biodiversity 3.5.1 → 4.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 832687083196a98a5923318b0d778fde31c852d0
-  data.tar.gz: 2dc45e6f8d201ee8c9abcd5c2cbb41ad3e0c20fa
+SHA256:
+  metadata.gz: be6873b8833844649f8f58641c1cb12250d6b539cdaa12c7e4657433c17ea2c1
+  data.tar.gz: 70ff3729b66bb1f8ae6eb7f553c1fe48d98cd191020f5a6ccf03b2f509843865
 SHA512:
-  metadata.gz: af478fe58904ec048ef4b67f0671a1c7c8dc59144303af60129b117ce7ec775a1fa73ceb154f3e10f2a2d05cac173b72ff539231acb0b6cc7dab2a4baacc230f
-  data.tar.gz: e6494923af734096b435e27b50ef8239477d58110c6b9f59a0f36324cc7110b6461eb81f0218c00766d6919a3d7eaa7f03dfc688195c0456ea50a5141e5d44ac
+  metadata.gz: b4bd5630b6e1401c98c0ed9fefdd945d7dd21f52ec911a6ca235163f6497c72ce94ad0dc957919601f87cdd73ce67c3f7274e910e7af1497d672eefdfa2a9d2b
+  data.tar.gz: 14a5920a83bb40a7d2f51d6bf633d1dc6415e596013a3a54ab1c27d07fdd0d64a5c2fb50fb4a47c430552d6a7c5f5c0e2a5ede9cc9890f295b3dcc1cec0e1fa8

data/.gitignore

@@ -16,3 +16,4 @@ bin
 .bundle
 bundle_bin
 Gemfile.lock
+.byebug_history

data/.rubocop.yml

@@ -1,10 +1,13 @@
 AllCops:
   Exclude:
-    - features/**/*
     - .bundle/**/*
     - bundle_bin/**/*
-Style/StringLiterals:
-  EnforcedStyle: double_quotes
-Style/DotPosition:
-  EnforcedStyle: trailing
-
+Metrics/AbcSize:
+  Exclude:
+    - lib/**/*
+Metrics/MethodLength:
+  Exclude:
+    - lib/**/*
+Metrics/BlockLength:
+  Exclude:
+    - spec/**/*

data/.ruby-version

@@ -1 +1 @@
-2.4.4
+2.5.7

data/.travis.yml

@@ -1,11 +1,6 @@
 rvm:
-  - 2.1
-  - 2.2
-  - 2.3
-  - 2.4
   - 2.5
+  - 2.6
 branches:
   only:
       - master
-before_script:
-  - bundle exec rake tt

data/CHANGELOG

@@ -1,3 +1,6 @@
+4.0.0 -- migrate code to gnparser C-shared library. This change breaks
+         backward compatibility, and makes parser dramatically faster.
+
 3.5.1 -- allow comma before 'and' or '&' in authorship
 
 3.5.0 -- add the tail cut by preprocessing to the results. The tail usually

data/Gemfile

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 source 'https://rubygems.org'
 
 gemspec

data/README.md

@@ -4,169 +4,76 @@ Biodiversity
 [![DOI](https://zenodo.org/badge/19435/GlobalNamesArchitecture/biodiversity.svg)](https://zenodo.org/badge/latestdoi/19435/GlobalNamesArchitecture/biodiversity)
 [![Gem Version][gem_svg]][gem_link]
 [![Continuous Integration Status][ci_svg]][ci_link]
-[![CodePolice][cc_svg]][cc_link]
-[![Dependency Status][deps_svg]][deps_link]
 
 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.
+**Important**: Biodiversity parser >= 4.0.0 uses binding to
+https://gitlab.com/gogna/gnparser and
+is not backward compatible with older versions. However it is much much faster
+and better than previous versions.
 
-biodiversity19 is now deprecated and will not be updated anymore.
-You are strongly encouraged to change your dependencies from
-biodiversity19 to biodiversity
+This gem does not have a remote server or a command line executable anymore.
+For such features use https://gitlab.com/gogna/gnparser.
 
-Follow [biodiversity issues][waffle] on waffle.io
 
-Installation
-------------
+## Installation
 
     sudo gem install biodiversity
 
-Example usage
--------------
+The gem should work on Linux, Mac and Windows (64bit) machines
 
-### As a command line script
+## Example usage
 
-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
-
-        -H, --host=host                  Specifies host as "127.0.0.1",
-                                         "localhost" etc.
-                                         Default: 127.0.0.1
-
-        -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][socket_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`, `.` 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.
+You can use it as a library in Ruby:
 
