biodiversity19 1.2.0 → 2.0.0

data/.rvmrc

@@ -1 +1 @@
-rvm use ruby-1.9.3-p194@biodiversity --create
+rvm use ruby-1.9.3-p392@biodiversity --create

data/CHANGELOG

@@ -1,3 +1,11 @@
+2.0.0 -- backward incompatibe change in parserver, therefore new major number.
+In parserver removed option --output=canonical_with_rank, instead added -r
+option which allows to have canonical with rank with either json or canonical 
+outputs
+
+1.2.0 -- changed method invocation signature ScientificNameParser.new 
+Now it can take options
+
 1.1.3 -- added 'fo' as rank
 
 1.1.2  -- static method for fixins all-caps canonical names, fixing caps 

data/README.rdoc

@@ -31,14 +31,14 @@ options:
 
 to return a canonical form of the name string
 
-  parserver --output=canonical_with_rank
-
-the same as above, but infraspecies' rank is shown if available
-
   parserver --port 5555
 
 run socket server on a different port
 
+  parserver --canonical_with_rank
+
+to add rank to canonical forms with infraspecific epithet, if it is given
+
 Then you can access it via 4334 port using a socket client library of your programming language.  You can find socket client script example in the examples directory of the gem.
 
 If you want to check if socket server works for you:

data/Rakefile

@@ -63,4 +63,3 @@ task :tt do
     `mv #{rf}.tmp #{rf}`
   end
 end
-

data/VERSION

@@ -1 +1 @@
-1.2.0
+2.0.0

data/bin/parserver

@@ -5,10 +5,11 @@ require 'socket'
 require 'biodiversity'          # Get sockets from stdlib
 
 DEFAULT_PORT = 4334
-RUBY_VERSION_INT = RUBY_VERSION.split(".")[0..1].join('').to_i
+RUBY_VERSION_INT = RUBY_VERSION.split('.')[0..1].join('').to_i
 OPTIONS = {
-  :output => "json",
-  :port => DEFAULT_PORT
+  output: 'json',
+  canonical_with_rank: false, 
+  port: DEFAULT_PORT
 }
 
 options = {}
@@ -16,67 +17,55 @@ ARGV.options do |opts|
   script_name = File.basename($0)
   opts.banner = "Usage: ruby #{script_name} [options]"
 
-  opts.separator ""
+  opts.separator ''
 
-  opts.on("-o", "--output=output", String,
-          "Specifies the type of the output:
+  opts.on('-r', 
+          '--canonical_with_rank', 
+          'Adds infraspecies rank to canonical forms'
+          ) { |rank| options[:canonical_with_rank] = rank }
+
+  opts.separator ''
+
+  opts.on('-o', '--output=output', String,
+          'Specifies the type of the output:
     json - parsed results in json
-    canonical - canonical version
-    canonical_with_rank - canonical with rank",
-          "Default: json") { |output| options[:output] = output }
+    canonical - canonical form only',
+          'Default: json') { |output| options[:output] = output }
 
-  opts.separator ""
+  opts.separator ''
 
-  opts.on("-p", "--port=port", String,
-          "Specifies the port number",
+  opts.on('-p', '--port=port', String,
+          'Specifies the port number',
           "Default: #{DEFAULT_PORT}") { |port| options[:port] = port }
 
-  opts.separator ""
+  opts.separator ''
 
-  opts.on("-h", "--help",
-          "Show this help message.") { puts opts; exit }
+  opts.on('-h', '--help',
+          'Show this help message.') { puts opts; exit }
 
   opts.parse!
 end
 
-OPTIONS[:output] = options[:output] if ['canonical', 'canonical_with_rank'].include?(options[:output])
+OPTIONS[:output] = options[:output] if ['canonical'].include?(options[:output])
 OPTIONS[:port] = options[:port].to_i if options[:port].to_i > 0
-
-def parser_error(name_string)
-  {:scientificName => {:parsed => false, :verbatim => name_string,  :error => 'Parser error'}}
-end
+OPTIONS[:canonical_with_rank] = !!options[:canonical_with_rank]
 
