#! /usr/bin/env guile
!#

(use-modules (rnrs programs)
             (rnrs io ports)
             (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))


(define-transformer gn:dataset->metadata
  (tables (Datasets
           (inner-join InfoFiles "ON InfoFiles.DatasetId = Datasets.DatasetId")
           (inner-join InbredSet "ON InbredSet.Id = InfoFiles.InbredSetId"))
          ;; Skip monkey datasets
          "WHERE InfoFiles.InfoPageName NOT LIKE 'INIA_MacFas_%'"
          "GROUP BY Datasets.DatasetId")
  (schema-triples
    (gnt:has_case_info a owl:ObjectProperty)
    (gnt:has_case_info rdfs:comment "Information about the cases used in this platform")
    (gnt:has_case_info rdfs:domain dcat:Dataset)
    (gnt:has_case_info rdfs:label "About Case")
    (gnt:has_citation a owl:ObjectProperty)
    (gnt:has_citation rdfs:comment "Citation for this dataset")
    (gnt:has_citation rdfs:domain dcat:Dataset)
    (gnt:has_citation rdfs:label "Citation")
    (gnt:has_contributors a owl:ObjectProperty)
    (gnt:has_contributors rdfs:comment "Contributors of this resource")
    (gnt:has_contributors rdfs:comment "Contributors of this resource")
    (gnt:has_contributors rdfs:domain dcat:Dataset)
    (gnt:has_contributors rdfs:label "Contributors")
    (gnt:has_data_processing_info a owl:ObjectProperty)
    (gnt:has_data_processing_info rdfs:comment "Information about how this dataset was processed")
    (gnt:has_data_processing_info rdfs:domain dcat:Dataset)
    (gnt:has_data_processing_info rdfs:label "About Data Processing")
    (gnt:has_experiment_design a owl:ObjectProperty)
    (gnt:has_experiment_design rdfs:comment "Experiment Design for this resource")
    (gnt:has_experiment_design rdfs:domain dcat:Dataset)
    (gnt:has_experiment_design rdfs:label "Experiment Design")
    (gnt:has_experiment_design_info a owl:ObjectProperty)
    (gnt:has_experiment_design_info rdfs:comment "Information about how the experiment was designed")
    (gnt:has_experiment_design_info rdfs:domain dcat:Dataset)
    (gnt:has_experiment_design_info rdfs:label "Experiment Design")
    (gnt:has_experiment_type a owl:ObjectProperty)
    (gnt:has_experiment_type rdfs:comment "Information about the experiment type")
    (gnt:has_experiment_type rdfs:domain dcat:Dataset)
    (gnt:has_experiment_type rdfs:label "Experiment Type Metadata")
    (gnt:has_platform_info a owl:ObjectProperty)
    (gnt:has_platform_info rdfs:comment "Information about the platform that was used with this dataset")
    (gnt:has_platform_info rdfs:domain dcat:Dataset)
    (gnt:has_platform_info rdfs:label "About Platform")
    (gnt:has_samples a owl:ObjectProperty)
    (gnt:has_samples rdfs:domain dcat:Dataset)
    (gnt:has_samples rdfs:label "Samples")
    (gnt:has_specifics a owl:ObjectProperty)
    (gnt:has_specifics rdfs:comment "Has specifics")
    (gnt:has_specifics rdfs:domain dcat:Dataset)
    (gnt:has_specifics rdfs:label "Specifics")
    (gnt:has_summary a owl:ObjectProperty)
    (gnt:has_summary rdfs:comment "Summary information about dataset")
    (gnt:has_summary rdfs:domain dcat:Dataset)
    (gnt:has_summary rdfs:label "Summary")
    (gnt:has_tissue_info a owl:ObjectProperty)
    (gnt:has_tissue_info rdfs:domain dcat:Dataset)
    (gnt:has_tissue_info rdfs:label "Metadata about Tissue for this resource"))
  (triples (string->identifier "dataset" (field InfoFiles InfoPageName) #:separator "_")
    (set rdf:type 'dcat:Dataset)
    (set dct:title (normalize-string-field (field InfoFiles InfoPageName)))
