dwca_hunter 0.5.0 → 0.5.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2a7db63e8ed5cb5d28892c4f43adaa015e52ae012a0363b6fe50aaa230038f04
-  data.tar.gz: 3b8bde91aeec03e927ec7811c0ccfba4c411e5f1a3c7521415bc359add68b8e1
+  metadata.gz: e30e9b34ea1c46b021bd3c2ec66ccad4996d4a921c7ce78791b84940bd239f05
+  data.tar.gz: 1be0e7119fd38094f94a53d71460a8f97a59f2e46a5e9740b814f5dcc97b42cd
 SHA512:
-  metadata.gz: 2992334297d7add2ad3875180b080c7278b7ab934440a5376a8fffb6943bcef9c585187ec67e1bf8737405e7153222bd65df494e4805ace843cfbfd07adf73c1
-  data.tar.gz: 91218db042979509afd377008df68c82d04a08fe39b653119cdbe3b187a27202e5da11f173310617535c2acabc1aef65aec142d4e6226d0abb250dcec2d38eab
+  metadata.gz: df1d9bebe191ebf8ae72d601f05374edeaeffbb627d08d7981da582559439dd9ad173656d78a7c88b3a9765562efa8a7095c4eaa5ed0f1f3ef856be94f990b63
+  data.tar.gz: 703bbf2d197a55a8d4e8510e940f77562540983bb5eddc7a7496ed77af5e610ce0ce5d95a1faa25878a8f8b12a17613808898453a0bd6b7aa19a87dc7c5f000e

data/CHANGELOG.md

@@ -2,14 +2,23 @@
 
 ## Unreleased (placeholder for the next version)
 
+## [v0.5.1]
+
+- Add [#11] clean up data for Mammal Species of the World
+- Add [#10] show logs during processing
+
 ## [v0.5.0]
+
 - Add [#8] convert project to a `Ruby gem`
 
 ## Footnotes
 
 This document follows [changelog guidelines]
 
+[#11]: https://github.com/GlobalNamesArchitecture/dwca_hunter/issues/11
+[#10]: https://github.com/GlobalNamesArchitecture/dwca_hunter/issues/10
 [#8]: https://github.com/GlobalNamesArchitecture/dwca_hunter/issues/8
+[v0.5.1]: https://github.com/gnames/dwca_hunter/compare/v0.5.0...v0.5.1
 [v0.5.0]: https://github.com/gnames/dwca_hunter/compare/v0.4.0...v0.5.0
 
 [changelog guidelines]: https://github.com/olivierlacan/keep-a-changelog

data/Gemfile.lock

@@ -1,9 +1,11 @@
 PATH
   remote: .
   specs:
-    dwca_hunter (0.5.0)
+    dwca_hunter (0.5.1)
+      biodiversity (~> 3.5)
       dwc-archive (~> 1.0)
       gn_uuid (~> 0.5)
+      htmlentities (~> 4.3)
       nokogiri (~> 1.8)
       rest-client (~> 2.0)
       thor (~> 0.19)

data/dwca_hunter.gemspec

@@ -26,8 +26,10 @@ Gem::Specification.new do |gem|
   gem.executables   = gem.files.grep(%r{^exe/}) { |f| File.basename(f) }
   gem.require_paths = ["lib"]
 
+  gem.add_dependency "biodiversity", "~> 3.5"
   gem.add_dependency "dwc-archive", "~> 1.0"
   gem.add_dependency "gn_uuid", "~> 0.5"
+  gem.add_dependency "htmlentities", "~> 4.3"
   gem.add_dependency "nokogiri", "~> 1.8"
   gem.add_dependency "rest-client", "~> 2.0"
   gem.add_dependency "thor", "~> 0.19"

data/exe/dwcahunter

@@ -4,6 +4,8 @@
 require "thor"
 require "dwca_hunter"
 
