#! /usr/bin/env guile
!#

(use-modules (srfi srfi-1)
             (srfi srfi-26)
             (ice-9 getopt-long)
             (ice-9 match)
             (ice-9 regex)
             (transform strings)
             (transform sql)
             (transform triples)
             (transform special-forms))



;; Classification Scheme
(define-transformer gnc:species->gn:species
  (tables (Species)
          "WHERE Name != 'monkey'")
  (triples "gnc:species"
    (set skos:member
         (string->identifier "" (remap-species-identifiers (field Species Fullname))))))

(define-transformer gnc:set->gn:set
  (tables (InbredSet)
          "WHERE public > 0 AND FullName NOT LIKE '%monkey%'")
  (triples "gnc:set"
    (set skos:member
         (string->identifier
          "set" (field InbredSet Name InbredSetName) #:separator "_"))))

(define-transformer gnc:species->metadata
  (tables (Species)
          "WHERE Name != 'monkey'")
  (triples
      (string->identifier "" (remap-species-identifiers (field Species Fullname)))
    (set rdf:type 'gnc:species)
    (set rdfs:label (remap-species-identifiers (field Species Fullname)))
    (set skos:prefLabel (field Species MenuName))
    (set skos:altLabel (field Species SpeciesName))
    (set gnt:short_name (field Species Name))
    (set gnt:has_taxonomic_family (string->identifier "family" (field Species Family) #:separator "_"))
    (set gnt:has_uniprot_taxon_id (ontology
                                   'taxon:
                                   (field Species TaxonomyId)))))

(define-transformer gnc:species->gn:set
  (tables (InbredSet
           (left-join Species "ON InbredSet.SpeciesId=Species.Id"))
          "WHERE public > 0 AND Species.Name != 'monkey'")
  (triples (string->identifier "" (remap-species-identifiers (field Species Fullname)))
    (set gnt:has_strain
         (string->identifier "set" (field InbredSet Name InbredSetName) #:separator "_"))))

(define-transformer gn:family->gn:species/metadata
  (tables (Species)
          "WHERE Name != 'monkey' GROUP BY FAMILY")
  (triples (string->identifier "family" (field Species Family) #:separator "_")
    (set gnt:has_species
         (string->identifier "" (remap-species-identifiers (field Species Fullname))))
    (set rdfs:label (field Species Family))
    (set gnt:has_family_order_id
         (annotate-field (field Species OrderId)
                         '^^xsd:integer))))

(define-transformer gn:family->gn:species
  (tables (Species)
          "WHERE Name != 'monkey'")
  (triples (string->identifier "family" (field Species Family) #:separator "_")
    (set gnt:has_species
         (string->identifier "" (remap-species-identifiers (field Species Fullname))))))


(define-transformer gn:set->metadata
  (tables (InbredSet
           (left-join Species "ON InbredSet.SpeciesId=Species.Id")
           (left-join MappingMethod
                      "ON InbredSet.MappingMethodId=MappingMethod.Id"))
          "WHERE public > 0 AND Species.Name != 'monkey'")
  (triples (string->identifier "set" (field InbredSet Name InbredSetName) #:separator "_")
    (set rdf:type 'gnc:set)
    (set rdfs:label (field InbredSet FullName))
    (set skos:prefLabel (field InbredSet Name InbredSetName))
    (set gnt:genetic_type (field InbredSet GeneticType))
    (set dct:description (annotate-field (sanitize-rdf-string (field InbredSet description))
                                         '^^rdf:HTML))
    (set gnt:uses_mapping_method
         (string->identifier "mapping_method" (field MappingMethod Name) #:separator "_"))
    (set gnt:has_set_code (field InbredSet InbredSetCode))
    (set gnt:has_species
         (string->identifier "" (remap-species-identifiers (field Species Fullname))))))

