biodiversity19 2.0.0 → 2.1.0

data/.travis.yml

@@ -0,0 +1,6 @@
+rvm:
+  - 1.9.3
+bundler_args: --without development
+branches:
+  only:
+      - master

data/CHANGELOG

@@ -1,14 +1,16 @@
+2.1.0 -- added ScientificNameParser.version method
+
 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 
+option which allows to have canonical with rank with either json or canonical
 outputs
 
-1.2.0 -- changed method invocation signature ScientificNameParser.new 
+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 
+1.1.2  -- static method for fixins all-caps canonical names, fixing caps
 for authors words, ampersand instead of 'et' in normalization
 
 1.1.1  -- more multi-uninomials cases, expanded viruses detection, added
@@ -23,14 +25,14 @@ cf., sp. etc), bug fixes, more robust salvage mode
 
 1.0.15 -- additional rules added for names ending with ssp. sp sp. and cf.
 
-1.0.14 -- canonical forms had allowed ë as a character until now. After this 
-version the only utf-8 character allowed in canonical forms should be the 
+1.0.14 -- canonical forms had allowed ë as a character until now. After this
+version the only utf-8 character allowed in canonical forms should be the
 multiplication sign for hybrids.
 
-1.0.13 -- canonical forms for cf. aff. qualifiers are modified: canonical for 
+1.0.13 -- canonical forms for cf. aff. qualifiers are modified: canonical for
 'Aus cf. bus' is now 'Aus bus'; canonical for 'Aus aff. bus' is now 'Aus'.
 Ranks at the end of the name like 'var', 'ssp', 'spp' are considered junk and
 are ignored
 
-1.0.12 -- bug is fixed which prevented 'Cucurbita pepo' be parsed correctly, 
+1.0.12 -- bug is fixed which prevented 'Cucurbita pepo' be parsed correctly,
 f., forma, fr. are now treated as any other ranks.

data/Gemfile

@@ -1,14 +1,15 @@
-source "http://rubygems.org"
+source 'https://rubygems.org'
 
-gem "treetop"
-gem "parallel"
-gem "unicode_utils"
+gem 'rake',           '~> 10.0'
+gem 'treetop',        '~> 1.4'
+gem 'parallel',       '~> 0.6'
+gem 'unicode_utils',  '~> 1.4'
 
 group :development do
-  gem "jeweler"
+  gem 'debugger',     '~> 1.5'
+  gem 'jeweler',      '~> 1.8'
 end
 
 group :test do
-  gem "debugger"
-  gem "rspec"
+  gem 'rspec',        '~> 2.13'
 end

data/Gemfile.lock

@@ -1,36 +1,35 @@
 GEM
-  remote: http://rubygems.org/
+  remote: https://rubygems.org/
   specs:
     columnize (0.3.6)
-    debugger (1.2.1)
+    debugger (1.5.0)
       columnize (>= 0.3.1)
-      debugger-linecache (~> 1.1.1)
-      debugger-ruby_core_source (~> 1.1.4)
-    debugger-linecache (1.1.2)
-      debugger-ruby_core_source (>= 1.1.1)
-    debugger-ruby_core_source (1.1.4)
-    diff-lcs (1.1.3)
+      debugger-linecache (~> 1.2.0)
+      debugger-ruby_core_source (~> 1.2.0)
+    debugger-linecache (1.2.0)
+    debugger-ruby_core_source (1.2.0)
+    diff-lcs (1.2.1)
     git (1.2.5)
     jeweler (1.8.4)
       bundler (~> 1.0)
       git (>= 1.2.5)
       rake
       rdoc
-    json (1.7.5)
-    parallel (0.5.18)
+    json (1.7.7)
+    parallel (0.6.2)
     polyglot (0.3.3)
-    rake (0.9.2.2)
-    rdoc (3.12)
+    rake (10.0.3)
+    rdoc (4.0.0)
       json (~> 1.4)
-    rspec (2.11.0)
-      rspec-core (~> 2.11.0)
-      rspec-expectations (~> 2.11.0)
-      rspec-mocks (~> 2.11.0)
-    rspec-core (2.11.1)
-    rspec-expectations (2.11.2)
-      diff-lcs (~> 1.1.3)
-    rspec-mocks (2.11.2)
-    treetop (1.4.10)
+    rspec (2.13.0)
+      rspec-core (~> 2.13.0)
+      rspec-expectations (~> 2.13.0)
+      rspec-mocks (~> 2.13.0)
+    rspec-core (2.13.1)
+    rspec-expectations (2.13.0)
+      diff-lcs (>= 1.1.3, < 2.0)
+    rspec-mocks (2.13.0)
+    treetop (1.4.12)
       polyglot
       polyglot (>= 0.3.1)
     unicode_utils (1.4.0)
@@ -39,9 +38,10 @@ PLATFORMS
   ruby
 