+DwcaHunter.logger = Logger.new($stdout)
+
 # DwcaHunterCLI determines command line interface to the gem functionality
 class DwcaHunterCLI < Thor
   desc "list [SEARCH]", "lists available sources to convert filtered by search"

data/files/species-black.txt

@@ -0,0 +1,251 @@
+ab
+above
+account
+ad
+ae
+al
+all
+allocation
+also
+anamorph
+and
+ap
+are
+areas
+as
+associated
+at
+available
+awaiting
+backbone
+bacterium
+basin
+bird
+bis
+but
+bv
+by
+ca
+calls
+cf
+circular
+cited
+clams
+clonal
+clone
+comes
+comment
+comments
+construct
+contrasts
+coralline
+coronaviridae
+culture
+cv
+da
+dc
+de
+de-
+def
+degrading
+del
+depletion
+der
+des
+described
+diatom
+differ
+display
+do
+du
+dummy
+ecological
+ectosymbiont
+ed
+either
+em
+en
+endosymbiont
+enrichment
+environmental
+et
+ex
+examples
+excluding
+expression
+extend
+eyes
+faeces
+figures
+fl
+flying
+fn
+fo
+follows
+foot
+for
+form
+forma
+formerly
+fosmid
+fossils
+fox
+fr
+fragments
+from
+fungal
+ge
+gen
+genera
+generic
+genus
+goes
+group
+he
+host
+hu
+hybrid
+id
+im
+in
+incertae
+ing
+is
+it
+jejuni-like
+jr
+kg
+la
+large
+largest
+leech
+leukemia-related
+libraries
+longer
+luciferase
+magnified
+marker
+mc
+morphology
+ms
+my
+name
+names
+new
+nf
+ng
+nm
+non
+not
+notes
+nov
+nr
+ns
+occurs
+of
+on
+one
+op
+or
+oral
+other
+ox
+parasite
+parasites
+part
+phylotype
+pipefish
+pl
+plasmid
+pomfret
+population
+populations
+pr
+probes
+prophage
+pt
+queens
+red
+reference
+references
+regarded
+region
+regions
+related
+reported
+resistance
+retroviruses
+revised
+rhodolith
+same
+sample
+samples
+scales
+se
+sea
+seahorse
+sec
+secondary
+sect
+section
+see
+seed
+seems
+segment
+series
+show
+shuttle
+sinus
+so
+soil
+south
+species
+specimens
+ss
+st
+strains
+subsp
+subspec
+subsp-nov
+summarized
+symbiont
+symbionts
+synthase
+taken
+taxon
+that
+the
+these
+thin
+this
+three
+to
+towards
+trapping
+two
+ty
+type
+und
+under
+unpublished
+up
+us
+usually
+van
+var
+variable
+variant
+variety
+vector
+vi
+virus
+von
+voyager
+was
+waters
+we
+were
+with
+wrote
+xx
+zur

data/lib/dwca_hunter.rb

@@ -1,11 +1,13 @@
 # frozen_string_literal: true
 
+require "biodiversity"
 require "logger"
 require "fileutils"
 require "uri"
 require "tmpdir"
 require "net/http"
 require "json"
+require "htmlentities"
 require "dwc_archive"
 require "dwca_hunter/resource"
 require "rest_client"

data/lib/dwca_hunter/encoding.rb

@@ -1,12 +1,18 @@
+# frozen_string_literal: true
+
 module DwcaHunter
+  # Encoding module fixes encoding issues with data
   module Encoding
     def self.latin1_to_utf8(file_path)
-      new_file = file_path + '.utf_8'
-      puts "Creating %s" % new_file
-      r = open(file_path)
-      w = open(new_file, 'w:utf-8')
+      new_file = file_path + ".utf_8"
+      puts "Creating #{new_file}"
+      r = File.open(file_path)
+      w = File.open(new_file, "w:utf-8")
+      he = HTMLEntities.new
       r.each do |l|
-        l.encode!('UTF-8', 'ISO-8859-1', invalid: :replace, replace: '?')
+        l = l
+        l = l.encode("UTF-8", "ISO-8859-1", invalid: :replace, replace: "?")
+        l = he.decode(l)
         w.write l
       end
       r.close

data/lib/dwca_hunter/resources/gnub.rb

@@ -1,4 +1,4 @@
-# encoding: utf-8
+__END__
 module DwcaHunter
   class ResourceGNUB < DwcaHunter::Resource
     def initialize(opts = {})
@@ -98,4 +98,3 @@ module DwcaHunter
     end
   end
 end
-

