biodiversity19 0.5.15 → 0.5.16

data/lib/biodiversity/parser/scientific_name_clean.treetop

@@ -22,6 +22,10 @@ grammar ScientificNameClean
       def details
         a.details.class == Array ? a.details : [a.details]
       end
+
+      def parser_run
+        1
+      end
     }
   end
   
@@ -509,7 +513,7 @@ grammar ScientificNameClean
   end
   
   rule genus
-    a:cap_latin_word !(space_hard author_prefix_word space_hard author_word) {
+    a:(cap_latin_word_pair/cap_latin_word) !(space_hard author_prefix_word space_hard author_word) {
       def value
         a.value
       end
@@ -555,7 +559,7 @@ grammar ScientificNameClean
   end
 
   rule uninomial_string
-    cap_latin_word {
+    (cap_latin_word_pair/cap_latin_word) {
       def canonical
         value
       end
@@ -938,6 +942,14 @@ grammar ScientificNameClean
     }
   end
   
+  rule cap_latin_word_pair
+    a:cap_latin_word "-" b:cap_latin_word {
+      def value
+        a.value + b.value.downcase
+      end
+    }
+  end
+  
   rule cap_latin_word
     a:([A-Z]/cap_digraph) b:latin_word "?" {
       def value
@@ -951,6 +963,12 @@ grammar ScientificNameClean
       end
     }
     /
+    a:("AE"/"OE") b:latin_word {
+      def value
+        a.text_value[0..0] + 'e' + b.value
+      end
+    }
+    /
     ("Ca"/"Ea"/"Ge"/"Ia"/"Io"/"Io"/"Ix"/"Lo"/"Oa"/"Ra"/"Ty"/"Ua"/"Aa"/"Ja"/"Zu"/"La"/"Qu"/"As"/"Ba") {
       def value
         text_value
@@ -1041,42 +1059,32 @@ grammar ScientificNameClean
   end
 
   rule latin_word
-    a:[a-zëüäöïéåóç] b:full_name_letters {
-      def value
-        a.text_value + b.value
-      end
-     }
-     /
-     a:digraph b:full_name_letters {
+    a:[a-zëæœ] b:valid_name_letters {
       def value
-        a.value + b.value
+        l = a.text_value
+        l = 'ae' if l == 'æ'
+        l = 'oe' if l == 'œ'
+        l + b.value
       end
      }
   end
 
-  rule full_name_letters
-    a:digraph b:full_name_letters {
-      def value
-        a.value + b.value
-      end
-    }
-    /
-    a:valid_name_letters b:digraph c:full_name_letters {
-      def value
-        a.value + b.value + c.value
-      end
-    }
-    /
-    valid_name_letters
-  end
-
   rule valid_name_letters
-    [a-z\-ëüäöïéåóç]+ {
+    [a-z\-ëæœ]+ {
       def value
-        text_value
+        res = ''
+        text_value.split('').each do |l|
+          l = 'ae' if l == 'æ'
+          l = 'oe' if l == 'œ'
+          # not sure if we should normalize ë as well. It is legal in botanical code, but it 
+          # might be beneficial to normalize it for the reconsiliation purposes
+          # l = 'e' if l == 'ë' 
+          res << l
+        end
+        res
       end
     }
-  end 
+  end
 
   rule cap_digraph
     "Æ" {
@@ -1092,20 +1100,6 @@ grammar ScientificNameClean
     }  
   end
 