 DEPENDENCIES
-  debugger
-  jeweler
-  parallel
-  rspec
-  treetop
-  unicode_utils
+  debugger (~> 1.5)
+  jeweler (~> 1.8)
+  parallel (~> 0.6)
+  rake (~> 10.0)
+  rspec (~> 2.13)
+  treetop (~> 1.4)
+  unicode_utils (~> 1.4)

data/README.md

@@ -0,0 +1,146 @@
+Biodiversity
+============
+
+[![Gem Version][1]][2]
+[![Continuous Integration Status][3]][4]
+[![CodePolice][5]][6]
+[![Dependency Status][7]][8]
+
+Parses taxonomic scientific name and breaks it into semantic elements.
+
+Installation
+------------
+
+*WARNING:* Do not use Ruby 1.8.7 -- it is outdated. The
+biodiversity gem for Ruby 1.8.7 is not getting updated anymore
+
+    sudo gem install biodiversity19 #for ruby 1.9.x
+    sudo gem install biodiversity #for ruby 1.8.x
+
+Example usage
+-------------
+
+### As a command line script
+
+You can parse file with taxonomic names from command line.
+File should contain one scientific name per line
+
+    nnparser file_with_names
+
+### As a socket server
+
+If you do not use Ruby and need a fast access to the parser functionality
+you can use a socket server
+
+    parserver
+
+    parserver -h
+    Usage: parserver [options]
+
+        -r, --canonical_with_rank        Adds infraspecies rank to canonical forms
+
+        -o, --output=output              Specifies the type of the output:
+        json - parsed results in json
+        canonical - canonical form only
+                                         Default: json
+
+        -p, --port=port                  Specifies the port number
+                                         Default: 4334
+
+        -h, --help                       Show this help message.
+
+    parserver --output=canonical
+
+
+
+With default settings you can access parserserver via 4334 port using a
+socket client library of your programming language.  You can find
+[socket client script example][9] in the examples directory of the gem.
+
+If you want to check if socket server works for you:
+
+    #run server in one terminal
+    parserver
+
+    #in another terminal window type
+    telnet localhost 4334
+
+If you enter a line with a scientific name -- server will send you back
+parsed information in json format.
+
+To stop telnet client type any of `end`,`exit`,`q`, `.` instead
+of scientific name
+
+    $ telnet localhost 4334
+    Trying ::1...
+    Connected to localhost.
+    Escape character is '^]'.
+    Acacia abyssinica Hochst. ex Benth. ssp. calophylla Brenan
+    {"scientificName":{"canonical":"Acacia abyssinica calophylla"...}}
+    end
+
+### As a library
+
+You can use it as a library in Ruby, JRuby etc.
+
+    require 'biodiversity'
+
+    parser = ScientificNameParser.new
+
+    #to find version number
+    ScientificNameParser.version
+
+    # to fix capitalization in canonicals
+    ScientificNameParser.fix_case("QUERCUS (QUERCUS) ALBA")
+    # Output: Quercus (Quercus) alba
+
+    # to parse a scientific name into a ruby hash
+    parser.parse("Plantago major")
+
+    #to get json representation
+    parser.parse("Plantago").to_json
+    #or
+    parser.parse("Plantago")
+    parser.all_json
+
+    # to clean name up
+    parser.parse("      Plantago       major    ")[:scientificName][:normalized]
+
+    # to get only cleaned up latin part of the name
+    parser.parse("Pseudocercospora dendrobii (H.C. Burnett) U. Braun & Crous 2003")[:scientificName][:canonical]
+
+    # to get detailed information about elements of the name
+    parser.parse("Pseudocercospora dendrobii (H.C. Burnett 1883) U. Braun & Crous 2003")[:scientificName][:details]
+
+
+To parse using several CPUs (4 seem to be optimal)
+
+    parser = ParallelParser.new
+    # ParallelParser.new(4) will try to run 4 processes if hardware allows
+    array_of_names = ["Betula alba", "Homo sapiens"....]
+    parser.parse(array_of_names)
+    # Output: {"Betula alba" => {:scientificName...}, "Homo sapiens" => {:scientificName...}, ...}
+
+parallel parser takes list of names and returns back a hash with names as keys and parsed data as values
+
+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]
+    # Output: Cola cordifolia var. puberula
+
+To resolve lsid and get back RDF file
+
+    LsidResolver.resolve("urn:lsid:ubio.org:classificationbank:2232671")
+
+
+
+[1]: https://badge.fury.io/rb/biodiversity19.png
+[2]: http://badge.fury.io/rb/biodiversity19
+[3]: https://secure.travis-ci.org/GlobalNamesArchitecture/biodiversity.png
+[4]: http://travis-ci.org/GlobalNamesArchitecture/biodiversity
+[5]: https://codeclimate.com/github/GlobalNamesArchitecture/biodiversity.png
+[6]: https://codeclimate.com/github/GlobalNamesArchitecture/biodiversity
+[7]: https://gemnasium.com/GlobalNamesArchitecture/biodiversity.png
+[8]: https://gemnasium.com/GlobalNamesArchitecture/biodiversity
+[9]: https://github.com/GlobalNamesArchitecture/biodiversity/blob/master/examples/socket_client.rb