data/lib/dwca_hunter/resources/mammal_species.rb

@@ -1,13 +1,19 @@
+# frozen_string_literal: true
+
 module DwcaHunter
+  # ResourceMammalSpecies converts "Mammal Species of the World" data
+  # to DarwinCore Archive file
   class ResourceMammalSpecies < DwcaHunter::Resource
     def initialize(opts = {})
+      @parser = ScientificNameParser.new
+      @black_sp = black_species
       @command = "mammal-species"
       @title = "The Mammal Species of The World"
       @uuid = "464dafec-1037-432d-8449-c0b309e0a030"
       @data = []
       @extensions = []
       @count = 1
-      @clades = {"Mammalia" => { rank: "class", id: @count}}
+      @clades = { "Mammalia" => { rank: "class", id: @count } }
       @url = "http://www.departments.bucknell.edu"\
              "/biology/resources/msw3/export.asp"
       @download_path = File.join(Dir.tmpdir, "dwca_hunter",
@@ -20,14 +26,14 @@ module DwcaHunter
     end
 
     def make_dwca
-      DwcaHunter::logger_write(self.object_id, "Extracting data")
+      DwcaHunter.logger_write(object_id, "Extracting data")
       encode
       collect_data
       generate_dwca
     end
 
     def download
-      DwcaHunter::logger_write(self.object_id, "Downloading file -- "\
+      DwcaHunter.logger_write(object_id, "Downloading file -- "\
                                "it will take some time...")
       dlr = DwcaHunter::Downloader.new(url, @download_path)
       dlr.download
@@ -47,8 +53,7 @@ module DwcaHunter
     end
 
     def generate_dwca
-      DwcaHunter::logger_write(self.object_id,
-                               'Creating DarwinCore Archive file')
+      DwcaHunter.logger_write(object_id, "Creating DarwinCore Archive file")
       core_init
       extensions_init
       eml_init
@@ -64,45 +69,63 @@ module DwcaHunter
       return if rec[:commonname].to_s == ""
       taxon_id = taxon[0]
       lang = "en"
-      name = rec[:commonname].gsub("\u{0092}", "'")
+      name = rec[:commonname].tr("\u{0092}", "'")
       @extensions[0][:data] << [taxon_id, name, lang]
-
     end
 
+    # rubocop:disable Metrics/AbcSize
+
     def process_synonyms(rec, taxon)
       accepted_id = taxon[0]
       parent_id = taxon[2]
       rank = taxon[-1]
-      return unless ['species', 'subspecies'].include? rank
+      return unless %w[species subspecies].include? rank
       synonyms = rec[:synonyms].gsub(/\.$/, "").
-        gsub(/<[\/ib]+>/, "").gsub(/[\s]+/, " ").split(";")
+                 gsub(%r{<[/ibsup]+>}, "").gsub(/[\s]+/, " ").split(";")
       synonyms = synonyms.map(&:strip)
-      synonyms = synonyms.map do |s|
-        next if s.match(/<u>/)
-        if s.match(/^[a-z]/)
-          s = rec[:genus] + " " + s
-        end
+      synonyms.map do |s|
+        next if s =~ /<u>/
+        s = rec[:genus] + " " + s if s =~ /^[a-z]/
         @count += 1
         id = @count
-        @core << [id, nil, parent_id, accepted_id, s, "synonym", rank]
+        if real_name?(s)
+          @core << [id, nil, parent_id, accepted_id, s, "synonym", rank]
+        else
+          puts "Rejected: #{s}"
+        end
+      end
+    end
+
+    # rubocop:enable Metrics/AbcSize
+
+    def real_name?(str)
+      parsed = @parser.parse(str)[:scientificName]
+      return false unless parsed[:parsed]
+      epithets = parsed[:canonical].split(" ")[1..-1]
+      return false if epithets.nil? || epithets.empty?
+      epithets.each do |e|
+        return false if @black_sp[e]
       end
+      true
     end
 
-    def process_name(rec, rank)
-      name =[@core.last[4], rec[:author], rec[:date]]
-      @core.last[4] = name.join(" ").gsub(/[\s]+/, " ").strip
+    def process_name(rec)
+      name = [@core.last[4], rec[:author], rec[:date]]
+      @core.last[4] = name.join(" ").gsub(%r{<[/ibsup]+>}, "").
+                      gsub(/[\s]+/, " ").strip
       @core.last[1] = rec[:id]
     end
 
