biodiversity19 1.1.3 → 1.2.0

data/README.rdoc

@@ -100,5 +100,10 @@ You can use it as a library
   # to resolve lsid and get back RDF file
   LsidResolver.resolve("urn:lsid:ubio.org:classificationbank:2232671")
 
+  # to get canonicals with ranks for infraspecific epithets:
+  parser = ScientificNameParser.new(canonical_with_rank: true)
+  parser.parse('Cola cordifolia var. puberula A. Chev.')[:scientificName][:canonical]
+  # should get 'Cola cordifolia var. puberula'
+
 Copyright (c) 2009-2011 Marine Biological Laboratory. See LICENSE.txt for
 further details.

data/VERSION

@@ -1 +1 @@
-1.1.3
+1.2.0

data/lib/biodiversity/parser.rb

@@ -12,7 +12,7 @@ module PreProcessor
   TAXON_CONCEPTS2 = /\s+(\(?s\.\s?s\.|\(?s\.\s?l\.|\(?s\.\s?str\.|\(?s\.\s?lat\.|sec\.|sec|near)\b.*$/
   TAXON_CONCEPTS3 = /(,\s*|\s+)(pro parte|p\.\s?p\.)\s*$/i  
   NOMEN_CONCEPTS  = /(,\s*|\s+)(\(?nomen|\(?nom\.|\(?comb\.).*$/i
-  LAST_WORD_JUNK  = /(,\s*|\s+)(spp\.|spp|var\.|var|von|van|ined\.|ined|sensu|new|non|nec|cf\.|cf|sp\.|sp|ssp\.|ssp|subsp|subgen|hybrid|hort\.|hort)\??\s*$/i
+  LAST_WORD_JUNK  = /(,\s*|\s+)(spp\.|spp|var\.|var|von|van|ined\.|ined|sensu|new|non|nec|nudum|cf\.|cf|sp\.|sp|ssp\.|ssp|subsp|subgen|hybrid|hort\.|hort)\??\s*$/i
   
   def self.clean(a_string)
     [NOTES, TAXON_CONCEPTS1, TAXON_CONCEPTS2, TAXON_CONCEPTS3, NOMEN_CONCEPTS, LAST_WORD_JUNK].each do |i|
@@ -36,7 +36,9 @@ class ParallelParser
   end
 
   def parse(names_list)
-    parsed = Parallel.map(names_list.uniq, :in_processes => @processes_num) { |n| [n, parse_process(n)] }
+    parsed = Parallel.map(names_list.uniq, in_processes: @processes_num) do |n| 
+      [n, parse_process(n)]
+    end
     parsed.inject({}) { |res, x| res[x[0]] = x[1]; res }
   end
 
@@ -47,7 +49,10 @@ class ParallelParser
   private
   def parse_process(name)
     p = ScientificNameParser.new
-    p.parse(name) rescue {:scientificName => {:parsed => false, :verbatim => name,  :error => 'Parser error'}}
+    failed_res = { scientificName: { parsed: false, 
+                                     verbatim: name,  
+                                     error: 'Parser error' } }
+    p.parse(name) rescue failed_res 
   end
 end
 
@@ -64,7 +69,10 @@ end
 # end
 
 class ScientificNameParser
-  VERSION = open(File.join(File.dirname(__FILE__), '..', '..', 'VERSION')).readline.strip
+  VERSION = open(File.join(File.dirname(__FILE__), 
+                           '..',
+                           '..',
+                           'VERSION')).readline.strip
   
   def self.fix_case(name_string)
     name_ary = name_string.split(/\s+/)
@@ -96,7 +104,8 @@ class ScientificNameParser
   end
 
   
-  def initialize
+  def initialize(opts = {})
+    @canonical_with_rank = !!opts[:canonical_with_rank]
     @verbatim = ''
     @clean = ScientificNameCleanParser.new
     @dirty = ScientificNameDirtyParser.new
@@ -134,7 +143,9 @@ class ScientificNameParser
           @parsed =  @dirty.parse(salvage_string) || @canonical.parse(a_string) || { :verbatim => a_string }
         end
       rescue
-        @parsed = {:scientificName => {:parsed => false, :verbatim => name,  :error => 'Parser error'}}
+        @parsed = { scientificName: { parsed: false, 
+                                      verbatim: name,  
+                                      error: 'Parser error' } }
       end
     end
 
@@ -142,7 +153,8 @@ class ScientificNameParser
       @verbatim = a_string
     end
 
-    def @parsed.all(verbatim = @verbatim)
+    def @parsed.all(opts = {})
+      canonical_with_rank = !!opts[:canonical_with_rank]
       parsed = self.class != Hash
       res = { :parsed => parsed, :parser_version => ScientificNameParser::VERSION}
       if parsed
@@ -159,8 +171,10 @@ class ScientificNameParser
       else
         res.merge!(self)
       end
+      if canonical_with_rank && canonical.count(" ") > 1 && res[:details][0][:infraspecies]
+        ScientificNameParser.add_rank_to_canonical(res)
+      end
       res = {:scientificName => res}
-      res
     end
     
     def @parsed.pos_json
@@ -172,7 +186,21 @@ class ScientificNameParser
     end
 
     @parsed.verbatim = @verbatim
-    @parsed.all
+    @parsed.all(canonical_with_rank: @canonical_with_rank)
+  end
+  
+  private
+
+  def self.add_rank_to_canonical(parsed)
+    parts = parsed[:canonical].split(" ")
+    name_ary = parts[0..1]
+    parsed[:details][0][:infraspecies].each do |data|
+      infrasp = data[:string]
+      rank = data[:rank]
+      name_ary << (rank && rank != 'n/a' ? "#{rank} #{infrasp}" : infrasp)
+    end
+    parsed[:canonical] = name_ary.join(" ")
   end
+  
 end
 

