{
    "version":"0.1.0",
    "id":"match-data",
    "use_case":"BOKU",
    "title":"Combine and match biodiversity data from separate sources",
    "description":"This process combines and matches biodiveryity data, i.e. occurrences for various species, from the sources GBIF, iNaturalist and VertNet, with data provided by the user or other sources. For more details, please ask BOKU.",
    "jobControlOptions":[
        "sync-execute",
        "async-execute"
    ],
    "keywords":[
        "pan-european use case",
        "AquaINFRA",
        "R"
    ],
    "links":[
        {
            "type":"text/html",
            "rel":"about",
            "title":"GitHub repo",
            "href":"https://github.com/AnthonyBasooma/specleanr",
            "hreflang":"en-US"
        },
        {
            "type":"application/json",
            "rel":"self",
            "href":"https://aquainfra.ogc.igb-berlin.de/pygeoapi/processes/match-data?f=json",
            "title":"Process description as JSON",
            "hreflang":"en-US"
        },
        {
            "type":"text/html",
            "rel":"alternate",
            "href":"https://aquainfra.ogc.igb-berlin.de/pygeoapi/processes/match-data?f=html",
            "title":"Process description as HTML",
            "hreflang":"en-US"
        },
        {
            "type":"text/html",
            "rel":"http://www.opengis.net/def/rel/ogc/1.0/job-list",
            "href":"https://aquainfra.ogc.igb-berlin.de/pygeoapi/jobs?f=html",
            "title":"Jobs list as HTML",
            "hreflang":"en-US"
        },
        {
            "type":"application/json",
            "rel":"http://www.opengis.net/def/rel/ogc/1.0/job-list",
            "href":"https://aquainfra.ogc.igb-berlin.de/pygeoapi/jobs?f=json",
            "title":"Jobs list as JSON",
            "hreflang":"en-US"
        },
        {
            "type":"application/json",
            "rel":"http://www.opengis.net/def/rel/ogc/1.0/execute",
            "href":"https://aquainfra.ogc.igb-berlin.de/pygeoapi/processes/match-data/execution?f=json",
            "title":"Execution for this process as JSON",
            "hreflang":"en-US"
        }
    ],
    "inputs":{
        "input_datasets":{
            "title":"Occurrence data (GBIF, iNaturalist, VertNet, or from any other source)",
            "description":"URL to CSV tables containing the occurrences from GBIF, iNaturalist and VertNet. This can be the outcome of the retrieve-biodiversity-data process.",
            "schema":{
                "type":"string"
            },
            "minOccurs":1,
            "maxOccurs":1,
            "keywords":[
                "csv"
            ]
        },
        "colnames_species_names":{
            "title":"Column names including species names",
            "description":"List of column names that indicate the Species Name in each of the provided datasets. Example: \"speciesname, scientificName\"",
            "schema":{
                "type":"array"
            },
            "minOccurs":1,
            "maxOccurs":1,
            "keywords":[]
        },
        "colnames_countries":{
            "title":"Column names including country",
            "description":"List of column names that indicate the Country in each of the provided datasets. Example: \"JDS4_sampling_ID\"",
            "schema":{
                "type":"array"
            },
            "minOccurs":1,
            "maxOccurs":1,
            "keywords":[]
        },
        "colnames_lat":{
            "title":"Column names including Latitude",
            "description":"List of column names that indicate the Latitude in each of the provided datasets. Example: \"lat, latitude\"",
            "schema":{
                "type":"array"
            },
            "minOccurs":1,
            "maxOccurs":1,
            "keywords":[]
        },
        "colnames_lon":{
            "title":"Column names including Longitude",
            "description":"List of column names that indicate the Longitude in each of the provided datasets. Example: \"lon, long, longitude\"",
            "schema":{
                "type":"array"
            },
            "minOccurs":1,
            "maxOccurs":1,
            "keywords":[]
        },
        "colnames_date":{
            "title":"Column names including Dates",
            "description":"List of column names that indicate the dates in each of the provided datasets. Example: \"Date, sampling_date\"",
            "schema":{
                "type":"array"
            },
            "minOccurs":1,
            "maxOccurs":1,
            "keywords":[]
        }
    },
    "outputs":{
        "matched_biodiversity_data":{
            "title":"Combined occurrences",
            "description":"A table containing the combined occurrences (user data and online data).",
            "schema":{
                "type":"object",
                "contentMediaType":"application/json"
            }
        }
    },
    "example":{
        "inputs":{
            "input_datasets":[
                "https://localhost/download/out/biodiv-data.csv",
                "https://localhost/referencedata/specleanr/efidata.csv"
            ],
            "colnames_species_names":[
                "speciesname",
                "scientificName"
            ],
            "colnames_countries":[
                "JDS4_sampling_ID"
            ],
            "colnames_lat":[
                "lat",
                "latitude"
            ],
            "colnames_lon":[
                "lon",
                "long",
                "longitude"
            ],
            "colnames_date":[
                "Date",
                "sampling_date"
            ]
        }
    },
    "outputTransmission":[
        "value"
    ]
}