-  rule digraph
-    "æ" {
-      def value
-      'ae'
-      end
-    }   
-    /
-    "œ" {
-      def value
-      'oe'
-      end
-    }
-  end
-
   rule year
     b:left_paren space a:(year_number_with_character/year_number) space c:right_paren {
       def value
@@ -1177,9 +1171,9 @@ grammar ScientificNameClean
   end
   
   rule multiplication_sign
-    "×" {
+    ("×"/"*") {
       def value
-        text_value
+        "×"
       end
     }
   end

data/lib/biodiversity/parser/scientific_name_dirty.rb

@@ -3,11 +3,51 @@ module ScientificNameDirty
   include Treetop::Runtime
 
   def root
-    @root || :root
+    @root ||= :root
   end
 
   include ScientificNameClean
 
+  module Root0
+    def space1
+      elements[0]
+    end
+
+    def a
+      elements[1]
+    end
+
+    def space2
+      elements[2]
+    end
+  end
+
+  module Root1
+    def value
+      a.value.gsub(/\s{2,}/, ' ').strip
+    end
+    
+    def canonical
+      a.canonical.gsub(/\s{2,}/, ' ').strip
+    end
+    
+    def pos
+      a.pos
+    end
+    
+    def hybrid
+      a.hybrid
+    end
+    
+    def details
+      a.details.class == Array ? a.details : [a.details]
+    end
+
+    def parser_run
+      2
+    end
+  end
+
   def _nt_root
     start_index = index
     if node_cache[:root].has_key?(index)
@@ -19,7 +59,25 @@ module ScientificNameDirty
       return cached
     end
 
-    r0 = super
+    i0, s0 = index, []
+    r1 = _nt_space
+    s0 << r1
+    if r1
+      r2 = _nt_scientific_name_5
+      s0 << r2
+      if r2
+        r3 = _nt_space
+        s0 << r3
+      end
+    end
+    if s0.last
+      r0 = instantiate_node(SyntaxNode,input, i0...index, s0)
+      r0.extend(Root0)
+      r0.extend(Root1)
+    else
+      @index = i0
+      r0 = nil
+    end
 
     node_cache[:root][start_index] = r0
 
@@ -329,6 +387,161 @@ module ScientificNameDirty
     r0
   end
 
+  module LatinWord0
+    def a
+      elements[0]
+    end
+
+    def b
+      elements[1]
+    end
+  end
+
+  module LatinWord1
+    def value
+      res = ''
+      text_value.split('').each do |l|
+        l = 'ae' if l == 'æ'
+        l = 'oe' if l == 'œ'
+        res << l
+      end
+      res.tr('àâåãäáçčéèíìïňññóòôøõöúùürŕřŗššşž',
+             'aaaaaacceeiiinnnoooooouuurrrrsssz')
+    end
+  end
+
+  def _nt_latin_word
+    start_index = index
+    if node_cache[:latin_word].has_key?(index)
+      cached = node_cache[:latin_word][index]
+      if cached
+        cached = SyntaxNode.new(input, index...(index + 1)) if cached == true
+        @index = cached.interval.end
+      end
+      return cached
+    end
+
+    i0, s0 = index, []
+    if has_terminal?('\G[a-z\\-ëæœàâåãäáçčéèíìïňññóòôøõöúùürŕřŗššşž]', true, index)
+      r1 = true
+      @index += 1
+    else
+      r1 = nil
+    end
+    s0 << r1
+    if r1
+      r2 = _nt_valid_name_letters
+      s0 << r2
+    end
+    if s0.last
+      r0 = instantiate_node(SyntaxNode,input, i0...index, s0)
+      r0.extend(LatinWord0)
+      r0.extend(LatinWord1)
+    else
+      @index = i0
+      r0 = nil
+    end
+
+    node_cache[:latin_word][start_index] = r0
+
+    r0
+  end
+
+  module ValidNameLetters0
+    def value
+      res = ''
+      text_value.split('').each do |l|
+        l = 'ae' if l == 'æ'
+        l = 'oe' if l == 'œ'
+        res << l
+      end
+      res.tr('àâåãäáçčéèíìïňññóòôøõöúùürŕřŗššşž',
+             'aaaaaacceeiiinnnoooooouuurrrrsssz')
+    end
+  end
+
+  def _nt_valid_name_letters
+    start_index = index
+    if node_cache[:valid_name_letters].has_key?(index)
+      cached = node_cache[:valid_name_letters][index]
+      if cached
+        cached = SyntaxNode.new(input, index...(index + 1)) if cached == true
+        @index = cached.interval.end
+      end
+      return cached
+    end
+
+    s0, i0 = [], index
+    loop do
+      if has_terminal?('\G[a-z\\-ëæœàâåãäáçčéèíìïňññóòôøõöúùürŕřŗššşž]', true, index)
+        r1 = true
+        @index += 1
+      else
+        r1 = nil
+      end
+      if r1
+        s0 << r1
+      else
+        break
+      end
+    end
+    if s0.empty?
+      @index = i0
+      r0 = nil
+    else
+      r0 = instantiate_node(SyntaxNode,input, i0...index, s0)
+      r0.extend(ValidNameLetters0)
+    end
+
+    node_cache[:valid_name_letters][start_index] = r0
+
+    r0
+  end
+
+  module ValidNameLetters0
+    def value
+      text_value
+    end
+  end
+
+  def _nt_valid_name_letters
+    start_index = index
+    if node_cache[:valid_name_letters].has_key?(index)
+      cached = node_cache[:valid_name_letters][index]
+      if cached
+        cached = SyntaxNode.new(input, index...(index + 1)) if cached == true
+        @index = cached.interval.end
+      end
+      return cached
+    end
+
+    s0, i0 = [], index
+    loop do
+      if has_terminal?('\G[a-z\\-ëüäöïéåóç]', true, index)
+        r1 = true
+        @index += 1
+      else
+        r1 = nil
+      end
+      if r1
+        s0 << r1
+      else
+        break
+      end
+    end
+    if s0.empty?
+      @index = i0
+      r0 = nil
+    else
+      r0 = instantiate_node(SyntaxNode,input, i0...index, s0)
+      r0.extend(ValidNameLetters0)
+    end
+
+    node_cache[:valid_name_letters][start_index] = r0
+
+    r0
+  end
+
   module RightParen0
     def space
       elements[1]