data/VERSION

@@ -1 +1 @@
-2.0.0
+2.1.0

data/bin/parserver

@@ -15,7 +15,7 @@ OPTIONS = {
 options = {}
 ARGV.options do |opts|
   script_name = File.basename($0)
-  opts.banner = "Usage: ruby #{script_name} [options]"
+  opts.banner = "Usage: #{script_name} [options]"
 
   opts.separator ''
 

data/lib/biodiversity/parser.rb

@@ -9,23 +9,44 @@ require 'json'
 module PreProcessor
   NOTES = /\s+(species\s+group|species\s+complex|group|author)\b.*$/i
   TAXON_CONCEPTS1 = /\s+(sensu\.|sensu|auct\.|auct)\b.*$/i
-  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  
+  TAXON_CONCEPTS2 = /\s+
+                     (\(?s\.\s?s\.|
+                     \(?s\.\s?l\.|
+                     \(?s\.\s?str\.|
+                     \(?s\.\s?lat\.|
+                    sec\.|sec|near)\b.*$/x
+  TAXON_CONCEPTS3 = /(,\s*|\s+)(pro parte|p\.\s?p\.)\s*$/i
   NOMEN_CONCEPTS  = /(,\s*|\s+)(\(?nomen|\(?nom\.|\(?comb\.).*$/i
-  LAST_WORD_JUNK  = /(,\s*|\s+)(spp\.|spp|var\.|var|von|van|ined\.|ined|sensu|new|non|nec|nudum|cf\.|cf|sp\.|sp|ssp\.|ssp|subsp|subgen|hybrid|hort\.|hort)\??\s*$/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*$/ix
+
   def self.clean(a_string)
-    [NOTES, TAXON_CONCEPTS1, TAXON_CONCEPTS2, 
+    [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'
     a_string
-  end   
+  end
 end
 
