biodiversity19 0.5.15

data/lib/biodiversity/parser/scientific_name_dirty.treetop

@@ -0,0 +1,211 @@
+# encoding: UTF-8
+grammar ScientificNameDirty
+  include ScientificNameClean
+
+  rule root
+    super
+  end
+
+  rule scientific_name_5
+    a:scientific_name_4 garbage {
+      def value
+        a.value
+      end
+      
+      def canonical
+        a.canonical
+      end
+      
+      def pos
+        a.pos
+      end
+      
+      def details
+        a.details
+      end
+    }
+    /
+    super
+  end
+  
+  rule infraspecies
+    a:infraspecies_string space b:year {
+      def value
+        a.value + " " + b.value
+      end
+  
+      def canonical
+        a.canonical
+      end
+  
+      def pos
+        a.pos.merge(b.pos)
+      end
+  
+      def details
+        {:infraspecies => a.details[:infraspecies].merge(b.details)}
+      end
+    }
+    /
+    a:infraspecies_string space string_authorship_inconsistencies space b:authorship {
+      def value
+        a.value + " " + b.value
+      end
+  
+      def canonical
+        a.canonical
+      end
+  
+      def pos
+        a.pos.merge(b.pos)
+      end
+  
+      def details
+        {:infraspecies => a.details[:infraspecies].merge(b.details)}
+      end
+    }
+    /
+    super
+  end
+  
+  rule species
+    a:species_string space b:year {
+       def value
+         a.value + " " + b.value
+       end
+     
+       def canonical
+         a.canonical
+       end
+     
+       def pos
+         a.pos.merge(b.pos)
+       end
+     
+       def details
+         {:species => a.details[:species].merge(b.details)}
+       end
+     }
+     /
+     super
+  end
+
+  rule right_paren
+   ")" space ")"
+   /
+   super
+  end
+  
+  rule left_paren
+   "(" space "("
+   /
+   super
+  end
+  
+  rule year
+    a:year_number space b:approximate_year {
+      def value
+        a.value + " " + b.value
+      end
+      
+      def pos
+        a.pos.merge(b.pos)
+      end
+      
+      def details
+        {:year => a.value, :approximate_year => b.value}
+      end
+    }
+    /
+    a:year_number space page_number {
+      def value
+        a.text_value
+      end
+      
+      def pos
+        {a.interval.begin => ['year', a.interval.end]}
+      end
+      
+      def details
+        {:year => value}
+      end
+    }
+    /
+    year_number_with_punctuation
+    /
+    approximate_year
+    /
+    double_year
+    /
+    super
+  end
+  
+  rule approximate_year
+    "[" space a:year_number space "]"+ {
+      def value
+       "(" + a.text_value + ")"
+      end
+      
+      def pos
+        {a.interval.begin => ['year', a.interval.end]}
+      end
+      
+      def details
+        {:approximate_year => value}
+      end
+    }
+  end
+  
+  
+  rule double_year
+    year_number "-" [0-9]+ [A-Za-z]? [\?]? {
+      def value
+        text_value
+      end
+      
+      def pos
+        {interval.begin => ['year', interval.end]}
+      end
+      
+      def details
+        {:year => value}
+      end
+    }
+  end
+  
+  rule year_number_with_punctuation
+    a:year_number "." {
+      def value
+        a.text_value
+      end
+
+      def pos
+        {interval.begin => ['year', interval.end]}
+      end
+
+      def details
+        {:year => value}
+      end
+    }
+  end
+
+  
+  rule page_number
+    ":" space [\d]+
+    {
+      def value
+      end
+    }
+  end
+  
+  rule string_authorship_inconsistencies
+    ("corrig.")
+  end
+  
+  rule garbage
+    space (["',.]) space [^щ]*
+    /
+    space_hard [^ш]+
+  end
+  
+end