data/lib/biodiversity/parser/scientific_name_dirty.treetop

@@ -3,7 +3,31 @@ grammar ScientificNameDirty
   include ScientificNameClean
 
   rule root
-    super
+    space a:scientific_name_5 space {
+      def value
+        a.value.gsub(/\s{2,}/, ' ').strip
+      end
+      
+      def canonical
+        a.canonical.gsub(/\s{2,}/, ' ').strip
+      end
+      
+      def pos
+        a.pos
+      end
+      
+      def hybrid
+        a.hybrid
+      end
+      
+      def details
+        a.details.class == Array ? a.details : [a.details]
+      end
+
+      def parser_run
+        2
+      end
+    }
   end
 
   rule scientific_name_5
@@ -90,6 +114,43 @@ grammar ScientificNameDirty
      super
   end
 
+  rule latin_word
+    a:[a-z\-ëæœàâåãäáçčéèíìïňññóòôøõöúùürŕřŗššşž] b:valid_name_letters {
+      def value
+        res = ''
+        text_value.split('').each do |l|
+          l = 'ae' if l == 'æ'
+          l = 'oe' if l == 'œ'
+          res << l
+        end
+        res.tr('àâåãäáçčéèíìïňññóòôøõöúùürŕřŗššşž',
+               'aaaaaacceeiiinnnoooooouuurrrrsssz')
+      end
+     }
+  end
+
+  rule valid_name_letters
+    [a-z\-ëæœàâåãäáçčéèíìïňññóòôøõöúùürŕřŗššşž]+ {
+      def value
+        res = ''
+        text_value.split('').each do |l|
+          l = 'ae' if l == 'æ'
+          l = 'oe' if l == 'œ'
+          res << l
+        end
+        res.tr('àâåãäáçčéèíìïňññóòôøõöúùürŕřŗššşž',
+               'aaaaaacceeiiinnnoooooouuurrrrsssz')
+      end
+    }
+  end
+  rule valid_name_letters
+    [a-z\-ëüäöïéåóç]+ {
+      def value
+        text_value
+      end
+    }
+  end
+
   rule right_paren
    ")" space ")"
    /