+    # rubocop:disable Metrics/AbcSize
+
     def process_hierarchy(rec)
       parent_id = @clades["Mammalia"][:id]
       is_row_rank = false
-      [:order, :suborder, :infraorder, :superfamily, :family,
-       :subfamily, :tribe, :genus, :subgenus,
-       :species, :subspecies].each do |rank|
-       is_row_rank = true if rank == rec[:taxonlevel].downcase.to_sym
+      %i[order suborder infraorder superfamily family
+         subfamily tribe genus subgenus species subspecies].each do |rank|
+        is_row_rank = true if rank == rec[:taxonlevel].downcase.to_sym
         clade = rec[rank]
-        clade = clade.capitalize if clade.match(/^[A-Z]+$/)
+        clade = clade.capitalize if clade =~ /^[A-Z]+$/
         next if clade.to_s == ""
         clade_id = nil
         clade = adjust_clade(rec, rank, clade)
@@ -114,16 +137,17 @@ module DwcaHunter
           @clades[clade] = { id: clade_id, rank: rank }
           @core << [clade_id, nil, parent_id, clade_id, clade, nil, rank.to_s]
           if is_row_rank
-            process_name(rec, rank)
+            process_name(rec)
             return @core.last
           end
         end
         parent_id = clade_id
       end
     end
+    # rubocop:enable Metrics/AbcSize
 
     def adjust_clade(rec, rank, clade)
-      if [:species, :subspecies].include? rank
+      if %i[species subspecies].include? rank
         clade = [rec[:genus], rec[:species]]
         clade << rec[:subspecies] if rank == :subspecies
         clade.join(" ").gsub(/[\s]+/, " ").strip
@@ -140,13 +164,13 @@ module DwcaHunter
           { first_name: "Don",
             last_name: "Wilson" },
           { first_name: "DeeAnn",
-            last_name: "Reader" },
-      ],
+            last_name: "Reader" }
+        ],
         metadata_providers: [
           { first_name: "Dmitry",
             last_name: "Mozzherin",
             email: "dmozzherin@gmail.com" }
-      ],
+        ],
         abstract: "Mammal Species of the World, 3rd edition (MSW3) is "\
         "a database of mammalian taxonomy, based upon the 2005 book "\
         "Mammal Species of the World. A Taxonomic and Geographic Reference "\
@@ -156,24 +180,32 @@ module DwcaHunter
     end
 
     def core_init
-      @core = [['http://rs.tdwg.org/dwc/terms/taxonID',
-                'http://globalnames.org/terms/localID',
-                'http://rs.tdwg.org/dwc/terms/parentNameUsageID',
-                'http://rs.tdwg.org/dwc/terms/acceptedNameUsageID',
-                'http://rs.tdwg.org/dwc/terms/scientificName',
-                'http://rs.tdwg.org/dwc/terms/taxonomicStatus',
-                'http://rs.tdwg.org/dwc/terms/taxonRank']]
+      @core = [["http://rs.tdwg.org/dwc/terms/taxonID",
+                "http://globalnames.org/terms/localID",
+                "http://rs.tdwg.org/dwc/terms/parentNameUsageID",
+                "http://rs.tdwg.org/dwc/terms/acceptedNameUsageID",
+                "http://rs.tdwg.org/dwc/terms/scientificName",
+                "http://rs.tdwg.org/dwc/terms/taxonomicStatus",
+                "http://rs.tdwg.org/dwc/terms/taxonRank"]]
       m = @clades["Mammalia"]
       @core << [m[:id], nil, nil, m[:id], "Mammalia", nil, "class"]
     end
 
+    def black_species
+      res = {}
+      path = File.join(__dir__, "..", "..", "..", "files", "species-black.txt")
+      File.open(path).each do |l|
+        res[l.strip] = 1
+      end
+      res
+    end
+
     def extensions_init
-      @extensions << { data: [['http://rs.tdwg.org/dwc/terms/taxonID',
-                               'http://rs.tdwg.org/dwc/terms/vernacularName',
-                               'http://purl.org/dc/terms/language']],
-                       file_name: 'vernacular_names.txt',
-                       row_type: 'http://rs.gbif.org/terms/1.0/VernacularName'
-                     }
+      @extensions << { data: [["http://rs.tdwg.org/dwc/terms/taxonID",
+                               "http://rs.tdwg.org/dwc/terms/vernacularName",
+                               "http://purl.org/dc/terms/language"]],
+                       file_name: "vernacular_names.txt",
+                       row_type: "http://rs.gbif.org/terms/1.0/VernacularName" }
     end
   end
 end

