view example.yaml @ 7:895c1ef05dbc draft default tip

Uploaded

#####################################################################################
# curate_csv_with_worms.yaml
#####################################################################################
#
# Clean data provided via standard input and print results to standard output:
# ka curate_csv_with_worms.yaml < ../data/five_records.csv
#
# Clean data in a named input file and print results to standard output:
# ka curate_csv_with_worms.yaml -p input=../data/five_records.csv
#
# Clean data in a named input file and save results to named output file:
# ka curate_csv_with_worms.yaml -p input=../data/five_records.csv -p output=output.csv
#
#####################################################################################

imports:

- classpath:/org/kurator/akka/types.yaml

components:

- id: ReadInput
  type: PythonActor
  properties:
    code: |
        import csv
        import sys
        def on_start(options):
          filePath = options.get('inputFile') 
          f = open(filePath, 'r') if filePath is not None else sys.stdin
          for record in csv.DictReader(f):
             yield record

- id: CleanRecords
  type: PythonClassActor
  properties:
    pythonClass: kurator_worms.record_curator.RecordCurator
    onData: clean_record
    parameters:
        taxon_name_field          : 'TaxonName'
        author_field              : 'Author'
        original_taxon_name_field : 'OriginalTaxonName'
        original_author_field     : 'OriginalAuthor'
        match_type_field          : 'WoRMSMatchType'
        lsid_field                : 'LSID'
        fuzzy_match_enabled       : 'True'
    listensTo:
      - !ref ReadInput

- id: WriteOutput
  type: PythonClassActor
  properties:
    pythonClass: CsvWriter
    code: |
        import csv
        import os
        import sys
        class CsvWriter(object): 
          def on_start(self, options):
            filePath = options.get('outputFile') 
            self.f = open(filePath, 'w') if filePath is not None else sys.stdout
            self.dw = csv.DictWriter(self.f,
                                     fieldnames=options['fieldnames'],
                                     quotechar="'", 
                                     lineterminator=os.linesep)
            self.dw.writeheader()
          def on_data(self, record):
            self.dw.writerow(record)
            sys.stdout.flush()
    parameters:
      fieldnames: [ID,TaxonName,Author,OriginalTaxonName,OriginalAuthor,WoRMSMatchType,LSID]
    listensTo:
      - !ref CleanRecords

- id: ValidateNamesWithWoRMSWorkflow
  type: Workflow
  properties:
    actors:
      - !ref ReadInput
      - !ref CleanRecords
      - !ref WriteOutput
    parameters:
       input:
         actor: !ref ReadInput
         parameter: inputFile
       output:
         actor: !ref WriteOutput
         parameter: outputFile