+# Public: Parser which runs in parallel.
+#
+# Examples
+#
+# parser = ParallelParser.new(4)
+# parser.parse(['Betula L.', 'Pardosa moesta'])
 class ParallelParser
 
+  # Public: Initialize ParallelParser.
+  #
+  # processes_num - an Integer to setup the number of processes (default: nil).
+  #                 If processes number is not set it will be determined
+  #                 automatically.
   def initialize(processes_num = nil)
     require 'parallel'
     cpu_num
@@ -36,13 +57,32 @@ class ParallelParser
     end
   end
 
+  # Public: Parses an array of scientific names using several processes
+  # in parallel.
+  #
+  # Scientific names are deduplicated in the process, so every string is
+  # parsed only once.
+  #
+  # names_list - takes an Array of scientific names,
+  #              each element should be a String.
+  #
+  # Examples
+  #
+  # parser = ParallelParser.new(4)
+  # parser.parse(['Homo sapiens L.', 'Quercus quercus'])
+  #
+  # Returns a Hash with scientific names as a key, and parsing results as
+  # a value.
   def parse(names_list)
-    parsed = Parallel.map(names_list.uniq, in_processes: @processes_num) do |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
 
+  # Public: Returns the number of cores/CPUs.
+  #
+  # Returns Integer of cores/CPUs.
   def cpu_num
     @cpu_num ||= Parallel.processor_count
   end
@@ -61,23 +101,28 @@ end
 #     @family    = /^\s*[A-Z][a-z]\+viridae|viroidae/i
 #     @subfamily = /^\s*[A-Z][a-z]\+virinae|viroinae/i
 #     @genus     = /^\s*[A-Z][a-z]\+virus|viroid/i
-#     @species   = /^\s*[A-z0-9u0391-u03C9\[\] ]\+virus|phage|viroid|satellite|prion[A-z0-9u0391-u03C9\[\] ]\+/i
+#     @species   = /^\s*[A-z0-9u0391-u03C9\[\] ]\+virus|phage|
+#                   viroid|satellite|prion[A-z0-9u0391-u03C9\[\] ]\+/ix
 #     @parsed    = nil
 #   end
 # end
 
 class ScientificNameParser
-  VERSION = open(File.join(File.dirname(__FILE__), 
+  VERSION = open(File.join(File.dirname(__FILE__),
                            '..',
                            '..',
                            'VERSION')).readline.strip
 
   FAILED_RESULT = ->(name) do
-    { scientificName: 
-      { parsed: false, verbatim: name.to_s.strip,  error: 'Parser error' } 
+    { scientificName:
+      { parsed: false, verbatim: name.to_s.strip,  error: 'Parser error' }
     }
   end
-  
+
+  def self.version
+    VERSION
+  end
+
   def self.fix_case(name_string)
     name_ary = name_string.split(/\s+/)
     words_num = name_ary.size
@@ -91,27 +136,27 @@ class ScientificNameParser
       end
     else
       if name_ary[0].size > 1
-        word1 = UnicodeUtils.upcase(name_ary[0][0]) + 
+        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]) + 
+        word2 = word2[0] + UnicodeUtils.upcase(word2[1]) +
           UnicodeUtils.downcase(word2[2..-1])
       else
         word2 = UnicodeUtils.downcase(name_ary[1])
       end
-      res = word1 + ' ' + 
-        word2 + ' ' + 
+      res = word1 + ' ' +
+        word2 + ' ' +
         name_ary[2..-1].map { |w| UnicodeUtils.downcase(w) }.join(' ')
       res.strip!
     end
     res
   end
 