    (set dct:identifier (format #f "GN~a" (field InfoFiles GN_AccesionId)))
    (set gnt:has_strain
         (string->identifier "set" (field InbredSet Name InbredSetName) #:separator "_"))
    (set gnt:has_experiment_type
         (let ((experiment-type
                (field InfoFiles Experiment_Type)))
           (if (or (null? experiment-type) (string-blank? experiment-type))
               "" (sanitize-rdf-string experiment-type))))
    (set gnt:has_tissue_info
         (let ((tissue-info
                (field Datasets AboutTissue)))
           (if (or (null? tissue-info) (string-blank? tissue-info))
               "" (sanitize-rdf-string tissue-info))))
    (set gnt:has_summary
         (let* ((summary
                 (field Datasets Summary)))
           (if (or (null? summary) (string-blank? summary))
               "" (sanitize-rdf-string summary))))
    (set gnt:has_citation
         (let ((citation
                (field Datasets Citation)))
           (if (or (null? citation) (string-blank? citation))
               "" (sanitize-rdf-string citation))))
    (set gnt:has_samples
         (let ((samples
                (field InfoFiles samples)))
           (if (or (null? samples) (string-blank? samples))
               "" (sanitize-rdf-string samples))))
    (set gnt:has_specifics
         (let* ((specifics
                 (field InfoFiles Specifics)))
           (if (or (null? specifics) (string-blank? specifics))
               "" (sanitize-rdf-string specifics))))
    (set gnt:has_case_info
         (let ((cases
                (field Datasets AboutCases)))
           (if (or (null? cases) (string-blank? cases))
               "" (sanitize-rdf-string cases))))
    (set gnt:has_platform_info
         (let* ((platform
                 (field Datasets AboutPlatform)))
           (if (or (null? platform) (string-blank? platform))
               "" (sanitize-rdf-string platform))))
    (set gnt:has_data_processing_info
         (let* ((processing
                 (field Datasets AboutDataProcessing)))
           (if (or (null? processing) (string-blank? processing))
               "" (sanitize-rdf-string processing))))
    (set gnt:has_experiment_design
         (let ((experiment-design
                (field Datasets ExperimentDesign)))
           (if (or (null? experiment-design) (string-blank? experiment-design))
               "" (sanitize-rdf-string experiment-design))))
    (set gnt:has_contributors
         (let ((contributors
                (field Datasets Contributors)))
           (if (or (null? contributors) (string-blank? contributors))
               "" (sanitize-rdf-string contributors))))))


(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 "Datasets Metadata")
   (connection %connection-settings)
   (table-metadata? #f)
   (prefixes
    '(("dct:" "<http://purl.org/dc/terms/>")
      ("dcat:" "<http://www.w3.org/ns/dcat#>")
      ("gn:" "<http://rdf.genenetwork.org/v1/id/>")
      ("gnc:" "<http://rdf.genenetwork.org/v1/category/>")
      ("gnt:" "<http://rdf.genenetwork.org/v1/term/>")
      ("rdf:" "<http://www.w3.org/1999/02/22-rdf-syntax-ns#>")
      ("rdfs:" "<http://www.w3.org/2000/01/rdf-schema#>")
      ("owl:" "<http://www.w3.org/2002/07/owl#>")
      ("skos:" "<http://www.w3.org/2004/02/skos/core#>")
      ("xkos:" "<http://rdf-vocabulary.ddialliance.org/xkos#>")
      ("xsd:" "<http://www.w3.org/2001/XMLSchema#>")))
   (inputs
    (list gn:dataset->metadata))
   (outputs
    `(#:documentation ,documentation
      #:rdf ,output))))