data/lib/biodiversity/parser.rb

@@ -34,6 +34,7 @@ class ScientificNameParser
           :canonical => self.canonical,
           :hybrid => hybrid,
           :details => self.details,
+          :parser_run => self.parser_run,
           :positions => self.pos
           })
       else

data/spec/parser/scientific_name_canonical.spec.rb

@@ -6,8 +6,7 @@ describe ScientificNameCanonical do
   before(:all) do
     set_parser(ScientificNameCanonicalParser.new)
   end
-  
-    
+
   it 'should parse names with valid name part and unparseable rest' do
     [
       ['Morea ssjjlajajaj324$33 234243242','Morea', [{:uninomial=>{:string=>"Morea"}}], {0=>["uninomial", 5]}],

data/spec/parser/scientific_name_clean.spec.rb

@@ -97,6 +97,7 @@ describe ScientificNameClean do
       ["Leœptura laetifica Dow, 1913", "Leoeptura laetifica Dow 1913"],
       ['Ærenea cognata Lacordaire, 1872', 'Aerenea cognata Lacordaire 1872'],
       ['Œdicnemus capensis', 'Oedicnemus capensis'],
+      ['Œnanthæ œnanthe','Oenanthae oenanthe'],
       ['Œnanthe œnanthe','Oenanthe oenanthe']
     ]
     names.each do |name_pair|
@@ -105,19 +106,13 @@ describe ScientificNameClean do
     end
   end
   
-  it 'should parse names with "common" utf-8 charactes' do
-    names = ["Rühlella","Sténométope laevissimus Bibron 1855"].each do |name|
-      parse(name).should_not be_nil
-    end
-    sn = "Trematosphaeria phaeospora (E. Müll.)         L.             Holm 1957"
-    parse(sn).should_not be_nil
-    value(sn).should == "Trematosphaeria phaeospora (E. Müll.) L. Holm 1957"
-    canonical(sn).should == "Trematosphaeria phaeospora"
-    details(sn).should == [{:genus=>{:string=>"Trematosphaeria"}, :species=>{:string=>"phaeospora", :authorship=>"(E. Müll.)         L.             Holm 1957", :combinationAuthorTeam=>{:authorTeam=>"L.             Holm", :author=>["L. Holm"], :year=>"1957"}, :basionymAuthorTeam=>{:authorTeam=>"E. Müll.", :author=>["E. Müll."]}}}]
-    pos(sn).should == {0=>["genus", 15], 16=>["species", 26], 28=>["author_word", 30], 31=>["author_word", 36], 46=>["author_word", 48], 61=>["author_word", 65], 66=>["year", 70]}
-    
+  it 'should parse names with e-umlaut' do
+   sn = 'Kalanchoë tuberosa'
+   canonical(sn).should == 'Kalanchoë tuberosa'
+   sn = 'Isoëtes asplundii H. P. Fuchs'
+   canonical(sn).should == 'Isoëtes asplundii'
   end
-    
+
   it 'should parse infragenus (ICZN code)' do
     sn = "Hegeter (Hegeter) intercedens Lindberg H 1950"
     parse(sn).should_not be_nil
@@ -298,6 +293,8 @@ describe ScientificNameClean do
     sn = 'Latrodectus 3guttatus Thorell, 1875'
     canonical(sn).should == 'Latrodectus 3-guttatus'
     value(sn).should == 'Latrodectus 3-guttatus Thorell 1875'
+    sn = 'Balaninus c-album Schönherr, CJ., 1836'
+    canonical(sn).should == 'Balaninus c-album'
   end
 