(define-transformer gn:set->gn:population
  (tables (InbredSet)
          "WHERE Family IS NOT NULL AND FullName NOT LIKE '%monkey%'")
  (schema-triples
   (gnt:has_reference_population rdfs:domain gnc:set)
   (gnt:has_reference_population a owl:ObjectProperty)
   (gnt:has_reference_population rdfs:comment "This group belongs to this population category.")
   (gnt:has_reference_population rdfs:label "belongs to population category."))
  (triples (string->identifier "set" (field InbredSet Name InbredSetName) #:separator "_")
    (set gnt:has_reference_population
         (string->identifier "population" (field InbredSet Family) #:separator "_"))))

(define-transformer gn:population->metadata
  (tables (InbredSet)
          "WHERE Family IS NOT NULL AND FullName NOT LIKE '%monkey%' GROUP BY Family")
  (triples (string->identifier "population" (field InbredSet Family) #:separator "_")
    (set rdf:type 'gnc:reference_population)
    (set rdfs:label (field InbredSet Family))
    (set skos:member 'gnc:population_category)
    (set gnt:has_population_order_id
         (annotate-field (field InbredSet FamilyOrder)
                         '^^xsd:integer))))

(define-transformer gn:population->gn:set
  (tables (InbredSet)
          "WHERE Family IS NOT NULL AND FullName NOT LIKE '%monkey%'")
  (triples (string->identifier "population" (field InbredSet Family) #:separator "_")
    (set gnt:has_strain
         (string->identifier "set" (field InbredSet Name InbredSetName) #:separator "_"))))

(define-transformer gnc:population_category->gn:population
  (tables (InbredSet)
          "WHERE public > 0 AND FullName NOT LIKE '%monkey%' GROUP BY Family")
  (triples "gnc:population_category"
    (set gnt:has_reference_population
         (string->identifier "population" (field InbredSet Family) #:separator "_"))))

(define-transformer gnc:taxonomic_family->gn:family
  (tables (Species)
          "WHERE Name != 'monkey' GROUP BY Family")
  (triples "gnc:taxonomic_family"
    (set gnt:has_taxonomic_family
         (string->identifier "family" (field Species Family) #:separator "_"))))



(let* ((option-spec
        '((settings (single-char #\s) (value #t))
          (output (single-char #\o) (value #t))
          (documentation (single-char #\d) (value #t))))
       (options (getopt-long (command-line) option-spec))
       (settings (option-ref options 'settings #f))
       (output (option-ref options 'output #f))
       (documentation (option-ref options 'documentation #f))
       (%connection-settings
        (call-with-input-file settings
          read)))

  (with-documentation
   (name "GN Classification Hierarchy")
   (connection %connection-settings)
   (table-metadata? #f)
   (prefixes
    '(("dcat:" "<http://www.w3.org/ns/dcat#>")
      ("dct:" "<http://purl.org/dc/terms/>")
      ("gn:" "<http://rdf.genenetwork.org/v1/id/>")
      ("gnc:" "<http://rdf.genenetwork.org/v1/category/>")
      ("owl:" "<http://www.w3.org/2002/07/owl#>")
      ("gnt:" "<http://rdf.genenetwork.org/v1/term/>")
      ("schema:" "<https://schema.org/>")
      ("skos:" "<http://www.w3.org/2004/02/skos/core#>")
      ("xkos:" "<http://rdf-vocabulary.ddialliance.org/xkos#>")
      ("xsd:" "<http://www.w3.org/2001/XMLSchema#>")
      ("rdf:" "<http://www.w3.org/1999/02/22-rdf-syntax-ns#>")
      ("rdfs:" "<http://www.w3.org/2000/01/rdf-schema#>")
      ("taxon:" "<http://purl.uniprot.org/taxonomy/>")))
   (inputs
    (list gnc:species->gn:species
          gnc:set->gn:set
          gnc:species->metadata
          gnc:species->gn:set
          gn:family->gn:species/metadata
          gn:family->gn:species
          gn:set->metadata
          gn:set->gn:population
          gn:population->metadata
          gn:population->gn:set
          gnc:population_category->gn:population
          gnc:taxonomic_family->gn:family))
   (outputs
    `(#:documentation ,documentation
      #:rdf ,output))))