-  
+
   def initialize(opts = {})
     @canonical_with_rank = !!opts[:canonical_with_rank]
     @verbatim = ''
@@ -122,8 +167,10 @@ class ScientificNameParser
   end
 
   def virus?(a_string)
-    !!(a_string.match(/\sICTV\s*$/) || 
-       a_string.match(/\b(virus|viruses|phage|phages|viroid|viroids|satellite|satellites|prion|prions)\b/i) || 
+    !!(a_string.match(/\sICTV\s*$/) ||
+       a_string.match(/\b(virus|viruses|
+                          phage|phages|viroid|viroids|
+                          satellite|satellites|prion|prions)\b/ix) ||
        a_string.match(/[A-Z]?[a-z]+virus\b/))
   end
 
@@ -134,24 +181,24 @@ class ScientificNameParser
   def parsed
     @parsed
   end
-  
+
   def parse(a_string)
     @verbatim = a_string.strip
     a_string = PreProcessor::clean(a_string)
-    
+
     if virus?(a_string)
       @parsed = { verbatim: a_string, virus: true }
     elsif unknown_placement?(a_string)
       @parsed = { verbatim: a_string }
     else
       begin
-        @parsed = @clean.parse(a_string) || @dirty.parse(a_string) 
+        @parsed = @clean.parse(a_string) || @dirty.parse(a_string)
         unless @parsed
           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) || 
+          @parsed =  @dirty.parse(salvage_string) ||
+                     @canonical.parse(a_string) ||
                      { verbatim: a_string }
         end
       rescue
@@ -181,18 +228,18 @@ class ScientificNameParser
       else
         res.merge!(self)
       end
-      if (canonical_with_rank && 
-          canonical.count(' ') > 1 && 
+      if (canonical_with_rank &&
+          canonical.count(' ') > 1 &&
           res[:details][0][:infraspecies])
         ScientificNameParser.add_rank_to_canonical(res)
       end
       res = {:scientificName => res}
     end
-    
+
     def @parsed.pos_json
       self.pos.to_json rescue ''
     end
-    
+
     def @parsed.all_json
       self.all.to_json rescue ''
     end
@@ -200,7 +247,7 @@ class ScientificNameParser
     @parsed.verbatim = @verbatim
     @parsed.all(canonical_with_rank: @canonical_with_rank)
   end
-  
+
   private
 
   def self.add_rank_to_canonical(parsed)
@@ -213,6 +260,6 @@ class ScientificNameParser
     end
     parsed[:canonical] = name_ary.join(' ')
   end
-  
+
 end
 

data/spec/parser/scientific_name.spec.rb

@@ -9,10 +9,14 @@ describe ScientificNameParser do
     set_parser(ScientificNameParser.new)
   end
 
+  it 'should return version number' do
+    ScientificNameParser.version.should =~ /^\d+\.\d+\.\d+/
+  end
+
   it 'should ScientificNameParser::fix_case' do
-    names = [ 
-      ["QUERCUS ALBA", "Quercus alba"], 
-      ["QUERCUS (QUERCUS) ALBA", "Quercus (Quercus) alba"], 
+    names = [
+      ["QUERCUS ALBA", "Quercus alba"],
+      ["QUERCUS (QUERCUS) ALBA", "Quercus (Quercus) alba"],
       ["QÜERCUS", "Qüercus"],
       ["PARDOSA MOéSTA", "Pardosa moésta"],
     ]
@@ -20,16 +24,17 @@ describe ScientificNameParser do
       ScientificNameParser::fix_case(name).should == capitalization
     end
   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')
+  #   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]
@@ -40,10 +45,12 @@ describe ScientificNameParser do
   #     end
   #   end
   # end
-  
+
   it 'should generate reasonable output if parser failed' do
     sn = 'ddd sljlkj 3223452432'
-    json(sn).should == '{"scientificName":{"parsed":false,"parser_version":"test_version","verbatim":"ddd sljlkj 3223452432"}}'  end
+    json(sn).should == '{"scientificName":{"parsed":false,' +
+      '"parser_version":"test_version","verbatim":"ddd sljlkj 3223452432"}}'
+  end
 
   it "should show version when the flag :show_version set to true" do
     parse('Homo sapiens')[:scientificName][:parser_version].should_not be_nil
@@ -58,7 +65,7 @@ describe ScientificNameParser do
   end
 end
 
