D-Net
/
dnet-hadoop
15
4
Fork 10
Code Issues 14 Pull Requests 8 Projects 2 Releases 1 Wiki Activity

new schemas for the entities in the dump with added descriptions

Browse Source
pull/50/head
Miriam Baglioni 4 years ago
parent 08806deddf
commit c209284ca7
5 changed files with 198 additions and 433 deletions
Show Stats Download Patch File Download Diff File

94
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump_whole/schema/datasource_schema.json
Unescape Escape View File

@ -5,32 +5,30 @@
"type": "object",
"properties": {
"scheme": {
"type": "string",
"description": "Description of scheme"
"type": "string"
},
"value": {
"type": "string",
"description": "Description of value"
"type": "string"
}
}
},
"description": "To represent the information described by a scheme and a value in that scheme (i.e. pid)"
}
},
"type": "object",
"properties": {
"accessrights": {
"type": "string",
"description": "Description of accessrights"
"description": "The database access type: {open, restricted or closed}"
},
"certificates": {
"type": "string",
"description": "Description of certificates"
},
"citationguidelineurl": {
"type": "string",
"description": "Description of citationguidelineurl"
"type": "string"
},
"contenttypes": {
"description": "Description of contenttypes",
"description": "OpenDoar specific fileds ",
"type": "array",
"items": {
"type": "string",
@ -39,7 +37,7 @@
},
"databaseaccessrestriction": {
"type": "string",
"description": "Description of databaseaccessrestriction"
"description": "One of {feeRequired, registration, other}"
},
"datasourcetype": {
"allOf": [
@ -47,114 +45,102 @@
"$ref": "#/definitions/ControlledField"
},
{
"description": "Description of datasourcetype"
"description": "The type of the datasource. See https://api.openaire.eu/vocabularies/dnet:datasource_typologies"
}
]
},
"datauploadrestriction": {
"type": "string",
"description": "Description of datauploadrestriction"
"description": "One of {feeRequired, registration, other}"
},
"dateofvalidation": {
"type": "string",
"description": "Description of dateofvalidation"
"description": "The date of last validation against the OpenAIRE guidelines for the datasource records"
},
"description": {
"type": "string",
"description": "Description of description"
"type": "string"
},
"englishname": {
"type": "string",
"description": "Description of englishname"
"description": "The English name of the datasource"
},
"id": {
"type": "string",
"description": "Description of id"
"description": "The OpenAIRE id of the resource"
},
"journal": {
"type": "object",
"properties": {
"conferencedate": {
"type": "string",
"description": "Description of conferencedate"
"type": "string"
},
"conferenceplace": {
"type": "string",
"description": "Description of conferenceplace"
"type": "string"
},
"edition": {
"type": "string",
"description": "Description of edition"
"description": "Edition of the journal or conference proceeding"
},
"ep": {
"type": "string",
"description": "Description of ep"
"description": "End page"
},
"iss": {
"type": "string",
"description": "Description of iss"
"type": "string"
},
"issnLinking": {
"type": "string",
"description": "Description of issnLinking"
"type": "string"
},
"issnOnline": {
"type": "string",
"description": "Description of issnOnline"
"type": "string"
},
"issnPrinted": {
"type": "string",
"description": "Description of issnPrinted"
"type": "string"
},
"name": {
"type": "string",
"description": "Description of name"
"description": "Name of the journal or conference"
},
"sp": {
"type": "string",
"description": "Description of sp"
"description": "Start page"
},
"vol": {
"type": "string",
"description": "Description of vol"
"type": "string"
}
},
"description": "Description of journal"
},
"languages": {
"description": "Description of languages",
"description": "OpenDOAR specific field",
"type": "array",
"items": {
"type": "string",
"description": "Description of languages"
"type": "string"
}
},
"logourl": {
"type": "string",
"description": "Description of logourl"
"type": "string"
},
"missionstatementurl": {
"type": "string",
"description": "Description of missionstatementurl"
"type": "string"
},
"officialname": {
"type": "string",
"description": "Description of officialname"
"description": "The official name of the datasource"
},
"openairecompatibility": {
"type": "string",
"description": "Description of openairecompatibility"
"description": "Information about the OpenAIRE compatibility of the ingested results (which guidelines they are compliant to)"
},
"originalId": {
"description": "Description of originalId",
"description": "Original identifiers for the datasource"
"type": "array",
"items": {
"type": "string",
"description": "Description of originalId"
"type": "string"
}
},
"pid": {
"description": "Description of pid",
"description": "Persistent identifiers for the datasource",
"type": "array",
"items": {
"allOf": [
@ -187,24 +173,22 @@
"description": "Description of releasestartdate"
},
"subjects": {
"description": "Description of subjects",
"description": "List of subjects associated to the datasource",
"type": "array",
"items": {
"type": "string",
"description": "Description of subjects"
"type": "string"
}
},
"uploadrights": {
"type": "string",
"description": "Description of uploadrights"
"description": "One of {open, restricted or closed}"
},
"versioning": {
"type": "boolean",
"description": "Description of versioning"
},
"websiteurl": {
"type": "string",
"description": "Description of websiteurl"
"type": "string"
}
}
}
}

