dwc-archive 0.4.13 → 0.4.14

data/VERSION

@@ -1 +1 @@
-0.4.13
+0.4.14

data/lib/dwc-archive/classification_normalizer.rb

@@ -27,7 +27,7 @@ class DarwinCore
 
     def initialize(dwc_instance, verbose = false)
       @dwc = dwc_instance
-      @core = get_fields(@dwc.core)
+      @core_fields = get_fields(@dwc.core)
       @extensions = @dwc.extensions.map { |e| [e, get_fields(e)] }
       @res = {}
       @parser = ParsleyStore.new(1,2)
@@ -56,7 +56,7 @@ class DarwinCore
 
   private
 
-    def canonical_name(a_scientific_name)
+    def get_canonical_name(a_scientific_name)
       if R19
         a_scientific_name.force_encoding('utf-8')
       end
@@ -84,38 +84,47 @@ class DarwinCore
     def add_synonym_from_core(taxon_id, row)
       taxon = @res[row[taxon_id]] ? @res[row[taxon_id]] : @res[row[taxon_id]] = DarwinCore::TaxonNormalized.new
       taxon.synonyms << SynonymNormalized.new(
-        row[@core[:scientificname]], 
-        canonical_name(row[@core[:scientificname]]), 
-        @core[:taxonomicstatus] ? row[@core[:taxonomicstatus]] : nil)
+        row[@core_fields[:scientificname]], 
+        row[@core_fields[:canonicalname]], 
+        @core_fields[:taxonomicstatus] ? row[@core_fields[:taxonomicstatus]] : nil)
+    end
+
+    def set_scientific_name(row, fields)
+      canonical_name = fields[:scientificnameauthorship] ? row[fields[:scientificname]] : get_canonical_name(row[fields[:scientificname]])
+      fields[:canonicalname] = row.size
+      row << canonical_name
+      scientific_name = (fields[:scientificnameauthorship] && row[fields[:scientificnameauthorship]].to_s.strip != '') ? row[fields[:scientificname]].strip + ' ' + row[fields[:scientificnameauthorship]].strip : row[fields[:scientificname]].strip
+      row[fields[:scientificname]] = scientific_name
     end
 
     def ingest_core
-      raise RuntimeError, "Darwin Core core fields must contain taxon id and scientific name" unless (@core[:id] && @core[:scientificname])
+      raise RuntimeError, "Darwin Core core fields must contain taxon id and scientific name" unless (@core_fields[:id] && @core_fields[:scientificname])
       puts "Reading core information" if @verbose
       rows = @dwc.core.read[0]
       puts "Ingesting information from the core" if @verbose
       rows.each_with_index do |r, i|
         count = i + 1
+        set_scientific_name(r, @core_fields)
         puts "Ingesting %s'th record" % count if @verbose and count % @verbose_count == 0
         #core has AcceptedNameUsageId
-        if @core[:acceptednameusageid] && r[@core[:acceptednameusageid]] && r[@core[:acceptednameusageid]] != r[@core[:id]]
-          add_synonym_from_core(@core[:acceptednameusageid], r)
-        elsif !@core[:acceptednameusageid] && status_synonym?(r[@core[:taxonomicstatus]])
+        if @core_fields[:acceptednameusageid] && r[@core_fields[:acceptednameusageid]] && r[@core_fields[:acceptednameusageid]] != r[@core_fields[:id]]
+          add_synonym_from_core(@core_fields[:acceptednameusageid], r)
+        elsif !@core_fields[:acceptednameusageid] && status_synonym?(r[@core_fields[:taxonomicstatus]])
           add_synonym_from_core(parent_id, r)
         else
-          taxon = @res[r[@core[:id]]] ? @res[r[@core[:id]]] : @res[r[@core[:id]]] = DarwinCore::TaxonNormalized.new
-          taxon.id = r[@core[:id]]
-          taxon.current_name = r[@core[:scientificname]]
-          taxon.current_name_canonical = canonical_name(r[@core[:scientificname]])
+          taxon = @res[r[@core_fields[:id]]] ? @res[r[@core_fields[:id]]] : @res[r[@core_fields[:id]]] = DarwinCore::TaxonNormalized.new
+          taxon.id = r[@core_fields[:id]]
+          taxon.current_name = r[@core_fields[:scientificname]]
+          taxon.current_name_canonical = r[@core_fields[:canonicalname]]
           taxon.parent_id = r[parent_id] 
-          taxon.rank = r[@core[:taxonrank]] if @core[:taxonrank]
-          taxon.status = r[@core[:taxonomicstatus]] if @core[:taxonomicstatus]
+          taxon.rank = r[@core_fields[:taxonrank]] if @core_fields[:taxonrank]
+          taxon.status = r[@core_fields[:taxonomicstatus]] if @core_fields[:taxonomicstatus]
         end
       end
     end
     