-describe "ScientificNameParser with ranked canonicals" do 
+describe "ScientificNameParser with ranked canonicals" do
   before(:all) do
     @parser = ScientificNameParser.new(canonical_with_rank: true)
   end
@@ -66,10 +73,11 @@ describe "ScientificNameParser with ranked canonicals" do
   it 'should not influence output for uninomials and binomials' do
     data = [
       ['Ekbainacanthus Yakowlew 1902','Ekbainacanthus'],
-      ['Ekboarmia sagnesi herrerai Exposito 2007', 'Ekboarmia sagnesi herrerai'],
+      ['Ekboarmia sagnesi herrerai Exposito 2007',
+       'Ekboarmia sagnesi herrerai'],
       ['Ekboarmia holli Oberthür', 'Ekboarmia holli']]
 
-    data.each do |d| 
+    data.each do |d|
       parsed = @parser.parse(d[0])[:scientificName][:canonical]
       parsed.should == d[1]
     end
@@ -77,13 +85,16 @@ describe "ScientificNameParser with ranked canonicals" do
 
   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']
+      ['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] 
+      parsed.should == d[1]
     end
   end
 
@@ -115,7 +126,8 @@ describe ParallelParser do
     res.keys.size.should == names.size
   end
 
-  it "should have parsed name in native ruby format and in returned as a hash with name as a key and parsed data as value" do
+  it "should have parsed name in native ruby format and in returned as \
+      a hash with name as a key and parsed data as value" do
     names = []
     read_test_file { |n| names << (n[:name]) if n[:name] }
     names.uniq!

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: biodiversity19
 version: !ruby/object:Gem::Version
-  version: 2.0.0
+  version: 2.1.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,72 +9,104 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-03-12 00:00:00.000000000 Z
+date: 2013-03-14 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '10.0'
 - !ruby/object:Gem::Dependency
   name: treetop
   requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
-    - - ! '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.4'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     none: false
     requirements:
-    - - ! '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.4'
 - !ruby/object:Gem::Dependency
   name: parallel
   requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
-    - - ! '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '0.6'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     none: false
     requirements:
-    - - ! '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '0.6'
 - !ruby/object:Gem::Dependency
   name: unicode_utils
   requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
-    - - ! '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.4'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     none: false
     requirements:
-    - - ! '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.4'
+- !ruby/object:Gem::Dependency
+  name: debugger
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.5'
 - !ruby/object:Gem::Dependency
   name: jeweler
   requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
-    - - ! '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.8'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     none: false
     requirements:
-    - - ! '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.8'
 - !ruby/object:Gem::Dependency
   name: treetop
   requirement: !ruby/object:Gem::Requirement
@@ -131,15 +163,16 @@ executables:
 extensions: []
 extra_rdoc_files:
 - LICENSE
-- README.rdoc
+- README.md
 files:
 - .document
 - .rvmrc
+- .travis.yml
 - CHANGELOG
 - Gemfile
 - Gemfile.lock
 - LICENSE
-- README.rdoc
+- README.md
 - Rakefile
 - VERSION
 - bin/nnparse
@@ -178,7 +211,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -2248676907984019850
+      hash: 1065169335698854656
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -187,7 +220,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.24
+rubygems_version: 1.8.25
 signing_key: 
 specification_version: 3
 summary: Parser of scientific names