 def get_output(name_string, parser)
   begin
-    if RUBY_VERSION_INT < 19
-      old_kcode = $KCODE
-      $KCODE = 'NONE'
-    end
     parsed = parser.parse(name_string)
-    if RUBY_VERSION_INT < 19
-      $KCODE = old_kcode
-    end
   rescue
-    parsed = parser_error(name_string)
+    parsed = ScientificNameParser::FAILED_RESULT.(name_string)
   end
   output =  OPTIONS[:output]
   return parsed.to_json if output == 'json'
-  canonical = parsed[:scientificName][:canonical]
-  return canonical.to_s if output == 'canonical' || canonical == nil || parsed[:scientificName][:hybrid] || !parsed[:scientificName][:parsed]
-  parts = parsed[:scientificName][:canonical].split(" ")
-
-  if parts.size > 2 && parsed[:scientificName][:details][0][:infraspecies]
-    name_ary = parts[0..1]
-    parsed[:scientificName][:details][0][:infraspecies].each do |data|
-      name_ary << (data[:rank] && data[:rank] != 'n/a'? "#{data[:rank]} #{data[:string]}" : data[:string])
-    end
-    canonical = name_ary.join(" ")
-  end
-  canonical
+  parsed[:scientificName][:canonical].to_s
 end
 
-puts "Running parser service on port #{OPTIONS[:port]}, output type is '#{OPTIONS[:output]}'"
-parser = ScientificNameParser.new
+puts "Running parser service on port %s, output type is '%s'" % 
+     [OPTIONS[:port], OPTIONS[:output]]
+opts = {}
+opts = {canonical_with_rank: true} if OPTIONS[:canonical_with_rank]
+parser = ScientificNameParser.new(opts)
 server = TCPServer.open(OPTIONS[:port])  # Socket to listen on a port
 loop do                         # Servers run forever
   Thread.start(server.accept) do |client|
@@ -85,7 +74,7 @@ loop do                         # Servers run forever
     while a = client.readline rescue nil
       count += 1
       puts "parsed %s'th name" % count if count % 1000 == 0
-      a.force_encoding("utf-8") if a && RUBY_VERSION_INT >= 19
+      a.force_encoding('utf-8') if a && RUBY_VERSION_INT >= 19
       if ['end','exit','q', '.'].include? a.strip
         client.close
         break

data/lib/biodiversity/parser.rb

@@ -15,7 +15,8 @@ module PreProcessor
   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|
+    [NOTES, TAXON_CONCEPTS1, TAXON_CONCEPTS2, 
+     TAXON_CONCEPTS3, NOMEN_CONCEPTS, LAST_WORD_JUNK].each do |i|
       a_string = a_string.gsub(i, '')
     end
     a_string = a_string.tr('ſ','s') #old 's'
@@ -49,10 +50,7 @@ class ParallelParser
   private
   def parse_process(name)
     p = ScientificNameParser.new
-    failed_res = { scientificName: { parsed: false, 
-                                     verbatim: name,  
-                                     error: 'Parser error' } }
-    p.parse(name) rescue failed_res 
+    p.parse(name) rescue ScientificNameParser::FAILED_RESULT.(name)
   end
 end
 
@@ -73,6 +71,12 @@ class ScientificNameParser
                            '..',
                            '..',
                            'VERSION')).readline.strip
+
+  FAILED_RESULT = ->(name) do
+    { scientificName: 
+      { parsed: false, verbatim: name.to_s.strip,  error: 'Parser error' } 
+    }
+  end
   
