gFeed/gCat-Controller/src/test/resources/org/gcube/data/publishing/gCatFeeder/catalogues/gCat/full-algorithm.json

{
    "item": {
        "author": "Gianpaolo Coro",
        "extras": [
            {
                "key": "system:type",
                "value": "Method"
            },
            {
                "key": "TechnicalDetails:input",
                "value": "FeaturesColumnNames [COLUMN_LIST]  : column Names for the features [a sequence of names of columns from OccurrencePointsTable separated by | ]"
            },
            {
                "key": "TechnicalDetails:input",
                "value": "maxIterations [OBJECT]  : XMeans max number of overall iterations of the clustering learning"
            },
            {
                "key": "TechnicalDetails:input",
                "value": "minClusters [OBJECT]  : minimum number of expected clusters"
            },
            {
                "key": "TechnicalDetails:input",
                "value": "maxClusters [OBJECT]  : maximum number of clusters to produce"
            },
            {
                "key": "TechnicalDetails:input",
                "value": "OccurrencePointsClusterLabel [OBJECT]  : table name of the resulting distribution"
            },
            {
                "key": "TechnicalDetails:input",
                "value": "OccurrencePointsTable [TABULAR] default :   : Occurrence Points Table. Max 4000 points [a http link to a table in UTF-8 encoding following this template: (GENERIC) A generic comma separated csv file in UTF-8 encoding]"
            },
            {
                "key": "TechnicalDetails:input",
                "value": "min_points [OBJECT]  : number of points which define an outlier set"
            },
            {
                "key": "TechnicalDetails:output",
                "value": "non_deterministic_output [FILE]  : NonDeterministicOutput"
            },
            {
                "key": "TechnicalDetails:output",
                "value": "OutputTable [TABULAR] default :   : Output cluster table [a http link to a table in UTF-8 ecoding following this template: (CLUSTER) http://goo.gl/PnKhhb]"
            },
            {
                "key": "Identity:Creator",
                "value": "Coro, Gianpaolo"
            },
            {
                "key": "Identity:CreationDate",
                "value": "1900-01-01"
            },
            {
                "key": "AccessMode:UsageMode",
                "value": "as-a-Service via Blue-Cloud Infrastructure"
            },
            {
                "key": "AccessMode:Availability",
                "value": "On-Line"
            },
            {
                "key": "TechnicalDetails:Hosting Environment",
                "value": "gCube SmartGear"
            },
            {
                "key": "TechnicalDetails:Dependencies on Other SW",
                "value": "gCube DataMiner"
            },
            {
                "key": "Rights:Field/Scope of use",
                "value": "Any use"
            },
            {
                "key": "Rights:Basic rights",
                "value": "Communication"
            },
            {
                "key": "Rights:Basic rights",
                "value": "Making available to the public"
            },
            {
                "key": "Rights:Basic rights",
                "value": "Distribution"
            },
            {
                "key": "Attribution:Attribution requirements",
                "value": "Cite as: Coro, Gianpaolo (2021): Xmeans. n.d.. Blue-Cloud. DataMiner Process. https://data.dev.d4science.org/ctlg/devVRE/xmeans_in_devvre. Retrieved from the DEVGateway (https://next.d4science.org/group/devvre/dataminer?OperatorId=org.gcube.dataanalysis.wps.statisticalmanager.synchserver.mappedclasses.clusterers.XMEANS) operated by D4Science.org www.d4science.org"
            }
        ],
        "license_id": "CC-BY-NC-SA-4.0",
        "maintainer": "Gianpaolo Coro",
        "name": "xmeans_in_devvre",
        "notes": "A clustering algorithm for occurrence points that relies on the X-Means algorithm, i.e. an extended version of the K-Means algorithm improved by an Improve-Structure part. A Maximum of 4000 points is allowed.",
        "private": false,
        "tags": [
            {
                "name": "Data Clustering"
            },
            {
                "name": "devVRE"
            },
            {
                "name": "WPS"
            },
            {
                "name": "Analytics"
            }
        ],
        "title": "Xmeans in devVRE",
        "version": null
    },