   it "should parse name with morph." do
@@ -448,13 +445,13 @@ describe ScientificNameClean do
   end
   
   it 'should parse names with taxon concept' do
-    sn = "Sténométope laevissimus sec. Eschmeyer 2004"
+    sn = "Stenometope laevissimus sec. Eschmeyer 2004"
     val = @parser.failure_reason.to_s.match(/column [0-9]*/).to_s().gsub(/column /,'')
-    details(sn).should == [{:genus=>{:string=>"Sténométope"}, :species=>{:string=>"laevissimus"}, :taxon_concept=>{:authorship=>"Eschmeyer 2004", :basionymAuthorTeam=>{:authorTeam=>"Eschmeyer", :author=>["Eschmeyer"], :year=>"2004"}}}]
+    details(sn).should == [{:genus=>{:string=>"Stenometope"}, :species=>{:string=>"laevissimus"}, :taxon_concept=>{:authorship=>"Eschmeyer 2004", :basionymAuthorTeam=>{:authorTeam=>"Eschmeyer", :author=>["Eschmeyer"], :year=>"2004"}}}]
     pos(sn).should == {0=>["genus", 11], 12=>["species", 23], 29=>["author_word", 38], 39=>["year", 43]}
-    sn = "Sténométope laevissimus Bibron 1855 sec. Eschmeyer 2004"
+    sn = "Stenometope laevissimus Bibron 1855 sec. Eschmeyer 2004"
     parse(sn).should_not be_nil
-    details(sn).should == [{:genus=>{:string=>"Sténométope"}, :species=>{:string=>"laevissimus", :authorship=>"Bibron 1855", :basionymAuthorTeam=>{:authorTeam=>"Bibron", :author=>["Bibron"], :year=>"1855"}}, :taxon_concept=>{:authorship=>"Eschmeyer 2004", :basionymAuthorTeam=>{:authorTeam=>"Eschmeyer", :author=>["Eschmeyer"], :year=>"2004"}}}]
+    details(sn).should == [{:genus=>{:string=>"Stenometope"}, :species=>{:string=>"laevissimus", :authorship=>"Bibron 1855", :basionymAuthorTeam=>{:authorTeam=>"Bibron", :author=>["Bibron"], :year=>"1855"}}, :taxon_concept=>{:authorship=>"Eschmeyer 2004", :basionymAuthorTeam=>{:authorTeam=>"Eschmeyer", :author=>["Eschmeyer"], :year=>"2004"}}}]
     pos(sn).should == {0=>["genus", 11], 12=>["species", 23], 24=>["author_word", 30], 31=>["year", 35], 41=>["author_word", 50], 51=>["year", 55]}
   end
   
@@ -462,6 +459,15 @@ describe ScientificNameClean do
     parse("   Asplenium X inexpectatum (E.L. Braun 1940) Morton (1956)   ").should_not be_nil
   end
   
+  it 'should parse names with any number of spaces' do 
+    sn = "Trematosphaeria phaeospora (E. Müll.)         L.             Holm 1957"
+    parse(sn).should_not be_nil
+    value(sn).should == "Trematosphaeria phaeospora (E. Müll.) L. Holm 1957"
+    canonical(sn).should == "Trematosphaeria phaeospora"
+    details(sn).should == [{:genus=>{:string=>"Trematosphaeria"}, :species=>{:string=>"phaeospora", :authorship=>"(E. Müll.)         L.             Holm 1957", :combinationAuthorTeam=>{:authorTeam=>"L.             Holm", :author=>["L. Holm"], :year=>"1957"}, :basionymAuthorTeam=>{:authorTeam=>"E. Müll.", :author=>["E. Müll."]}}}]
+    pos(sn).should == {0=>["genus", 15], 16=>["species", 26], 28=>["author_word", 30], 31=>["author_word", 36], 46=>["author_word", 48], 61=>["author_word", 65], 66=>["year", 70]}
+  end
+  
   it 'should not parse serveral authors groups with several years NOT CORRECT' do
     parse("Pseudocercospora dendrobii (H.C. Burnett 1883) (Leight.) (Movss. 1967) U. Braun & Crous 2003").should be_nil
   end
@@ -469,23 +475,17 @@ describe ScientificNameClean do
   it "should not parse unallowed utf-8 chars in name part" do
     parse("Érematosphaeria phaespora").should be_nil
     parse("Trematosphaeria phaeáapora").should be_nil
-    parse("Trematоsphaeria phaeáapora").should be_nil #cyrillic o
+    parse("Trematоsphaeria phaeaapora").should be_nil #cyrillic o
   end
 