data/lib/biodiversity/parser.rb

@@ -0,0 +1,57 @@
+# encoding: UTF-8
+dir = File.dirname(__FILE__)
+require File.join(dir, *%w[parser scientific_name_clean])
+require File.join(dir, *%w[parser scientific_name_dirty])
+require File.join(dir, *%w[parser scientific_name_canonical])
+require 'rubygems'
+require 'json'
+
+class ScientificNameParser
+  
+  def initialize
+    @verbatim = ''
+    @clean = ScientificNameCleanParser.new
+    @dirty = ScientificNameDirtyParser.new
+    @canonical = ScientificNameCanonicalParser.new
+    @parsed = nil
+  end
+  
+  def parsed
+    @parsed
+  end
+  
+  def parse(a_string)
+    @verbatim = a_string
+    @parsed = @clean.parse(a_string) || @dirty.parse(a_string) || @canonical.parse(a_string) || {:verbatim => a_string}
+    def @parsed.all
+      parsed = self.class != Hash
+      res = {:parsed => parsed}
+      if parsed
+        hybrid = self.hybrid rescue false
+        res.merge!({
+          :verbatim => self.text_value,
+          :normalized => self.value,
+          :canonical => self.canonical,
+          :hybrid => hybrid,
+          :details => self.details,
+          :positions => self.pos
+          })
+      else
+        res.merge!(self)
+      end
+      res = {:scientificName => res}
+      res
+    end
+    
+    def @parsed.pos_json
+      self.pos.to_json rescue ''
+    end
+    
+    def @parsed.all_json
+      self.all.to_json rescue ''
+    end
+    
+    @parsed.all
+  end
+end
+

data/lib/biodiversity.rb

@@ -0,0 +1,9 @@
+require 'rubygems'
+require 'treetop'
+
+dir = File.dirname(__FILE__)
+
+BIODIVERSITY_ROOT = File.join(dir, 'biodiversity')
+require File.join(dir, "/../conf/environment")
+require File.join(BIODIVERSITY_ROOT, "parser")
+require File.join(BIODIVERSITY_ROOT, "guid")

data/spec/guid/lsid.spec.rb

@@ -0,0 +1,12 @@
+dir = File.dirname("__FILE__")
+require 'rubygems'
+require 'spec'
+require File.expand_path(dir + "../../conf/environment")
+require File.expand_path(dir + "../../lib/biodiversity/guid")
+
+describe LsidResolver do   
+  it "should return RFD document from lsid" do
+    lsid = "urn:lsid:ubio.org:classificationbank:2232671"
+    LsidResolver.resolve(lsid).class.should == "".class
+  end
+end

data/spec/parser/scientific_name.spec.rb

@@ -0,0 +1,35 @@
+#NOTE: this spec needs compiled treetop files.
+dir = File.dirname("__FILE__")
+require File.expand_path(dir + '../../spec/parser/spec_helper')
+require File.expand_path(dir + '../../lib/biodiversity/parser')
+
+describe ScientificNameClean do
+  before(:all) do
+    set_parser(ScientificNameParser.new)
+  end
+  
+  it 'should generate standardized json' do
+    read_test_file do |y|
+      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')
+  #   read_test_file do |y|
+  #     if y[:comment]
+  #       new_test.write y[:comment]
+  #     else
+  #       name = y[:name]
+  #       jsn = json(y[:name])# rescue puts(y[:name])
+  #       new_test.write("#{name}|#{jsn}\n")
+  #     end
+  #   end
+  # end
+  
+  it 'should generate reasonable output if parser failed' do
+    sn = 'ddd sljlkj 3223452432'
+    json(sn).should == '{"scientificName":{"parsed":false,"verbatim":"ddd sljlkj 3223452432"}}'
+  end
+
+end

data/spec/parser/scientific_name_canonical.spec.rb

@@ -0,0 +1,27 @@
+# encoding: UTF-8
+dir = File.dirname("__FILE__")
+require File.expand_path(dir + '../../spec/parser/spec_helper')
+
+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]}],
+      ['Morea (Morea) Burt 2342343242 23424322342 23424234', 'Morea (Morea)', [{:genus=>{:string=>"Morea"}, :infragenus=>{:string=>"Morea"}}], {0=>["genus", 5], 7=>["infragenus", 12]}],      
+      ['Morea (Morea) burtius 2342343242 23424322342 23424234', 'Morea (Morea) burtius', [{:genus=>{:string=>"Morea"}, :infragenus=>{:string=>"Morea"}, :species=>{:string=>"burtius"}}], {0=>["genus", 5], 7=>["infragenus", 12], 14=>["species", 21]}],
+      ['Moraea spathulata ( (L. f. Klatt','Moraea spathulata',[{:genus=>{:string=>"Moraea"}, :species=>{:string=>"spathulata"}}], {0=>["genus", 6], 7=>["species", 17]} ],
+      ['Verpericola megasoma ""Dall" Pils.','Verpericola megasoma',[{:genus=>{:string=>"Verpericola"}, :species=>{:string=>"megasoma"}}], {0=>["genus", 11], 12=>["species", 20]}] 
+    ].each do |n|
+      parse(n[0]).should_not be_nil
+      value(n[0]).should == n[1]
+      details(n[0]).should == n[2]
+      pos(n[0]).should == n[3]
+      parse(n[0]).hybrid.should be_false
+    end
+  end  
+  
+end