data/lib/biodiversity/parser/scientific_name_clean.treetop

@@ -262,6 +262,28 @@ grammar ScientificNameClean
       end
     }
     /  
+    a:genus space b:infragenus space aid:annotation_identification? space c:species space aid:annotation_identification space d:infraspecies_mult {
+      def value
+        a.value + " " + b.value + " " + c.value + " " + d.value
+      end
+    
+      def canonical
+        a.canonical + " " + c.canonical + " " + d.canonical
+      end
+    
+      def pos
+        a.pos.merge(b.pos).merge(c.pos).merge(d.pos)
+      end
+      
+      def hybrid
+        c.hybrid rescue false
+      end
+    
+      def details
+        a.details.merge(b.details).merge(c.details).merge(d.details)
+      end
+    }
+    /  
     a:genus space b:infragenus space aid:annotation_identification? space c:species {
       def value
         if defined? aid.apply

data/spec/parser/scientific_name.spec.rb

@@ -26,6 +26,7 @@ describe ScientificNameParser do
       JSON.load(json(y[:name])).should == JSON.load(y[:jsn]) unless y[:comment]
     end
   end
+
   
   # it 'should generate new test_file' do
   #   new_test = open(File.expand_path(dir + "../../spec/parser/test_data_new.txt"),'w')
@@ -57,6 +58,36 @@ describe ScientificNameParser do
   end
 end
 
+describe "ScientificNameParser with ranked canonicals" do 
+  before(:all) do
+    @parser = ScientificNameParser.new(canonical_with_rank: true)
+  end
+
+  it 'should not influence output for uninomials and binomials' do
+    data = [
+      ['Ekbainacanthus Yakowlew 1902','Ekbainacanthus'],
+      ['Ekboarmia sagnesi herrerai Exposito 2007', 'Ekboarmia sagnesi herrerai'],
+      ['Ekboarmia holli Oberthür', 'Ekboarmia holli']]
+
+    data.each do |d| 
+      parsed = @parser.parse(d[0])[:scientificName][:canonical]
+      parsed.should == d[1]
+    end
+  end
+
+  it 'should preserve rank for ranked multinomials' do
+    data = [
+      ['Cola cordifolia var. puberula A. Chev.', 'Cola cordifolia var. puberula'],
+      ['Abies homolepis forma umbilicata (Mayr) Schelle', 'Abies homolepis forma umbilicata'],
+      ['Quercus ilex ssp. ballota (Desf.) Samp', 'Quercus ilex ssp. ballota']
+    ]
+    data.each do |d|
+      parsed = @parser.parse(d[0])[:scientificName][:canonical]
+      parsed.should == d[1] 
+    end
+  end
+
+end
 
 describe ParallelParser do
   it "should find number of cpus" do

data/spec/parser/test_data.txt

@@ -190,6 +190,8 @@ Endoxyla sp. GM-, 2003|{"scientificName":{"parsed":true, "parser_version":"test_
 Liopropoma sp.2 Not applicable|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Liopropoma sp.2 Not applicable", "normalized":"Liopropoma", "canonical":"Liopropoma", "hybrid":false, "details":[{"genus":{"string":"Liopropoma"}, "annotation_identification":"sp.", "ignored":{"unparsed":"2 Not applicable"}}], "parser_run":1, "positions":{"0":["genus", 10], "11":["annotation_identification", 14]}}}
 Lacanobia nr. subjuncta Bold:Aab, 0925|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Lacanobia nr. subjuncta Bold:Aab, 0925", "normalized":"Lacanobia", "canonical":"Lacanobia", "hybrid":false, "details":[{"genus":{"string":"Lacanobia"}, "annotation_identification":"nr.", "ignored":{"species":{"string":"subjuncta", "authorship":"Bold:Aab", "basionymAuthorTeam":{"authorTeam":"Bold:Aab", "author":["Bold:Aab"]}}}}], "parser_run":2, "positions":{"0":["genus", 9], "10":["annotation_identification", 13]}}}
 Lacanobia sp. nr. subjuncta Bold:Aab, 0925|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Lacanobia sp. nr. subjuncta Bold:Aab, 0925", "normalized":"Lacanobia", "canonical":"Lacanobia", "hybrid":false, "details":[{"genus":{"string":"Lacanobia"}, "annotation_identification":"sp. nr.", "ignored":{"species":{"string":"subjuncta", "authorship":"Bold:Aab", "basionymAuthorTeam":{"authorTeam":"Bold:Aab", "author":["Bold:Aab"]}}}}], "parser_run":2, "positions":{"0":["genus", 9], "10":["annotation_identification", 17]}}}
+#Larus occidentalis cf. wymani|{}
+Calidris cf. cooperi|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Calidris cf. cooperi", "normalized":"Calidris cf. cooperi", "canonical":"Calidris cooperi", "hybrid":false, "details":[{"genus":{"string":"Calidris"}, "annotation_identification":"cf.", "species":{"species":{"string":"cooperi"}}}], "parser_run":1, "positions":{"0":["genus", 8], "9":["annotation_identification", 12], "13":["species", 20]}}}
 #TODO:Gemmula cf. cosmoi NP-2008 -- generates wrong authorship
 
 #unknown authorship

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: biodiversity19
 version: !ruby/object:Gem::Version
-  version: 1.1.3
+  version: 1.2.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-11-08 00:00:00.000000000 Z
+date: 2013-03-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: treetop
@@ -178,7 +178,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -2308575381079309035
+      hash: 3489764594482913391
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: