noEmptyString"
+          },
+          "descriptionType": {
+            "$ref": "#/definitions/descriptionType"
+          },
+          "lang": {
+            "type": "string"
+          }
+        },
+        "required": ["description", "descriptionType"]
+      },
+      "uniqueItems": true
+    },
+    "agency": {
+      "type": "string",
+      "enum": [ "Crossref", "DataCite", "JaLC", "KISTI", "mEDRA", "OP"]
+    },
+    "schema_version": {
+      "type": "string",
+      "const": "http://datacite.org/schema/kernel-4"
+    },
+    "state": {
+      "type": "string",
+      "enum": [ "draft", "findable", "registered", "not_found"]
+    }
+  },
+  "required": [
+    "id",
+    "creators",
+    "titles",
+    "publisher",
+    "publication_year",
+    "types"
+  ]
+}

data/spec/fixtures/crosscite.json

@@ -58,6 +58,6 @@
         "description": "This tools are used to analyse the data produced by the Crosssover Experiment I designed to test Choice Architecture techniques as UI interventions in a SEEk4Science data catalogue. It contains:\n\n- Data structures for the experimental data.<br>\n- Visualisation functions<br>\n- Analysis functions\n\n## Installation\n\n- R<br>\n- python<br>\n- ipython 4\n\nClone and use.\n\n## Usage\n\n<br>\n```python<br>\nsource('parallel_plot.r')<br>\nwith(z, parallelset(trt,response, freq=count, alpha=0.2))<br>\n```\n\n<br>\n## Contributing\n\n1. Fork it!<br>\n2. Create your feature branch: `git checkout -b my-new-feature`<br>\n3. Commit your changes: `git commit -am 'Add some feature'`<br>\n4. Push to the branch: `git push origin my-new-feature`<br>\n5. Submit a pull request :D\n\n<br>\n## License\n\nThis work supports my PhD Thesis at University of Manchester."
     }],
     "schema_version": "http://datacite.org/schema/kernel-4",
-    "agency": "datacite",
+    "agency": "DataCite",
     "state": "findable"
 }

data/spec/fixtures/datacite.json

@@ -79,5 +79,5 @@
     "description": "Eating your own dog food is a slang term to describe that an organization should itself use the products and services it provides. For DataCite this means that we should use DOIs with appropriate metadata and strategies for long-term preservation for..."
   }],
   "schemaVersion": "http://datacite.org/schema/kernel-4",
-  "agency": "datacite"
+  "agency": "DataCite"
 }

data/spec/fixtures/datacite_software.json

@@ -17,5 +17,5 @@
   "publisher": "KNB Data Repository",
   "publication-year": "2016",
   "schema-version": "http://datacite.org/schema/kernel-3",
-  "agency": "datacite"
+  "agency": "DataCite"
 }

data/spec/fixtures/datacite_software_version.json

@@ -68,7 +68,7 @@
   "schemaVersion": "http://datacite.org/schema/kernel-4",
   "providerId": "cern",
   "clientId": "cern.zenodo",
-  "agency": "datacite",
+  "agency": "DataCite",
   "state": "findable"
 }
    

data/spec/fixtures/vcr_cassettes/Briard_Metadata/json_schema_errors/doi_not_found.yml