     def parent_id
-      parent_id_field = @core[:highertaxonid] || @core[:parentnameusageid]
+      parent_id_field = @core_fields[:highertaxonid] || @core_fields[:parentnameusageid]
     end
 
     def calculate_classification_path
@@ -172,10 +181,11 @@ class DarwinCore
       ext, fields = *extension
       ext.read[0].each_with_index do |r, i|
         count = i + 1
+        set_scientific_name(r, fields)
         puts "Ingesting %s'th record" % count if @verbose && count % @verbose_count == 0
         @res[r[fields[:id]]].synonyms << SynonymNormalized.new(
           r[fields[:scientificname]], 
-          canonical_name(r[fields[:scientificname]]), 
+          r[fields[:canonicalname]], 
           fields[:taxonomicstatus] ? r[fields[:taxonomicstatus]] : nil)
       end
     end

data/spec/lib/dwc-archive_spec.rb

@@ -98,6 +98,17 @@ describe DarwinCore do
       norm = dwc.normalize_classification
       norm.select { |k,v| !v.synonyms.empty? }.map { |k,v| v.synonyms }.size.should > 0
     end
+
+    it "should be able work with files which have scientificNameAuthorship" do
+      file = File.join(@file_dir, 'sci_name_authorship.tar.gz')
+      dwc = DarwinCore.new(file)
+      $lala = 1
+      norm = dwc.normalize_classification
+      taxa = norm.select{|k,v| v.current_name_canonical.match " "}.select{|k,v| [v.current_name.split(" ").size >  v.current_name_canonical.split(" ").size]}
+      taxa.size.should == 507
+      syn = norm.select{|k,v| v.synonyms.size > 0}.map {|k,v| v.synonyms}.flatten.select {|s| s.name.split(" ").size  > s.canonical_name.split(" ").size}
+      syn.size.should == 50
+    end
   end
 
 end

metadata

@@ -1,12 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: dwc-archive
 version: !ruby/object:Gem::Version 
+  hash: 19
   prerelease: false
   segments: 
   - 0
   - 4
-  - 13
-  version: 0.4.13
+  - 14
+  version: 0.4.14
 platform: ruby
 authors: 
 - Dmitry Mozzherin
@@ -14,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-10-07 00:00:00 -04:00
+date: 2010-10-08 00:00:00 -04:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -25,6 +26,7 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        hash: 3
         segments: 
         - 0
         version: "0"
@@ -38,6 +40,7 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        hash: 13
         segments: 
         - 1
         - 2
@@ -53,6 +56,7 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        hash: 3
         segments: 
         - 0
         version: "0"
@@ -104,6 +108,7 @@ files:
 - spec/files/junk_dir_inside.zip
 - spec/files/meta.xml
 - spec/files/minimal.tar.gz
+- spec/files/sci_name_authorship.tar.gz
 - spec/files/synonyms_in_core_accepted_name_field.tar.gz
 - spec/files/synonyms_in_extension.tar.gz
 - spec/files/uncompressed
@@ -125,6 +130,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
       segments: 
       - 0
       version: "0"
@@ -133,6 +139,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
       segments: 
       - 0
       version: "0"