biodiversity 1.0.10 → 3.0.0

data/.rvmrc

@@ -1 +1 @@
-rvm use ruby-1.9.2-p290@biodiversity --create
+rvm use ruby-1.9.3-p392@biodiversity --create

data/.travis.yml

@@ -0,0 +1,7 @@
+rvm:
+  - 1.9.3
+  - 2.0.0
+bundler_args: --without development
+branches:
+  only:
+      - master

data/CHANGELOG

@@ -0,0 +1,42 @@
+3.0.0 -- removing support for ruby 1.8.7, making biodiversity gem be the same
+as biodiversity19, deprecating biodiversity19. A few newly discovered bugs
+are fixed.
+
+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
+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
+for authors words, ampersand instead of 'et' in normalization
+
+1.1.1  -- more multi-uninomials cases, expanded viruses detection, added
+abbreviated genera and a few small fixes
+
+1.1.0  -- added multi-uninomials, fixes in identification annotations (aff.,
+cf., sp. etc), bug fixes, more robust salvage mode
+
+1.0.17 -- fixed a bug which prevented all diacritics be converted correctly
+
+1.0.16 -- dirty mode now converts ë to e
+
+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
+multiplication sign for hybrids.
+
+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,
+f., forma, fr. are now treated as any other ranks.

data/Gemfile

@@ -1,13 +1,15 @@
-source "http://rubygems.org"
+source 'https://rubygems.org'
 
-gem "treetop"
-gem "parallel"
+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 "ruby-debug19", :require => "ruby-debug"
-  gem "rspec"
+  gem 'rspec',        '~> 2.13'
 end

data/Gemfile.lock

@@ -1,47 +1,47 @@
 GEM
-  remote: http://rubygems.org/
+  remote: https://rubygems.org/
   specs:
-    archive-tar-minitar (0.5.2)
-    columnize (0.3.4)
-    diff-lcs (1.1.3)
+    columnize (0.3.6)
+    debugger (1.5.0)
+      columnize (>= 0.3.1)
+      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 (1.6.4)
+    jeweler (1.8.4)
       bundler (~> 1.0)
       git (>= 1.2.5)
       rake
-    linecache19 (0.5.12)
-      ruby_core_source (>= 0.1.4)
-    parallel (0.5.9)
+      rdoc
+    json (1.7.7)
+    parallel (0.6.2)
     polyglot (0.3.3)
-    rake (0.9.2.2)
-    rspec (2.7.0)
-      rspec-core (~> 2.7.0)
-      rspec-expectations (~> 2.7.0)
-      rspec-mocks (~> 2.7.0)
-    rspec-core (2.7.1)
-    rspec-expectations (2.7.0)
-      diff-lcs (~> 1.1.2)
-    rspec-mocks (2.7.0)
-    ruby-debug-base19 (0.11.25)
-      columnize (>= 0.3.1)
-      linecache19 (>= 0.5.11)
-      ruby_core_source (>= 0.1.4)
-    ruby-debug19 (0.11.6)
-      columnize (>= 0.3.1)
-      linecache19 (>= 0.5.11)
-      ruby-debug-base19 (>= 0.11.19)
-    ruby_core_source (0.1.5)
-      archive-tar-minitar (>= 0.5.2)
-    treetop (1.4.10)
+    rake (10.0.3)
+    rdoc (4.0.0)
+      json (~> 1.4)
+    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)
 