   def self.fix_case(name_string)
     name_ary = name_string.split(/\s+/)
@@ -87,17 +91,21 @@ class ScientificNameParser
       end
     else
       if name_ary[0].size > 1
-        word1 = UnicodeUtils.upcase(name_ary[0][0]) + UnicodeUtils.downcase(name_ary[0][1..-1])
+        word1 = UnicodeUtils.upcase(name_ary[0][0]) + 
+          UnicodeUtils.downcase(name_ary[0][1..-1])
       else
         word1 = name_ary[0]
       end
       if name_ary[1].match(/^\(/)
-        word2 = name_ary[1].gsub(/\)$/, '') + ")"
-        word2 = word2[0] + UnicodeUtils.upcase(word2[1]) + UnicodeUtils.downcase(word2[2..-1])
+        word2 = name_ary[1].gsub(/\)$/, '') + ')'
+        word2 = word2[0] + UnicodeUtils.upcase(word2[1]) + 
+          UnicodeUtils.downcase(word2[2..-1])
       else
         word2 = UnicodeUtils.downcase(name_ary[1])
       end
-      res = word1 + " " + word2 + " " + name_ary[2..-1].map { |w| UnicodeUtils.downcase(w) }.join(" ")
+      res = word1 + ' ' + 
+        word2 + ' ' + 
+        name_ary[2..-1].map { |w| UnicodeUtils.downcase(w) }.join(' ')
       res.strip!
     end
     res
@@ -114,7 +122,9 @@ class ScientificNameParser
   end
 
   def virus?(a_string)
-    !!(a_string.match(/\sICTV\s*$/) || a_string.match(/\b(virus|viruses|phage|phages|viroid|viroids|satellite|satellites|prion|prions)\b/i) || a_string.match(/[A-Z]?[a-z]+virus\b/))
+    !!(a_string.match(/\sICTV\s*$/) || 
+       a_string.match(/\b(virus|viruses|phage|phages|viroid|viroids|satellite|satellites|prion|prions)\b/i) || 
+       a_string.match(/[A-Z]?[a-z]+virus\b/))
   end
 
   def unknown_placement?(a_string)
@@ -126,13 +136,13 @@ class ScientificNameParser
   end
   
   def parse(a_string)
-    @verbatim = a_string
+    @verbatim = a_string.strip
     a_string = PreProcessor::clean(a_string)
     
     if virus?(a_string)
-      @parsed = { :verbatim => a_string, :virus => true }
+      @parsed = { verbatim: a_string, virus: true }
     elsif unknown_placement?(a_string)
-      @parsed = { :verbatim => a_string }
+      @parsed = { verbatim: a_string }
     else
       begin
         @parsed = @clean.parse(a_string) || @dirty.parse(a_string) 
@@ -140,12 +150,12 @@ class ScientificNameParser
           index = @dirty.index || @clean.index
           salvage_match = a_string[0..index].split(/\s+/)[0..-2]
           salvage_string = salvage_match ? salvage_match.join(' ') : a_string
-          @parsed =  @dirty.parse(salvage_string) || @canonical.parse(a_string) || { :verbatim => a_string }
+          @parsed =  @dirty.parse(salvage_string) || 
+                     @canonical.parse(a_string) || 
+                     { verbatim: a_string }
         end
       rescue
-        @parsed = { scientificName: { parsed: false, 
-                                      verbatim: name,  
-                                      error: 'Parser error' } }
+        @parsed = FAILED_RESULT.(@verbatim)
       end
     end
 
@@ -156,22 +166,24 @@ class ScientificNameParser
     def @parsed.all(opts = {})
       canonical_with_rank = !!opts[:canonical_with_rank]
       parsed = self.class != Hash
-      res = { :parsed => parsed, :parser_version => ScientificNameParser::VERSION}
+      res = { parsed: parsed, parser_version: ScientificNameParser::VERSION}
       if parsed
         hybrid = self.hybrid rescue false
         res.merge!({
-          :verbatim => @verbatim,
-          :normalized => self.value,
-          :canonical => self.canonical,
-          :hybrid => hybrid,
-          :details => self.details,
-          :parser_run => self.parser_run,
-          :positions => self.pos
+          verbatim: @verbatim,
+          normalized: self.value,
+          canonical: self.canonical,
+          hybrid: hybrid,
+          details: self.details,
+          parser_run: self.parser_run,
+          positions: self.pos
           })
       else
         res.merge!(self)
       end
-      if canonical_with_rank && canonical.count(" ") > 1 && res[:details][0][:infraspecies]
+      if (canonical_with_rank && 
+          canonical.count(' ') > 1 && 
+          res[:details][0][:infraspecies])
         ScientificNameParser.add_rank_to_canonical(res)
       end
       res = {:scientificName => res}
@@ -192,14 +204,14 @@ class ScientificNameParser
   private
 