31
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump_whole/schema/organization_schema.json
Unescape Escape View File

@ -3,11 +3,10 @@
"type": "object",
"properties": {
"alternativenames": {
"description": "Description of alternativenames",
"description": "Alternative names that identify the organisation",
"type": "array",
"items": {
"type": "string",
"description": "Description of alternativenames"
"type": "string"
}
},
"country": {
@ -15,48 +14,44 @@
"properties": {
"code": {
"type": "string",
"description": "Description of code"
"description": "The organisation country code"
},
"label": {
"type": "string",
"description": "Description of label"
"description": "The organisation country label"
}
},
"description": "Description of country"
"description": "The country of the organisation"
},
"id": {
"type": "string",
"description": "Description of id"
"description": "The OpenAIRE id for the organisation"
},
"legalname": {
"type": "string",
"description": "Description of legalname"
"type": "string"
},
"legalshortname": {
"type": "string",
"description": "Description of legalshortname"
"type": "string"
},
"pid": {
"description": "Description of pid",
"description": "Persistent identifiers for the organisation i.e. isni 0000000090326370",
"type": "array",
"items": {
"type": "object",
"properties": {
"scheme": {
"type": "string",
"description": "Description of scheme"
"description": "The scheme of the identifier (i.e. isni)"
},
"value": {
"type": "string",
"description": "Description of value"
"description": "the value in the schema (i.e. 0000000090326370)"
}
},
"description": "Description of pid"
}
}
},
"websiteurl": {
"type": "string",
"description": "Description of websiteurl"
"type": "string"
}
}
}

93
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump_whole/schema/project_schema.json
Unescape Escape View File

@ -3,23 +3,20 @@
"type": "object",
"properties": {
"acronym": {
"type": "string",
"description": "Description of acronym"
"type": "string"
},
"callidentifier": {
"type": "string",
"description": "Description of callidentifier"
"type": "string"
},
"code": {
"type": "string",
"description": "Description of code"
"description": "The grant agreement"
},
"enddate": {
"type": "string",
"description": "Description of enddate"
"type": "string"
},
"funding": {
"description": "Description of funding",
"description": "Funding information for the project",
"type": "array",
"items": {
"type": "object",
@ -29,29 +26,27 @@
"properties": {
"description": {
"type": "string",
"description": "Description of description"
"description": "Description of the funding stream"
},
"id": {
"type": "string",
"description": "Description of id"
"description": "Id of the funding stream"
}
},
"description": "Description of funding_stream"
}
},
"jurisdiction": {
"type": "string",
"description": "Description of jurisdiction"
"description": "The jurisdiction of the funder (i.e. EU)"
},
"name": {
"type": "string",
"description": "Description of name"
"description": "The name of the funder (European Commission)"
},
"shortName": {
"type": "string",
"description": "Description of shortName"
"description": "The short name of the funder (EC)"
}
},
"description": "Description of funding"
}
}
},
"granted": {
@ -59,76 +54,66 @@
"properties": {
"currency": {
"type": "string",
"description": "Description of currency"
"description": "The currency of the granted amount"
},
"fundedamount": {
"type": "number",
"description": "Description of fundedamount"
"description": "The funded amount"
},
"totalcost": {
"type": "number",
"description": "Description of totalcost"
"description": "The total cost"
}
},
"description": "Description of granted"
},
"id": {
"type": "string",
"description": "Description of id"
},
"keywords": {
"type": "string",
"description": "Description of keywords"
},
"openaccessmandatefordataset": {
"type": "boolean",
"description": "Description of openaccessmandatefordataset"
},
"openaccessmandateforpublications": {
"type": "boolean",
"description": "Description of openaccessmandateforpublications"
"description": "The funded amount for the project"
},
"programme": {
"description": "Description of programme",
"h2020programme": {
"description": "The h2020 programme the project is funded under",
"type": "array",
"items": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "Description of code"
"description": "The code of the programme"
},
"description": {
"type": "string",
"description": "Description of description"
"description": "The description of the programme"
}
},
"description": "Description of programme"
}
}
},
"startdate": {
"id": {
"type": "string",
"description": "Description of startdate"
"description": "OpenAIRE id for the project"
},
"keywords": {
"type": "string"
},
"openaccessmandatefordataset": {
"type": "boolean"
},
"openaccessmandateforpublications": {
"type": "boolean"
},
"startdate": {
"type": "string"
},
"subject": {
"description": "Description of subject",
"type": "array",
"items": {
"type": "string",
"description": "Description of subject"
"type": "string"
}
},
"summary": {
"type": "string",
"description": "Description of summary"
"type": "string"
},
"title": {
"type": "string",
"description": "Description of title"
"type": "string"
},
"websiteurl": {
"type": "string",
"description": "Description of websiteurl"
"type": "string"
}
}
}

33
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump_whole/schema/relation_schema.json
Unescape Escape View File

@ -6,11 +6,11 @@
"properties": {
"id": {
"type": "string",
"description": "Description of id"
"description": "The OpenAIRE id of the entity"
},
"type": {
"type": "string",
"description": "Description of type"
"description": "The type of the entity (i.e. organisation)"
}
}
}
@ -22,47 +22,38 @@
"properties": {
"provenance": {
"type": "string",
"description": "Description of provenance"
"description": "The reason why OpenAIRE holds the relation "
},
"trust": {
"type": "string",
"description": "Description of trust"
"description": "The trust of the relation"
}
},
"description": "Description of provenance"
}
},
"reltype": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Description of name"
"description": "the semantics of the relation (i.e. isAuthorInstitutionOf)"
},
"type": {
"type": "string",
"description": "Description of type"
"description": "the type of the relation (i.e. affiliation)"
}
},
"description": "Description of reltype"
"description": "To represent the semantics of the generic relation between two entities"
},
"source": {
"allOf": [
{
"$ref": "#/definitions/Node"
},
{
"description": "Description of source"
}
{"$ref": "#/definitions/Node"},
{"description": "The node source in the relation"}
]
},
"target": {
"allOf": [
{
"$ref": "#/definitions/Node"
},
{
"description": "Description of target"
}
{"$ref": "#/definitions/Node"},
{"description": "The node target in the relation"}
]
}
}

380
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump_whole/schema/result_schema.json
Unescape Escape View File