   it "should parse new stuff" do
     sn = 'Nesticus quelpartensis Paik & Namkung, in Paik, Yaginuma & Namkung, 1969'
     details(sn).should == [{:genus=>{:string=>"Nesticus"}, :species=>{:string=>"quelpartensis", :authorship=>"Paik & Namkung, in Paik, Yaginuma & Namkung, 1969", :basionymAuthorTeam=>{:authorTeam=>"Paik & Namkung", :author=>["Paik", "Namkung"], :exAuthorTeam=>{:authorTeam=>"Paik, Yaginuma & Namkung", :author=>["Paik", "Yaginuma", "Namkung"], :year=>"1969"}}}}]
     parse('Dipoena yoshidai Ono, in Ono et al., 1991').should_not be_nil
-    sn = 'Choriozopella trägårdhi Lawrence, 1947'
-    details(sn).should == [{:genus=>{:string=>"Choriozopella"}, :species=>{:string=>"trägårdhi", :authorship=>"Lawrence, 1947", :basionymAuthorTeam=>{:authorTeam=>"Lawrence", :author=>["Lawrence"], :year=>"1947"}}}]
     sn = 'Latrodectus mactans bishopi Kaston, 1938'
     details(sn).should == [{:genus=>{:string=>"Latrodectus"}, :species=>{:string=>"mactans"}, :infraspecies=>[{:string=>"bishopi", :rank=>"n/a", :authorship=>"Kaston, 1938", :basionymAuthorTeam=>{:authorTeam=>"Kaston", :author=>["Kaston"], :year=>"1938"}}]}]
     sn = 'Diplocephalus aff. procerus Thaler, 1972'
     details(sn).should == [{:genus=>{:string=>"Diplocephalus"}, :species=>{:string=>"procerus", :authorship=>"Thaler, 1972", :basionymAuthorTeam=>{:authorTeam=>"Thaler", :author=>["Thaler"], :year=>"1972"}}}]
-    sn = 'Dyarcyops birói Kulczynski, 1908'
-    details(sn).should == [{:genus=>{:string=>"Dyarcyops"}, :species=>{:string=>"birói", :authorship=>"Kulczynski, 1908", :basionymAuthorTeam=>{:authorTeam=>"Kulczynski", :author=>["Kulczynski"], :year=>"1908"}}}]
-    sn = 'Sparassus françoisi Simon, 1898'
-    details(sn).should == [{:genus=>{:string=>"Sparassus"}, :species=>{:string=>"françoisi", :authorship=>"Simon, 1898", :basionymAuthorTeam=>{:authorTeam=>"Simon", :author=>["Simon"], :year=>"1898"}}}]
     sn = 'Thiobacillus x Parker and Prisk 1953' #have to figure out black lists for this one
     sn = 'Bacille de Plaut, Kritchevsky and Séguin 1921'
     details(sn).should == [{:uninomial=>{:string=>"Bacille", :authorship=>"de Plaut, Kritchevsky and Séguin 1921", :basionymAuthorTeam=>{:authorTeam=>"de Plaut, Kritchevsky and Séguin", :author=>["de Plaut", "Kritchevsky", "Séguin"], :year=>"1921"}}}]
@@ -501,4 +501,26 @@ describe ScientificNameClean do
     details(sn).should == [{:genus=>{:string=>"Flexibacter"}, :species=>{:string=>"elegans", :authorship=>"Soriano 1945, non Lewin 1969", :basionymAuthorTeam=>{:authorTeam=>"Soriano", :author=>["Soriano"], :year=>"1945"}}}]
   end
   