    "profile": "<metadataformat type=\"Method\">\n\t<metadatafield categoryref=\"Identity\">\n\t\t<fieldName>External Identifier</fieldName>\n\t\t<mandatory>false</mandatory>\n\t\t<dataType>String</dataType>\n\t\t<maxOccurs>*</maxOccurs>\n\t\t<note>This applies only to methods that have been already published. Insert here a DOI, an handle, and any other Identifier assigned when publishing the dataset alsewhere.</note>\n\t</metadatafield>\n\t<metadatafield categoryref=\"Identity\">\n\t\t<fieldName>Creator</fieldName>\n\t\t<mandatory>true</mandatory>\n\t\t<dataType>String</dataType>\n\t\t<maxOccurs>*</maxOccurs>\n\t\t<note>The name of the creator, with email and ORCID. The format should be: family, given[, email][, ORCID]. Example: Smith, John, js@acme.org, orcid.org/0000-0002-1825-0097</note>\n\t\t<validator>\n\t\t\t<regularExpression>^[a-zA-ZÀ-ÿ .'-]+, [a-zA-ZÀ-ÿ .'-]+[, ]*([a-zA-Z0-9_!#$%’*+=?`{|}~^.-]+@[a-zA-Z0-9À-ÿ.-]+)?[, ]*(orcid.org\\/0000-000(1-[5-9]|2-[0-9]|3-[0-4])\\d\\d\\d-\\d\\d\\d[\\dX])?$</regularExpression>\n\t\t</validator>\n\t</metadatafield>\n\t<metadatafield categoryref=\"Identity\">\n\t\t<fieldName>CreationDate</fieldName>\n\t\t<mandatory>true</mandatory>\n\t\t<dataType>Time</dataType>\n\t\t<maxOccurs>1</maxOccurs>\n\t\t<note>The date of creation of the dataset (different from the date of registration of the dataset automatically added by the system). Use ISO 8601 Date Format: YYYY-MM-DD[ HH:MM] Ex. 1998-11-10 or 2015-05-29 11:55</note>\n\t\t<validator>\n\t\t\t<regularExpression>^(\\d{4}\\-(0?[1-9]|1[012])\\-(0?[1-9]|[12][0-9]|3[01]))+([ ]+(\\d{2}(:?\\d{2})?)?)?$</regularExpression>\n\t\t</validator>\n\t</metadatafield>\n\t<metadatafield categoryref=\"Identity\">\n\t\t<fieldName>Owner</fieldName>\n\t\t<mandatory>false</mandatory>\n\t\t<dataType>String</dataType>\n\t\t<maxOccurs>*</maxOccurs>\n\t\t<note>The owner of the method (free text).</note>\n\t</metadatafield>\n\t<metadatafield categoryref=\"Identity\">\n\t\t<fieldName>RelatedPaper</fieldName>\n\t\t<mandatory>false</mandatory>\n\t\t<dataType>String</dataType>\n\t\t<maxOccurs>1</maxOccurs>\n\t\t<note>Insert a complete reference to an associated work.</note>\n\t</metadatafield>\n\t<metadatafield categoryref=\"Coverage\">\n\t\t<fieldName>Semantic Coverage</fieldName>\n\t\t<mandatory>false</mandatory>\n\t\t<dataType>String</dataType>\n\t\t<maxOccurs>*</maxOccurs>\n\t\t<note>Tagging e.g. Functional analysis, Environment analysis and visualisation, ...</note>\n\t</metadatafield>\n\t<metadatafield categoryref=\"AccessMode\">\n\t\t<fieldName>UsageMode</fieldName>\n\t\t<mandatory>true</mandatory>\n\t\t<dataType>String</dataType>\n\t\t<maxOccurs>1</maxOccurs>\n\t\t<note>How the method is expected to be exploited.</note>\n\t\t<vocabulary isMultiSelection=\"true\">\n\t\t\t<vocabularyField>Download</vocabularyField>\n\t\t\t<vocabularyField>as-a-Application via Blue-Cloud Infrastructure</vocabularyField>\n\t\t\t<vocabularyField>as-a-Application via third-party Infrastructure</vocabularyField>\n\t\t\t<vocabularyField>as-a-Service via Blue-Cloud Infrastructure</vocabularyField>\n\t\t\t<vocabularyField>as-a-Service via third-party Infrastructure</vocabularyField>\n\t\t</vocabulary>\n\t</metadatafield>\n\t<metadatafield categoryref=\"AccessMode\">\n\t\t<fieldName>Availability</fieldName>\n\t\t<mandatory>false</mandatory>\n\t\t<dataType>String</dataType>\n\t\t<maxOccurs>1</maxOccurs>\n\t\t<note>How the availability to the resource is offered. On-line means that the method can be executed through the Virtual Laboratory Gateway. On-site means that the method can only be executed by visiting the hosting provider.</note>\n\t\t<vocabulary>\n\t\t\t<vocabularyField>On-Line</vocabularyField>\n\t\t\t<vocabularyField>On-Site</vocabularyField>\n\t\t</vocabulary>\n\t</metadatafield>\n\t<metadatafield categoryref=\"TechnicalDetails\">\n\t\t<fieldName>Hosting Environment</fieldName>\n\t\t<mandatory>false</mandatory>\n\t\t<dataType>String</dataType>\n\t\t<maxOccurs>1</maxOccurs>\n\t\t<note>E.g. Linux, Microsoft Azure, Amazon EC2</note>\n\t</metadatafield>\n\t<metadatafiel
    "profileID": "Method",
    "resources": [
        {
            "description": "Link to the GUI designed to operate with DataMiner",
            "format": "https",
            "name": "Gateway Link",
            "url": "https://next.d4science.org/group/devvre/dataminer?OperatorId=org.gcube.dataanalysis.wps.statisticalmanager.synchserver.mappedclasses.clusterers.XMEANS"
        },
        {
            "description": "WPS Link to the Method",
            "format": "WPS",
            "name": "WPS Link",
            "url": "https://dataminer1.dev.d4science.org:443/wps/WebProcessingService?Request=DescribeProcess&Version=1.0.0&Service=WPS&Identifier=org.gcube.dataanalysis.wps.statisticalmanager.synchserver.mappedclasses.clusterers.XMEANS"
        }
    ]
}