 
 ```ruby
 require 'biodiversity'
 
-parser = ScientificNameParser.new
+#to find the gem version number
+Biodiversity.version
 
-#to find version number
-ScientificNameParser.version
+# Note that the version in parsed output will correspond to the version of
+# gnparser.
 
-# to fix capitalization in canonicals
-ScientificNameParser.fix_case("QUERCUS (QUERCUS) ALBA")
-# Output: Quercus (Quercus) alba
+# to parse a scientific name into a simple Ruby hash
+Biodiversity::Parser.parse("Plantago major", simple = true)
 
-# to parse a scientific name into a ruby hash
-parser.parse("Plantago major")
+# to parse many scientific names using all computer CPUs
+Biodiversity::Parser.parse(["Plantago major", ... ], simple = true)
+
+# to parse a scientific name into a very detailed Ruby hash
+Biodiversity::Parser.parse("Plantago major")
+
+# to parse many scientific names with all details using all computer CPUs
+Biodiversity::Parser.parse(["Plantago major", ... ])
 
 #to get json representation
-parser.parse("Plantago").to_json
-#or
-parser.parse("Plantago")
-parser.all_json
+Biodiversity::Parser.parse("Plantago").to_json
 
 # to clean name up
-parser.parse("      Plantago       major    ")[:scientificName][:normalized]
+Biodiversity::Parser.parse("      Plantago       major    ")[: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 canonical form with infraspecies ranks
-parsed = parser.parse("Seddera latifolia Hochst. & Steud. var. latifolia")
-ranked = ScientificNameParser.add_rank_to_canonical(parsed)
-ranked[:scientificName][:canonical]
-#or
-parser = ScientificNameParser.new(canonical_with_rank: true)
-ranked = parser.parse("Seddera latifolia Hochst. & Steud. var. latifolia")
-ranked[:scientificName][:canonical]
+# to get canonical form with or without infraspecies ranks, as well as
+# stemmed version.
+parsed = Biodiversity::Parser.parse("Seddera latifolia H. & S. var. latifolia")
+parsed[:canonicalName][:full]
+parsed[:canonicalName][:simple]
+parsed[:canonicalName][:stem]
 
 # 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:
-
-
-```ruby
-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
+Biodiversity::Parser.parse("Pseudocercospora dendrobii (H.C. Burnett 1883) U. \
+Braun & Crous 2003")[:details]
 ```
 
 'Surrogate' is a broad group which includes 'Barcode of Life' names, and various
 undetermined names with cf. sp. spp. nr. in them:
 
 ```ruby
-parser.parse("Coleoptera BOLD:1234567")[:scientificName][:surrogate]
+parser.parse("Coleoptera BOLD:1234567")[:surrogate]
 ```
-### What is "id" in the parsed results?
+### What is "nameStringID" in the parsed results?
 
 ID field contains UUID v5 hexadecimal string. ID is generated out of bytes
 from the name string itself, and identical id can be generated using [any
@@ -175,67 +82,19 @@ version 5 in a [blog post][uuid_blog]
 
 For example "Homo sapiens" should generate "16f235a0-e4a3-529c-9b83-bd15fe722110" UUID
 
-### Parse using several CPUs (4 threads seem to be optimal)
-
-```ruby
-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
-
-### Canonicals with ranks for infraspecific epithets:
-
-```ruby
-parser = ScientificNameParser.new(canonical_with_rank: true)
-parser.parse('Cola cordifolia var. puberula \
-A. Chev.')[:scientificName][:canonical]
-# Output: Cola cordifolia var. puberula
-```
-
-### Resolving lsid and geting back RDF file
-
-    LsidResolver.resolve("urn:lsid:ubio.org:classificationbank:2232671")
-
-Troubleshooting
----------------
-
-If nnparse or parserver do not start -- try to run
-
-    gem uninstall biodiversity
-    gem uninstall biodiversity19
-
-and make sure you remove all versions and all nnparse and parserver scripts.
-Then install biodiversity again
-
-    gem install biodiversity
-
-It should fix the problem.
-
 Copyright
 ---------
 
 Authors: [Dmitry Mozzherin][dimus]
 
-Copyright (c) 2008-2018 Dmitry Mozzherin. See [LICENSE][license]
+Copyright (c) 2008-2019 Dmitry Mozzherin. See [LICENSE][license]
 for further details.
 