+  # it 'should parse hybrid names with capitalized second name in genus (botanical code error)' do
+  #   sn = 'Anacampti-Platanthera P. Fourn.'
+  #   @parser.parse(sn)
+  #   puts @parser.failure_reason
+  #   parse(sn).should_not be_nil
+  #   canonical(sn).should == 'Anacamptiplatanthera'
+  #   sn = 'Anacampti-Platanthera vulgaris P. Fourn.'
+  #   parse(sn).should_not be_nil
+  #   canonical(sn).should == 'Anacamptiplatanthera'
+  # end
+
+  # it 'shoud parse hybrid names with * character' do 
+  #   sn = "Carduus acanthoides * crispus"
+  #   details(sn).should == ''
+  # end
+    
+  it 'should parse genus names starting with uppercase letters AE OE' do
+    sn = 'AEmona separata Broun 1921'
+    canonical(sn).should == 'Aemona separata'
+    sn = 'OEmona simplex White, 1855'
+    canonical(sn).should == 'Oemona simplex'
+  end
 end

data/spec/parser/scientific_name_dirty.spec.rb

@@ -7,7 +7,6 @@ describe ScientificNameDirty do
    set_parser(ScientificNameDirtyParser.new)
   end
   
-
   it 'should parse clean names' do
     parse("Betula verucosa (L.) Bar. 1899").should_not be_nil
   end
@@ -85,6 +84,23 @@ describe ScientificNameDirty do
     details('Oscillaria caviae Simons 1920, according to Simons 1922').should == [{:genus=>{:string=>"Oscillaria"}, :species=>{:string=>"caviae", :authorship=>"Simons 1920", :basionymAuthorTeam=>{:authorTeam=>"Simons", :author=>["Simons"], :year=>"1920"}}}]
     sn = 'Bacterium monocytogenes hominis"" Nyfeldt 1932'
     details(sn).should == [{:genus=>{:string=>"Bacterium"}, :species=>{:string=>"monocytogenes"}, :infraspecies=>[{:string=>"hominis", :rank=>"n/a"}]}]
+    sn = 'Choriozopella trägårdhi Lawrence, 1947'
+    details(sn).should == [{:genus=>{:string=>"Choriozopella"}, :species=>{:string=>"tragardhi", :authorship=>"Lawrence, 1947", :basionymAuthorTeam=>{:authorTeam=>"Lawrence", :author=>["Lawrence"], :year=>"1947"}}}]
+    sn = 'Sparassus françoisi Simon, 1898'
+    details(sn).should == [{:genus=>{:string=>"Sparassus"}, :species=>{:string=>"francoisi", :authorship=>"Simon, 1898", :basionymAuthorTeam=>{:authorTeam=>"Simon", :author=>["Simon"], :year=>"1898"}}}]
+    sn = 'Dyarcyops birói Kulczynski, 1908'
+    details(sn).should == [{:genus=>{:string=>"Dyarcyops"}, :species=>{:string=>"biroi", :authorship=>"Kulczynski, 1908", :basionymAuthorTeam=>{:authorTeam=>"Kulczynski", :author=>["Kulczynski"], :year=>"1908"}}}]
+  end
+  
+  it 'should parse names with "common" utf-8 charactes' do
+    names = ["Rühlella","Sténométope laevissimus Bibron 1855"].each do |name|
+      parse(name).should_not be_nil
+    end
   end
   
+# AsterophUa japonica
+# AsyTuktus ridiculw Parent 1931
+# AtremOEa Staud 1870
+
+
 end