   def self.add_rank_to_canonical(parsed)
-    parts = parsed[:canonical].split(" ")
+    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(" ")
+    parsed[:canonical] = name_ary.join(' ')
   end
   
 end

data/spec/parser/scientific_name.spec.rb

@@ -123,7 +123,7 @@ describe ParallelParser do
     res = pparser.parse(names)
     names.each_with_index do |name, i|
       res[name].is_a?(Hash).should be_true
-      res[name][:scientificName][:verbatim].should == name
+      res[name][:scientificName][:verbatim].should == name.strip
     end
   end
 end

data/spec/parser/test_data.txt

@@ -276,8 +276,8 @@ Coeloglossum viride (L.) Hartman x Dactylorhiza majalis (Rchb. f.) P.F. Hunt & S
 Polypodium  x vulgare nothosubsp. mantoniae (Rothm.) Schidlay|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Polypodium  x vulgare nothosubsp. mantoniae (Rothm.) Schidlay", "normalized":"Polypodium × vulgare nothosubsp. mantoniae (Rothm.) Schidlay", "canonical":"Polypodium vulgare mantoniae", "hybrid":true, "details":[{"genus":{"string":"Polypodium"}, "species":{"string":"vulgare"}, "infraspecies":[{"string":"mantoniae", "rank":"nothosubsp.", "authorship":"(Rothm.) Schidlay", "combinationAuthorTeam":{"authorTeam":"Schidlay", "author":["Schidlay"]}, "basionymAuthorTeam":{"authorTeam":"Rothm.", "author":["Rothm."]}}]}], "parser_run":1, "positions":{"0":["genus", 10], "14":["species", 21], "22":["infraspecific_type", 33], "34":["infraspecies", 43], "45":["author_word", 51], "53":["author_word", 61]}}}
 
 #empty spaces
-    Asplenium       Xinexpectatum(E. L. Braun ex Friesner      )Morton   |{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"    Asplenium       Xinexpectatum(E. L. Braun ex Friesner      )Morton   ", "normalized":"Asplenium × inexpectatum (E. L. Braun ex Friesner) Morton", "canonical":"Asplenium inexpectatum", "hybrid":true, "details":[{"genus":{"string":"Asplenium"}, "species":{"string":"inexpectatum", "authorship":"(E. L. Braun ex Friesner      )Morton", "combinationAuthorTeam":{"authorTeam":"Morton", "author":["Morton"]}, "basionymAuthorTeam":{"authorTeam":"E. L. Braun", "author":["E. L. Braun"], "exAuthorTeam":{"authorTeam":"Friesner", "author":["Friesner"]}}}}], "parser_run":1, "positions":{"4":["genus", 13], "21":["species", 33], "34":["author_word", 36], "37":["author_word", 39], "40":["author_word", 45], "49":["author_word", 57], "64":["author_word", 70]}}}
-   
+    Asplenium       Xinexpectatum(E. L. Braun ex Friesner      )Morton   |{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Asplenium       Xinexpectatum(E. L. Braun ex Friesner      )Morton", "normalized":"Asplenium × inexpectatum (E. L. Braun ex Friesner) Morton", "canonical":"Asplenium inexpectatum", "hybrid":true, "details":[{"genus":{"string":"Asplenium"}, "species":{"string":"inexpectatum", "authorship":"(E. L. Braun ex Friesner      )Morton", "combinationAuthorTeam":{"authorTeam":"Morton", "author":["Morton"]}, "basionymAuthorTeam":{"authorTeam":"E. L. Braun", "author":["E. L. Braun"], "exAuthorTeam":{"authorTeam":"Friesner", "author":["Friesner"]}}}}], "parser_run":1, "positions":{"4":["genus", 13], "21":["species", 33], "34":["author_word", 36], "37":["author_word", 39], "40":["author_word", 45], "49":["author_word", 57], "64":["author_word", 70]}}}
+  
 ####
 #
 # Names with problems

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: biodiversity19
 version: !ruby/object:Gem::Version
-  version: 1.2.0
+  version: 2.0.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-03-11 00:00:00.000000000 Z
+date: 2013-03-12 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: 3489764594482913391
+      hash: -2248676907984019850
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: