Darwin Core Archive

require 'rubygems'
require 'dwc_archive'

dwc = DarwinCore.new('/path_to_file/archive_file.tar.gz')
dwc.archive.files      # the archive file list
dwc.metadata.data      # summary of metadata from eml.xml if it exists
dwc.metadata.authors   # authors of the archive
dwc.core.data          # summary of DarwinCore main file
dwc.core.file_path     # path to the DarwinCore main file
dwc.extensions         # array of DarwinCore Star extensions
dwc.extensions[0].data # summary for an extension

# read content of the core data file into memory or used with a block
# it returns array of arrays of data
# rows that had a wrong encoding will be collected into errors array
data, errors = dwc.core.read

# read content using a block, getting back results in sets of 100 rows each
results = []
tail_data, tail_errors = dwc.core.read(100) do |data, errors|
  results << [data, errors]
end
results << [tail_data, tail_errors]

# read content of an extension data file into memory
data, errors = dwc.core.extensions[0].read

# read content of an extension data using block
results = []
tail_data, tail_errors = dwc.core.extensions[0](100) do |data, errors|
  results << [data, errors]
end
results << [tail_data, tail_errors]

# normalize names in classification collecting together synonyms,
# canonical names, vernacular names and associating paths to taxons
# in a classification distributed as DwCA file

result = dwc.normalize_classification

# for a finer control over normalization:

cn = DarwinCore::ClassificationNormalizer.new(dwc)
cn.normalize
# if you don't want to generate path consisting of canonical forms
# of ancestors to a taxon
cn.normalize(:with_canonical_names => false)

# if you don't want to ingest information from extensions
cn.normalize(:with_extensions => false)

# to get a flat hash of nodes with attached vernacular names and synonyms
normalized_data = cn.normalized_data

# to get a representation of tree organization as a hash
classification_tree = cn.tree

# to get list of all name strings used as scientific or vernacular names
all_name_strings = cn.name_strings

# to get list of errors generated during the normalization
errors = cn.error_names

DarwinCore.clean_all   # remove all expanded archives

gen = DarwinCore::Generator.new('/tmp/dwc_birches.tar.gz')

core = [
  ["http://rs.tdwg.org/dwc/terms/taxonID",
   "http://rs.tdwg.org/dwc/terms/parentNameUsageID",
   "http://rs.tdwg.org/dwc/terms/scientificName",
   "http://rs.tdwg.org/dwc/terms/taxonRank"],
  [1, 0, "Plantae", "kingdom"],
  [2, 1, "Betula", "genus"],
  [3, 2, "Betula verucosa", "species"]
]

vernacular_names = [
  ["http://rs.tdwg.org/dwc/terms/TaxonID",
  "http://rs.tdwg.org/dwc/terms/vernacularName"],
  [1, "Plants"],
  [1, "Растения"],
  [2, "Birch"],
  [2, "Береза"],
  [3, "Wheeping Birch"],
  [3, "Береза плакучая"]
]

eml = {
  :id => '1234',
  :license => 'http://creativecommons.org/licenses/by-sa/3.0/',
  :title => 'Test Classification',
  :authors => [
    { :first_name => 'John',
      :last_name => 'Doe',
      :email => 'jdoe@example.com',
      :organization => 'Example',
      :position => 'Assistant Professor',
      :url => 'http://example.org' },
      { :first_name => 'Jane',
        :last_name => 'Doe',
        :email => 'jane@example.com' }
],
  :metadata_providers => [
    { :first_name => 'Jim',
      :last_name => 'Doe',
      :email => 'jimdoe@example.com',
      :url => 'http://aggregator.example.org' }],
  :abstract => 'test classification',
  :citation =>
    'Test classification: Doe John, Doe Jane, Taxnonmy, 10, 1, 2010',
  :url => 'http://example.com'
}

gen.add_core(core, 'core.txt')
gen.add_extension(vernacular_names,
                  'vernacular_names.txt',
                  true, 'http://rs.gbif.org/terms/1.0/VernacularName')
gen.add_meta_xml
gen.add_eml_xml(eml)
gen.pack