@@ -0,0 +1,105 @@
+---
+http_interactions:
+- request:
+    method: get
+    uri: https://doi.org/ra/10.1371
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      User-Agent:
+      - Mozilla/5.0 (compatible; Maremma/4.9.9; mailto:info@front-matter.io)
+      Accept:
+      - text/html,application/json,application/xml;q=0.9, text/plain;q=0.8,image/png,*/*;q=0.5
+      Accept-Encoding:
+      - gzip,deflate
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      Date:
+      - Wed, 23 Nov 2022 15:36:55 GMT
+      Content-Type:
+      - application/json;charset=UTF-8
+      Connection:
+      - keep-alive
+      Permissions-Policy:
+      - interest-cohort=(),browsing-topics=()
+      Content-Encoding:
+      - gzip
+      Cf-Cache-Status:
+      - DYNAMIC
+      Report-To:
+      - '{"endpoints":[{"url":"https:\/\/a.nel.cloudflare.com\/report\/v3?s=pW2Rci9kcFvLvpKnUQNEYCx%2Fa%2Bd%2B3xaolNj89vj9WL3%2FEpnSbPfnDwsL716zPkDpJ2b6gbTuj%2BjPahlSuzsQtj%2FWktyqlLO1KW84Ols70l3zSI%2FsusAEyB%2BBQ7OdCK4Sibm7%2BvY%3D"}],"group":"cf-nel","max_age":604800}'
+      Nel:
+      - '{"success_fraction":0,"report_to":"cf-nel","max_age":604800}'
+      Strict-Transport-Security:
+      - max-age=31536000; includeSubDomains; preload
+      Server:
+      - cloudflare
+      Cf-Ray:
+      - 76eafbb279b2fa30-AMS
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+    body:
+      encoding: ASCII-8BIT
+      string: !binary |-
+        H4sIAAAAAAAAA4vmUlCoBmIFBSUXf08lKwUlQwM9Q2NzQyUdiGiQI0jQuSi/uLgoNU0JKFjLFQsAfpIZsjYAAAA=
+    http_version:
+  recorded_at: Wed, 23 Nov 2022 15:36:55 GMT
+- request:
+    method: get
+    uri: https://api.crossref.org/works/10.1371/xxx/transform/application/vnd.crossref.unixsd+xml
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      User-Agent:
+      - Mozilla/5.0 (compatible; Maremma/4.9.9; mailto:info@front-matter.io)
+      Accept:
+      - text/xml;charset=utf-8
+      Accept-Encoding:
+      - gzip,deflate
+  response:
+    status:
+      code: 404
+      message: Not Found
+    headers:
+      Date:
+      - Wed, 23 Nov 2022 15:36:56 GMT
+      Content-Type:
+      - text/plain;charset=utf-8
+      Set-Cookie:
+      - AWSALB=fgolOntpvptfUSWwgVtdcZuqoAXyqywffb3/prJUNszVTqIEZzP8H5Px3Pw8FqVU86WtTyvC54B6PUTSnD45xuicq+jAN8SwbaAhlhFqshxOtTjCdz4drG6U7jzo;
+        Expires=Wed, 30 Nov 2022 15:36:56 GMT; Path=/, AWSALBCORS=fgolOntpvptfUSWwgVtdcZuqoAXyqywffb3/prJUNszVTqIEZzP8H5Px3Pw8FqVU86WtTyvC54B6PUTSnD45xuicq+jAN8SwbaAhlhFqshxOtTjCdz4drG6U7jzo;
+        Expires=Wed, 30 Nov 2022 15:36:56 GMT; Path=/; SameSite=None
+      Access-Control-Expose-Headers:
+      - Link
+      Access-Control-Allow-Headers:
+      - X-Requested-With, Accept, Accept-Encoding, Accept-Charset, Accept-Language,
+        Accept-Ranges, Cache-Control
+      Access-Control-Allow-Origin:
+      - "*"
+      Server:
+      - Jetty(9.4.40.v20210413)
+      X-Ratelimit-Limit:
+      - '50'
+      X-Ratelimit-Interval:
+      - 1s
+      X-Api-Pool:
+      - polite
+      X-Rate-Limit-Limit:
+      - '50'
+      X-Rate-Limit-Interval:
+      - 1s
+      Permissions-Policy:
+      - interest-cohort=()
+      Connection:
+      - close
+    body:
+      encoding: ASCII-8BIT
+      string: Resource not found.
+    http_version:
+  recorded_at: Wed, 23 Nov 2022 15:36:56 GMT
+recorded_with: VCR 3.0.3