@ -1,207 +1,152 @@
{
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"AccessRight": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "Description of code"
},
"label": {
"type": "string",
"description": "Description of label"
},
"scheme": {
"type": "string",
"description": "Description of scheme"
}
}
},
"ControlledField": {
"type": "object",
"properties": {
"scheme": {
"type": "string",
"description": "Description of scheme"
"type": "string"
},
"value": {
"type": "string",
"description": "Description of value"
"type": "string"
}
}
},
"KeyValue": {
"type": "object",
"properties": {
"key": {
"type": "string",
"description": "Description of key"
},
"value": {
"type": "string",
"description": "Description of value"
}
}
},
"description": "To represent the information described by a scheme and a value in that scheme (i.e. pid)"
},
"Provenance": {
"type": "object",
"properties": {
"provenance": {
"type": "string",
"description": "Description of provenance"
"description": "The process that produced/provided the information"
},
"trust": {
"type": "string",
"description": "Description of trust"
"type": "string"
}
}
},
"description": "Indicates the process that produced (or provided) the information, and the trust associated to the information"
}
},
"type": "object",
"properties": {
"author": {
"description": "Description of author",
"type": "array",
"items": {
"type": "object",
"properties": {
"affiliation": {
"description": "Description of affiliation",
"type": "array",
"items": {
"type": "string",
"description": "Description of affiliation"
}
},
"fullname": {
"type": "string",
"description": "Description of fullname"
"type": "string"
},
"name": {
"type": "string",
"description": "Description of name"
"type": "string"
},
"pid": {
"type": "object",
"properties": {
"id": {
"allOf": [
{
"$ref": "#/definitions/ControlledField"
},
{
"description": "Description of id"
}
{"$ref": "#/definitions/ControlledField"},
{"description": "The author's id and scheme. OpenAIRE currently supports 'ORCID'"}
]
},
"provenance": {
"allOf": [
{
"$ref": "#/definitions/Provenance"
},
{
"description": "Description of provenance"
}
{"$ref": "#/definitions/Provenance"},
{"description": "Provenance of author's pid"}
]
}
},
"description": "Description of pid"
}
},
"rank": {
"type": "integer",
"description": "Description of rank"
"type": "integer"
},
"surname": {
"type": "string",
"description": "Description of surname"
"type": "string"
}
},
"description": "Description of author"
}
}
},
"bestaccessright": {
"allOf": [
{
"$ref": "#/definitions/AccessRight"
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "COAR access mode code: http://vocabularies.coar-repositories.org/documentation/access_rights/"
},
"label": {
"type": "string",
"description": "Label for the access mode"
},
{
"description": "Description of bestaccessright"
"scheme": {
"type": "string",
"description": "Scheme of reference for access right code. Always set to COAR access rights vocabulary: http://vocabularies.coar-repositories.org/documentation/access_rights/"
}
]
},
"description": "The openest access right associated to the manifestations of this research results"
},
"codeRepositoryUrl": {
"type": "string",
"description": "Description of codeRepositoryUrl"
"description": "Only for results with type 'software': the URL to the repository with the source code"
},
"contactgroup": {
"description": "Description of contactgroup",
"description": "Only for results with type 'software': Information on the group responsible for providing further information regarding the resource",
"type": "array",
"items": {
"type": "string",
"description": "Description of contactgroup"
"type": "string"
}
},
"contactperson": {
"description": "Description of contactperson",
"description": "Only for results with type 'software': Information on the person responsible for providing further information regarding the resource",
"type": "array",
"items": {
"type": "string",
"description": "Description of contactperson"
"type": "string"
}
},
"container": {
"type": "object",
"properties": {
"conferencedate": {
"type": "string",
"description": "Description of conferencedate"
"type": "string"
},
"conferenceplace": {
"type": "string",
"description": "Description of conferenceplace"
"type": "string"
},
"edition": {
"type": "string",
"description": "Description of edition"
"description": "Edition of the journal or conference proceeding"
},
"ep": {
"type": "string",
"description": "Description of ep"
"description": "End page"
},
"iss": {
"type": "string",
"description": "Description of iss"
"description": "Journal issue"
},
"issnLinking": {
"type": "string",
"description": "Description of issnLinking"
"type": "string"
},
"issnOnline": {
"type": "string",
"description": "Description of issnOnline"
"type": "string"
},
"issnPrinted": {
"type": "string",
"description": "Description of issnPrinted"
"type": "string"
},
"name": {
"type": "string",
"description": "Description of name"
"description": "Name of the journal or conference"
},
"sp": {
"type": "string",
"description": "Description of sp"
"description": "start page"
},
"vol": {
"type": "string",
"description": "Description of vol"
"type": "string"
}
},
"description": "Description of container"
"description": "Container has information about the conference or journal where the result has been presented or published"
},
"contributor": {
"description": "Description of contributor",
"type": "array",
"items": {
"type": "string",
@ -209,312 +154,177 @@
}
},
"country": {
"description": "Description of country",
"type": "array",
"items": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "Description of code"
"description": "ISO 3166-1 alpha-2 country code"
},
"label": {
"type": "string",
"description": "Description of label"
"type": "string"
},
"provenance": {
"allOf": [
{
"$ref": "#/definitions/Provenance"
},
{
"description": "Description of provenance"
}
{"$ref": "#/definitions/Provenance"},
{"description": "Why this result is associated to the country."}
]
}
},
"description": "Description of country"
}
}
},
"coverage": {
"description": "Description of coverage",
"type": "array",
"items": {
"type": "string",
"description": "Description of coverage"
"type": "string"
}
},
"dateofcollection": {
"type": "string",
"description": "Description of dateofcollection"
"description": "When OpenAIRE collected the record the last time"
},