data/lib/dwca_hunter/resources/wikispecies.rb

@@ -5,7 +5,7 @@ module DwcaHunter
       @problems_file = open('problems.txt', 'w:utf-8')
       @command = "wikispecies"
       @title = 'Wikispecies'
-      @url = 'http://dumps.wikimedia.org/specieswiki/latest/' +
+      @url = 'http://dumps.wikimedia.org/specieswiki/latest/' \
              'specieswiki-latest-pages-articles.xml.bz2'
       @url = opts[:url] if opts[:url]
       @uuid = '68923690-0727-473c-b7c5-2ae9e601e3fd'
@@ -347,4 +347,3 @@ module DwcaHunter
 
   end
 end
-

data/lib/dwca_hunter/version.rb

@@ -1,5 +1,5 @@
 module DwcaHunter
-  VERSION = "0.5.0"
+  VERSION = "0.5.1"
 
   def self.version
     VERSION

metadata

@@ -1,15 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: dwca_hunter
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.5.1
 platform: ruby
 authors:
 - Dmitry Mozzherin
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-07-20 00:00:00.000000000 Z
+date: 2018-08-04 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: biodiversity
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.5'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.5'
 - !ruby/object:Gem::Dependency
   name: dwc-archive
   requirement: !ruby/object:Gem::Requirement
@@ -38,6 +52,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.5'
+- !ruby/object:Gem::Dependency
+  name: htmlentities
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.3'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.3'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
@@ -204,6 +232,7 @@ files:
 - files/birdlife_7.csv
 - files/fishbase_taxon_cache.tsv
 - files/reptile_checklist_2014_12.csv
+- files/species-black.txt
 - lib/dwca_hunter.rb
 - lib/dwca_hunter/downloader.rb
 - lib/dwca_hunter/encoding.rb
@@ -219,7 +248,6 @@ files:
 - lib/dwca_hunter/resources/opentree.rb
 - lib/dwca_hunter/resources/reptiles_checklist.rb
 - lib/dwca_hunter/resources/wikispecies.rb
-- lib/dwca_hunter/resources/worms.rb
 - lib/dwca_hunter/url.rb
 - lib/dwca_hunter/version.rb
 - lib/dwca_hunter/xml.rb

