######################################################################### # # This indexMapping file contains a set of key/value mappings that map for each # term that we're interested in harvesting, the POJO attributes name # (used during synchronisation and as the column header in the outputted harvested.txt file) # to their corresponding DwC (revision 2009-09-23) term URI's label. # # This file is used to sweep over the DwC-Archive's core file picking # out only those columns that are actually of interest. # # In theory the list of DwC terms will not change following DwC's ratification. # Nonetheless, we still have to support those DwC term URIs that were used # (for example by the Integrated Publishing Toolkit (IPT)) prior to ratification. # # Important note #1: the construction of the key follows a set of rules # outlined here: # # 1. The key is derived from the POJO attribute name # 2. The key can have a numbered extension (i.e. '.1', '.2', etc), that # designates its priority with 1 being the most important. # # For example: latitude.1=decimalLatitude # latitude.2=verbatimLatitude # # Here, 'latitude' is the POJO attribute name we use. Furthermore, # should values be harvested for both decimalLatitude and verbatimLatitude, # decimalLatitude takes precedence. Therefore, during synchronisation with # the database it is the decimalLatitude value that is used. # # Important note #2: The value is derived from the last part of the DwC term URI, # otherwise known as the term label. # # For example: The URI for verbatimLatitude is: # # http://rs.tdwg.org/dwc/terms/verbatimLatitude # # and as the term label, which becomes the value, is verbatimLatitude # ######################################################################### #DATE.LAST.MODIFIED # The most recent date-time on which the resource was changed. For Darwin Core, recommended best practice is to use an encoding scheme, such as ISO 8601:2004(E). dateLastModified=modified ############################################# #relating to raw_occurrence_record table ############################################# #INSTITUTION.CODE institutionCode=institutionCode #COLLECTION.CODE collectionCode.1=collectionCode collectionCode.2=collectionID collectionCode.3=datasetID # For backwards compatibility - no longer in DwC collectionCode.4=sourceID #CATALOGUE.NUMBER catalogueNumber.1=catalogNumber catalogueNumber.2=occurrenceID #TAXONOMY scientificName=scientificName author=scientificNameAuthorship kingdom=kingdom phylum=phylum klass=class order=order family=family genus=genus species=specificEpithet subspecies=infraspecificEpithet rank=taxonRank #GEOSPATIAL latitude.1=decimalLatitude latitude.2=verbatimLatitude longitude.1=decimalLongitude longitude.2=verbatimLongitude latLongPrecision.1=coordinateUncertaintyInMeters latLongPrecision.2=coordinatePrecision minAltitude=minimumElevationInMeters maxAltitude=maximumElevationInMeters minDepth=minimumDepthInMeters maxDepth=maximumDepthInMeters continentOrOcean.1=continent continentOrOcean.2=waterBody country.1=countryCode country.2=country stateOrProvince=stateProvince county=county locality.1=locality locality.2=verbatimLocality #COLLECTOR collectorName.1=recordedBy # For backwards compatibility - no longer in DwC collectorName.2=collector #IDENTIFIER identifierName=identifiedBy #TEMPORAL dateCollected.1=eventDate # The collection date can also come in individual parts year=year month=month day=day # For backwards compatibility - no longer in DwC dateCollected.2=earliestDateCollected dateCollected.3=latestDateCollected #IDENTIFICATION dateIdentified=dateIdentified #BASIS.OF.RECORD basisOfRecord=basisOfRecord ############################################# #relating to identifier_record table ############################################# # An identifier given to the event in the field. Often serves as a link between field notes and the Event. identifierType2=fieldNumber # might be a GUID but it is always a SOURCE_ID. Since 99% of the time the id index = occurrenceID, this is commented out # To ensure the Source ID is always written, the id index is written to the harvested.txt file with name identifierType7 # identifierType7=occurrenceID # A list (concatenated and separated) of sequence identifiers, like GenBank IDs identifierType5=associatedSequences # A list (concatenated and separated) of previous or alternate fully qualified catalog numbers identifierType6=otherCatalogNumbers # For backwards compatibility - no longer in DwC identifierType3=collectorNumber ############################################# #relating to typification_record table ############################################# typification=typeStatus ############################################# #relating to image_record table ############################################# # A list (concatenated and separated) of identifiers (publication, global unique identifier, URI) of media associated # with the Occurrence. In the Portal, it maps to image_record.type=0 (IMAGETYPE_UNKNOWN) imageType0=associatedMedia ############################################# #relating to link_record table ############################################# # A list (concatenated and separated) of identifiers (publication, bibliographic reference, global unique identifier, URI) # of literature associated with the Occurrence. The Portal doesn't have a link record type 2, and gets converted to 1 # during synchronization. Due to a bug in the Data Portal, only type 1 gets displayed anyway at the moment. linkType2=associatedReferences # A related resource that is referenced, cited, or otherwise pointed to by the described resource. We interpret this # as representing an occurrence page referring to the occurrence record. linkType1=references # For backwards compatibility - no longer in DwC linkType0=source