"description": {
"description": "Description of description",
"type": "array",
"items": {
"type": "string",
"description": "Description of description"
"type": "string"
}
},
"documentationUrl": {
"description": "Description of documentationUrl",
"description": "Only for results with type 'software': URL to the software documentation",
"type": "array",
"items": {
"type": "string",
"description": "Description of documentationUrl"
"type": "string"
}
},
"embargoenddate": {
"type": "string",
"description": "Description of embargoenddate"
},
"externalReference": {
"description": "Description of externalReference",
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Description of name"
},
"provenance": {
"allOf": [
{
"$ref": "#/definitions/Provenance"
},
{
"description": "Description of provenance"
}
]
},
"typology": {
"type": "string",
"description": "Description of typology"
},
"value": {
"type": "string",
"description": "Description of value"
}
},
"description": "Description of externalReference"
}
"description": "Date when the embargo ends and this result turns Open Access"
},
"format": {
"description": "Description of format",
"type": "array",
"items": {
"type": "string",
"description": "Description of format"
"type": "string"
}
},
"geolocation": {
"description": "Description of geolocation",
"description": "Geolocation information",
"type": "array",
"items": {
"type": "object",
"properties": {
"box": {
"type": "string",
"description": "Description of box"
"type": "string"
},
"place": {
"type": "string",
"description": "Description of place"
"type": "string"
},
"point": {
"type": "string",
"description": "Description of point"
"type": "string"
}
},
"description": "Description of geolocation"
}
}
},
"id": {
"type": "string",
"description": "Description of id"
},
"instance": {
"description": "Description of instance",
"type": "array",
"items": {
"type": "object",
"properties": {
"accessright": {
"allOf": [
{
"$ref": "#/definitions/AccessRight"
},
{
"description": "Description of accessright"
}
]
},
"collectedfrom": {
"allOf": [
{
"$ref": "#/definitions/KeyValue"
},
{
"description": "Description of collectedfrom"
}
]
},
"hostedby": {
"allOf": [
{
"$ref": "#/definitions/KeyValue"
},
{
"description": "Description of hostedby"
}
]
},
"license": {
"type": "string",
"description": "Description of license"
},
"publicationdate": {
"type": "string",
"description": "Description of publicationdate"
},
"refereed": {
"type": "string",
"description": "Description of refereed"
},
"type": {
"type": "string",
"description": "Description of type"
},
"url": {
"description": "Description of url",
"type": "array",
"items": {
"type": "string",
"description": "Description of url"
}
}
},
"description": "Description of instance"
}
"description": "OpenAIRE Identifier"
},
"language": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "Description of code"
"description": "alpha-3/ISO 639-2 code of the language"
},
"label": {
"type": "string",
"description": "Description of label"
"description": "English label"
}
},
"description": "Description of language"
}
},
"lastupdatetimestamp": {
"type": "integer",
"description": "Description of lastupdatetimestamp"
"description": "Timestamp of last update of the record in OpenAIRE"
},
"maintitle": {
"type": "string",
"description": "Description of maintitle"
"type": "string"
},
"originalId": {
"description": "Description of originalId",
"description": "Identifiers of the record at the original sources",
"type": "array",
"items": {
"type": "string",
"description": "Description of originalId"
"type": "string"
}
},
"pid": {
"description": "Description of pid",
"description": "Persistent identifiers of the result",
"type": "array",
"items": {
"allOf": [
{
"$ref": "#/definitions/ControlledField"
},
{
"description": "Description of pid"
}
{"$ref": "#/definitions/ControlledField"},
{"description": "scheme: list of available schemes are at https://api.openaire.eu/vocabularies/dnet:pid_types, value: the PID of the result "}
]
}
},
"programmingLanguage": {
"type": "string",
"description": "Description of programmingLanguage"
"description": "Only for results with type 'software': the programming language"
},
"publicationdate": {
"type": "string",
"description": "Description of publicationdate"
"type": "string"
},
"publisher": {
"type": "string",
"description": "Description of publisher"
"type": "string"
},
"size": {
"type": "string",
"description": "Description of size"
"description": "Only for results with type 'dataset': the declared size of the dataset"
},
"source": {
"description": "Description of source",
"description": "See definition of Dublin Core field dc:source",
"type": "array",
"items": {
"type": "string",
"description": "Description of source"
"type": "string"
}
},
"subjects": {
"description": "Description of subjects",
"description": "Keywords associated to the result",
"type": "array",
"items": {
"type": "object",
"properties": {
"provenance": {
"allOf": [
{
"$ref": "#/definitions/Provenance"
},
{
"description": "Description of provenance"
}
{"$ref": "#/definitions/Provenance"},
{"description": "Why this subject is associated to the result"}
]
},
"subject": {
"allOf": [
{
"$ref": "#/definitions/ControlledField"
},
{
"description": "Description of subject"
}
{"$ref": "#/definitions/ControlledField"},
{"description": "OpenAIRE subject classification scheme (https://api.openaire.eu/vocabularies/dnet:subject_classification_typologies) and value. When the scheme is 'keyword', it means that the subject is free-text (i.e. not a term from a controlled vocabulary)."},
]
}
},
"description": "Description of subjects"
}
}
},
"subtitle": {
"type": "string",
"description": "Description of subtitle"
"type": "string"
},
"tool": {
"description": "Description of tool",
"description": "Only for results with type 'other': tool useful for the interpretation and/or re-used of the research product",
"type": "array",
"items": {
"type": "string",
"description": "Description of tool"
"type": "string"
}
},
"type": {
"type": "string",
"description": "Description of type"
"description": "Type of the result: one of 'publication', 'dataset', 'software', 'other' (see also https://api.openaire.eu/vocabularies/dnet:result_typologies)"
},
"version": {
"type": "string",
"description": "Description of version"
"description": "Version of the result"
}
}
}
}

Write Preview
Loading…
Cancel
Save