 PLATFORMS
   ruby
 
 DEPENDENCIES
-  jeweler
-  parallel
-  rspec
-  ruby-debug19
-  treetop
+  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 +1,167 @@
+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.
+
+*WARNING, IMPORTANT!:*
+Support for Ruby 1.8.7 IS DROPPED. Both biodiversity and
+biodiversity19 will be for Ruby > 1.9.1 and will be identical gems.
+
+biodiversity19 is now deprecated and will be phased out in a couple of years.
+You are strongly encouraged to change your dependencies from
+biodiversity19 to biodiversity
+
+Installation
+------------
+
+    sudo gem install biodiversity
+
+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
+
+    nnparse file_with_names
+
+The resuls will be put into parsed.json file in the current directory.
+To save results into a different file:
+
+    nnparse file_with_names output_file
+
+### 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]
+
+Returned result is not always linear, if name is complex. To get simple linear
+representation of the name you can use:
+
+    parser.parse("Pseudocercospora dendrobii (H.C. Burnett) U. Braun & Crous 2003")[:scientificName][:position]
+    # returns {0=>["genus", 16], 17=>["species", 26],
+    # 28=>["author_word", 32], 33=>["author_word", 40],
+    # 42=>["author_word", 44], 45=>["author_word", 50],
+    # 53=>["author_word", 58], 59=>["year", 63]}
+    # where the key is the char index of the start of
+    # a word, first element of the value is a semantic meaning
+    # of the word, second element of the value is the character index
+    # of end of the word
+
+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/Rakefile

@@ -20,35 +20,41 @@ ruby_version = RUBY_VERSION.split('.')[0..1].join('').to_i
 begin
   require 'jeweler'
   Jeweler::Tasks.new do |gem|
-    gem.name = ruby_version < 19 ? "biodiversity" : "biodiversity19"
+    gem.name = 'biodiversity'
+    #To delete ruby_version < 19 ? 'biodiversity' : 'biodiversity19'
     gem.summary = 'Parser of scientific names'
     gem.description = 'Tools for biodiversity informatics'
-    gem.email = "dmozzherin@gmail.com"
-    gem.homepage = "http://github.com/GlobalNamesArchitecture/biodiversity"
-    gem.authors = ["Dmitry Mozzherin"]
+    gem.email = 'dmozzherin@gmail.com'
+    gem.homepage = 'http://github.com/GlobalNamesArchitecture/biodiversity'
+    gem.authors = ['Dmitry Mozzherin']
     gem.has_rdoc = false
     gem.bindir = 'bin'
     gem.executables = ['nnparse', 'parserver']
     gem.add_dependency('treetop')
     gem.add_dependency('parallel')
-    gem.add_dependency('json') if ruby_version < 19
+    # gem.add_dependency('json') if ruby_version < 19
     gem.add_development_dependency "rspec"
-    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+    # gem is a Gem::Specification...
+    # see http://www.rubygems.org/read/chapter/20 for additional settings
   end
 rescue LoadError
-  puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
+  puts 'Jeweler (or a dependency) not available. ' +
+    'Install it with: sudo gem install jeweler'
 end
 
 task :tt do
-  ['scientific_name_clean', 'scientific_name_dirty', 'scientific_name_canonical'].each do |f|
+  ['scientific_name_clean',
+   'scientific_name_dirty',
+   'scientific_name_canonical'].each do |f|
     file = "#{dir}/lib/biodiversity/parser/#{f}"
     FileUtils.rm("#{file}.rb") if FileTest.exist?("#{file}.rb")
     system("tt #{file}.treetop")
     rf = "#{file}.rb"
-    rfn = open(rf + ".tmp", 'w')
+    rfn = open(rf + '.tmp', 'w')
     skip_head = false
     f = open(rf)
-    #getting around a bug in treetop which prevents setting UTF-8 encoding in ruby19
+    # getting around a bug in treetop which prevents setting
+    # UTF-8 encoding in ruby19
     f.each_with_index do |l, i|
       skip_head = l.match(/^# Autogenerated/) if i == 0
       if skip_head && (l.strip == '' || l.match(/^# Autogenerated/))
@@ -63,4 +69,3 @@ task :tt do
     `mv #{rf}.tmp #{rf}`
   end
 end
-

data/VERSION

@@ -1 +1 @@
-1.0.10
+3.0.0

data/bin/parserver

@@ -5,78 +5,67 @@ 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 = {}
 ARGV.options do |opts|
   script_name = File.basename($0)
-  opts.banner = "Usage: ruby #{script_name} [options]"
+  opts.banner = "Usage: #{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