data/lib/dwca_hunter/resources/worms.rb

@@ -1,176 +0,0 @@
-# encoding: utf-8
-module DwcaHunter
-  class ResourceWoRMS < DwcaHunter::Resource
-    def initialize(opts = {})
-      @command = 'worms'
-      @title = 'WoRMS'
-      @url = 'http://content60.eol.org/resources/26.tar.gz'
-      @uuid =  '9d27a7ad-2e6a-4597-a79b-23fb3b2f8284'
-      @download_path = File.join(Dir.tmpdir,
-                                 'dwca_hunter',
-                                 'worms',
-                                 'data.tar.gz')
-      @fields = ['dc:identifier',
-                 'dc:source',
-                 'dwc:Kingdom',
-                 'dwc:Phylum',
-                 'dwc:Class',
-                 'dwc:Order',
-                 'dwc:Family',
-                 'dwc:Genus',
-                 'dwc:ScientificName']
-      @rank = { 1 => 'kingdom',
-                2 => 'phylum',
-                3 => 'class',
-                4 => 'order',
-                5 => 'family',
-                6 => 'genus',
-                7 => 'species' }
-      @known_paths = {}
-      @data = []
-      @extensions = []
-      @extensions << { data: [[
-        'http://rs.tdwg.org/dwc/terms/taxonId',
-        'http://rs.tdwg.org/dwc/terms/scientificName']],
-        file_name: 'synonyms.txt' }
-      @re = {
-        cdata: %r#\<\!\[CDATA\[(.*)\]\]\>#
-      }
-      @core = [[
-        'http://rs.tdwg.org/dwc/terms/taxonID',
-        'http://purl.org/dc/terms/parentNameUsageID',
-        'http://purl.org/dc/terms/source',
-        'http://rs.tdwg.org/dwc/terms/acceptedNameUsageID',
-        'http://purl.org/dc/terms/scientificName',
-        'http://purl.org/dc/terms/taxonRank']]
-      super
-    end
-
-    def unpack
-      unpack_tar
-    end
-
-    def make_dwca
-      collect_data
-      make_core_data
-      generate_dwca
-    end
-
-    private
-
-    def collect_data
-      DwcaHunter::logger_write(self.object_id, 'Traversing xml file...')
-      xml_file = File.join(@download_dir, '26.xml')
-      f = open(xml_file, 'r:utf-8')
-      in_taxon = false
-      taxon = nil
-      count = 0
-      Nokogiri::XML::Reader(f).each do |node|
-        if !in_taxon && node.name == 'taxon'
-          in_taxon = true
-          taxon = {}
-          @fields.each { |field| taxon[field.to_sym] = nil }
-          taxon[:synonyms] = []
-        elsif in_taxon && node.name == 'taxon'
-          in_taxon = false
-          @data << taxon
-          taxon = nil
-          count += 1
-          if count % BATCH_SIZE == 0
-            DwcaHunter::logger_write(self.object_id,
-                                     "Extracted %s taxons" % count)
-          end
-        elsif in_taxon
-          item = node.name.to_sym
-          if taxon.has_key?(item) && !taxon[item]
-            text = node.inner_xml
-            if cdata = text.match(@re[:cdata])
-              text = cdata[1]
-            else
-              text = DwcaHunter::XML.unescape(text)
-            end
-            taxon[item] = text
-          elsif node.name == 'synonym' &&
-              (cdata = node.inner_xml.match(@re[:cdata]))
-            taxon[:synonyms] << cdata[1]
-          end
-        end
-      end
-    end
-
-    def get_gn_id(path_string)
-      gn_uuid = UUID.create_v5(path_string, GNA_NAMESPACE)
-      id = Base64.urlsafe_encode64(gn_uuid.raw_bytes)[0..-3]
-      "gn:" + id
-    end
-
-    def make_core_data
-      DwcaHunter::logger_write(self.object_id, 'Creating core data')
-      @data.each_with_index do |taxa, i|
-        if i % BATCH_SIZE == 0
-          DwcaHunter::logger_write(self.object_id,
-                                   'Traversing %s species for core' % i)
-        end
-        path = get_path(taxa)
-        parent_id = get_gn_id(path.join('|'))
-        @core << [taxa[:'dc:identifier'],
-                  parent_id, taxa[:'dc:source'],
-                  nil,
-                  taxa[:'dwc:ScientificName'],
-                  'species']
-
-        taxa[:synonyms].each do |synonym|
-          @extensions[0][:data] << [taxa[:'dc:identifier'], synonym]
-        end
-
-        until path.empty?
-          path_string = path.join("|")
-          unless @known_paths[path_string]
-            @known_paths[path_string] = 1
-            parent_id = (path.size == 1) ?
-                        nil :
-                        get_gn_id([path[0..-2]].join('|'))
-            id = get_gn_id(path_string)
-            @core << [id, parent_id, nil, nil, path[-1], @rank[path.size]]
-          end
-          path.pop
-        end
-      end
-    end
-
-    def get_path(taxa)
-      path = []
-      @fields[2..-2].each do |field|
-        path << taxa[field.to_sym]
-      end
-      path
-    end
-
-    def generate_dwca
-      DwcaHunter::logger_write(self.object_id,
-                               'Creating DarwinCore Archive file')
-      @eml = {
-          id: @uuid,
-          title: @title,
-          authors: [
-            { email: 'info@marinespecies.org',
-              url: 'http://www.marinespecies.org' }
-          ],
-          metadata_providers: [
-            { first_name: 'Dmitry',
-              last_name: 'Mozzherin',
-              email: 'dmozzherin@gmail.com' }
-            ],
-          abstract: 'The aim of a World Register of Marine Species (WoRMS) ' +
-                    'is to provide an authoritative and comprehensive list ' +
-                    'of names of marine organisms, including information ' +
-                    'on synonymy. While highest priority goes to valid ' +
-                    'names, other names in use are included so that this ' +
-                    'register can serve as a guide to interpret taxonomic ' +
-                    'literature.',
-      }
-      super
-    end
-  end
-end
-