 [gem_svg]: https://badge.fury.io/rb/biodiversity.svg
 [gem_link]: http://badge.fury.io/rb/biodiversity
 [ci_svg]: https://secure.travis-ci.org/GlobalNamesArchitecture/biodiversity.svg
 [ci_link]: http://travis-ci.org/GlobalNamesArchitecture/biodiversity
-[cc_svg]: https://codeclimate.com/github/GlobalNamesArchitecture/biodiversity.svg
-[cc_link]: https://codeclimate.com/github/GlobalNamesArchitecture/biodiversity
-[deps_svg]: https://gemnasium.com/GlobalNamesArchitecture/biodiversity.svg
-[deps_link]: https://gemnasium.com/GlobalNamesArchitecture/biodiversity
-[socket_example]: http://bit.ly/149iLm5
 [dimus]: https://github.com/dimus
 [license]: https://github.com/GlobalNamesArchitecture/biodiversity/blob/master/LICENSE
-[waffle]: https://waffle.io/GlobalNamesArchitecture/biodiversity
 [uuid_examples]: https://github.com/GlobalNamesArchitecture/gn_uuid_examples
 [uuid_blog]: http://globalnamesarchitecture.github.io/gna/uuid/2015/05/31/gn-uuid-0-5-0.html

data/Rakefile

@@ -1,53 +1,20 @@
-require "bundler"
-Bundler::GemHelper.install_tasks
-
-begin
-  Bundler.setup(:default, :development)
-rescue Bundler::BundlerError => e
-  $stderr.puts e.message
-  $stderr.puts "Run `bundle install` to install missing gems"
-  exit e.status_code
-end
-
-require "rspec/core"
-require "rspec/core/rake_task"
-require "rake/dsl_definition"
-require "rake"
-require "rspec"
-require "rspec/core/rake_task"
+# frozen_string_literal: true
 
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
+require 'rubocop/rake_task'
+require 'rake/dsl_definition'
+require 'rake'
+require 'rspec'
 
-task :default => :spec
-
-RSpec::Core::RakeTask.new do |t|
-  t.pattern = "spec/**/*spec.rb"
+RSpec::Core::RakeTask.new(:spec) do |rspec|
+  rspec.pattern = FileList['spec/**/*_spec.rb']
 end
 
-task :tt do
-  dir = File.dirname(__FILE__)
-  ["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")
-    skip_head = false
-    f = open(rf)
-    # 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/))
-        next
-      else
-        skip_head = false
-        rfn.write(l)
-      end
-    end
-    rfn.close
-    f.close
-    `mv #{rf}.tmp #{rf}`
-  end
+RuboCop::RakeTask.new
+task default: %i[rubocop spec]
+
+desc 'open an irb session preloaded with this gem'
+task :console do
+  sh 'irb -r pp -r ./lib/biodiversity.rb'
 end

data/biodiversity.gemspec

@@ -1,30 +1,27 @@
-$:.push File.expand_path("../lib", __FILE__)
+# frozen_string_literal: true
 
-require "biodiversity/version"
+$LOAD_PATH.push File.expand_path('lib', __dir__)
+
+require 'biodiversity/version'
 
 Gem::Specification.new do |gem|
-  gem.name          = "biodiversity"
+  gem.name          = 'biodiversity'
   gem.version       = Biodiversity::VERSION
-  gem.homepage      = "https://github.com/GlobalNamesArchitecture/biodiversity"
-  gem.license       = "MIT"
-  gem.summary       = "Parser of scientific names"
-  gem.description   = "Tools for biodiversity informatics"
-  gem.authors       = ["Dmitry Mozzherin"]
-  gem.email         = "dmozzherin@gmail.com"
+  gem.homepage      = 'https://github.com/GlobalNamesArchitecture/biodiversity'
+  gem.license       = 'MIT'
+  gem.summary       = 'Parser of scientific names'
+  gem.description   = 'Parsing tool for biodiversity informatics'
+  gem.authors       = ['Dmitry Mozzherin']
+  gem.email         = 'dmozzherin@gmail.com'
 
   gem.files         = `git ls-files`.split("\n")
-  gem.executables   = ["nnparse", "parserver"]
-  gem.require_paths = ["lib"]
+  gem.require_paths = ['lib']
 
-  gem.add_runtime_dependency "treetop", "~> 1.6"
-  gem.add_runtime_dependency "parallel", "~> 1.12"
-  gem.add_runtime_dependency "unicode_utils", "~> 1.4"
-  gem.add_runtime_dependency "gn_uuid", "~> 0.5"
+  gem.add_runtime_dependency 'ffi', '~> 1.11'
 
-  gem.add_development_dependency "bundler", "~> 1.16"
-  gem.add_development_dependency "rake", "~> 12.3"
-  gem.add_development_dependency "rspec", "~> 3.7"
-  gem.add_development_dependency "webmock", "~> 3.3"
-  gem.add_development_dependency "rr", "~> 1.2"
-  gem.add_development_dependency "rubocop", "~> 0.52"
+  gem.add_development_dependency 'bundler', '~> 2.0'
+  gem.add_development_dependency 'byebug', '~> 11.0'
+  gem.add_development_dependency 'rake', '~> 13.0'
+  gem.add_development_dependency 'rspec', '~> 3.9'
+  gem.add_development_dependency 'rubocop', '~> 0.76'
 end