data/README.rdoc

@@ -1,109 +0,0 @@
-= Biodiversity
-
-{<img src="https://codeclimate.com/badge.png" />}[https://codeclimate.com/github/GlobalNamesArchitecture/biodiversity]
-
-Parses taxonomic scientific name and breaks it into semantic elements.
-
-== Installation
-
-To install gem you need RubyGems >= 1.3.6
-
-  $ sudo gem install biodiversity #for ruby 1.8.x
-  $ sudo gem install biodiversity19 #for ruby 1.9.x
-
-== Example usage
-
-=== As a command line script
-
-You can parse file with taxonomic names from command line. File should contain one scientific name per line
-
-  nnparser file_with_names
-
-=== As a socket server
-
-If you do not use ruby and need a fast access to the parser functionality  you can use a socket server
-
-  parserver
-
-options:
-
-  parserver --output=canonical
-
-to return a canonical form of the name string
-
-  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:
-
-  #run server in one terminal
-  parserver
-
-  #in another terminal window type
-  telnet localhost 4334
-
-If you enter a line with a scientific name server will send you back parsed information in json format.
-
-To stop telnet client type any of 'end','exit','q', '.' (without quotes) instead of scientific name
-
-  $ telnet localhost 4334
-  Trying ::1...
-  Connected to localhost.
-  Escape character is '^]'.
-  Acacia abyssinica Hochst. ex Benth. ssp. calophylla Brenan
-  {"scientificName":{"canonical":"Acacia abyssinica calophylla","parsed":true,"parser_run":1,"verbatim":"Acacia abyssinica Hochst. ex Benth. ssp. calophylla Brenan\r\n","positions":{"0":["genus",6],"18":["author_word",25],"29":["author_word",35],"7":["species",17],"41":["infraspecies",51],"52":["author_word",58]},"hybrid":false,"normalized":"Acacia abyssinica Hochst. ex Benth. ssp. calophylla Brenan","details":[{"species":{"basionymAuthorTeam":{"exAuthorTeam":{"author":["Benth."],"authorTeam":"Benth."},"author":["Hochst."],"authorTeam":"Hochst."},"string":"abyssinica","authorship":"Hochst. ex Benth."},"infraspecies":[{"basionymAuthorTeam":{"author":["Brenan"],"authorTeam":"Brenan"},"string":"calophylla","rank":"ssp.","authorship":"Brenan"}],"genus":{"string":"Acacia"}}]}}
-
-
-=== As a library
-
-You can use it as a library
-
-  require 'biodiversity'
-
-  parser = ScientificNameParser.new
-
-  # to fix capitalization in canonicals
-  ScientificNameParser.fix_case("QUERCUS (QUERCUS) ALBA") # Quercus (Quercus) alba
-
-  # to parse a scientific name into a ruby hash
-  parser.parse("Plantago major")
-
-  #to get json representation
-  parser.parse("Plantago").to_json
-  #or
-  parser.parse("Plantago")
-  parser.all_json
-
-  # to clean name up
-  parser.parse("             Plantago       major    ")[:scientificName][:normalized]
-
-  # to get only cleaned up latin part of the name
-  parser.parse("Pseudocercospora dendrobii (H.C. Burnett) U. Braun & Crous 2003")[:scientificName][:canonical]
-
-  # to get detailed information about elements of the name
-  parser.parse("Pseudocercospora dendrobii (H.C. Burnett 1883) U. Braun & Crous 2003")[:scientificName][:details]
-
-  # to parse using several CPUs (4 seem to be optimal)
-  parser = ParallelParser.new # ParallelParser.new(4) will try to run 4 processes if hardware allows
-  array_of_names = ["Betula alba", "Homo sapiens"....]
-  parser.parse(array_of_names) # -> {"Betula alba" => {:scientificName...}, "Homo sapiens" => {:scientificName...}, ...}
-
-  parallel parser takes list of names and returns back a hash with names as keys and parsed data as values
-
-  # 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.