taxamatch_rb 1.0.1 → 1.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 3f9cbd9334dff96ed1723f1487bc3bb89805c4f4
+  data.tar.gz: 5928a559f917d9908d251cb873285e0242d60476
+SHA512:
+  metadata.gz: d598f616d3f34f1cfc051b1e6ee049075eb3a87d5714d3712075434eead6f88e3667bde46edfd0a5cd7a8c868b3139d4ca9802f21205f38e918b4eba07e92324
+  data.tar.gz: d429b8e677be3fe170f01c66dc07c002fa05e77f14fc89e78dce4f6ded814c3a52477e44ebc0fb8688bf40cba686da45e5ede275d54cebdf6d3daa7f518637e5

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.rubocop.yml

@@ -0,0 +1,9 @@
+AllCops:
+  Exclude:
+    - features/**/*
+    - .bundle/**/*
+    - bundle_bin/**/*
+Style/StringLiterals:
+  EnforcedStyle: double_quotes
+Style/DotPosition:
+  EnforcedStyle: trailing

data/.travis.yml

@@ -0,0 +1,10 @@
+rvm:
+  - 2.0
+  - 2.1
+  - 2.2
+script:
+  - bundle exec rake
+branches:
+  only:
+      - master
+

data/CHANGELOG

@@ -1,3 +1,5 @@
+1.1.0 - create gem with bundle instead of jeweler, refactoring
+
 1.0.0 - fixed a parsing problem with infraspecies without string,
 upgraded version to 1 because the signature of the gem did stabilized
 
@@ -12,3 +14,4 @@ upgraded version to 1 because the signature of the gem did stabilized
 characters, all utf-8 characters unknown to normalizer are becoming '?'
 
 0.9.1 - updated gems
+

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,31 @@
+Contributor Code of Conduct
+===========================
+
+As contributors and maintainers of this project, we pledge to respect all
+people who contribute through reporting issues, posting feature requests,
+updating documentation, submitting pull requests or patches, and other
+activities.
+
+We are committed to making participation in this project a harassment-free
+experience for everyone, regardless of level of experience, gender, gender
+identity and expression, sexual orientation, disability, personal appearance,
+body size, race, age, or religion.
+
+Examples of unacceptable behavior by participants include the use of sexual
+language or imagery, derogatory comments or personal attacks, trolling, public
+or private harassment, insults, or other unprofessional conduct.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct. Project maintainers who do not
+follow the Code of Conduct may be removed from the project team.
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by opening an issue or contacting one or more of the project
+maintainers.
+
+This Code of Conduct is adapted from the [Contributor
+Covenant][1], [version 1.0.0][2]
+
+[1]: http:contributor-covenant.org
+[2]: http://contributor-covenant.org/version/1/0/0/

data/Gemfile

@@ -1,19 +1,4 @@
 source 'https://rubygems.org'
-require 'yaml'
 
-gem 'biodiversity','~> 3.1.0'
-gem 'damerau-levenshtein', '~> 0.5.4'
-gem 'json', '~> 1.7.7'
-
-group :test do
-  gem 'rake', '~> 10.0'
-  gem 'rake-compiler', '~> 0.8'
-  gem 'rspec', '~> 2.13'
-  gem 'cucumber', '~> 1.3'
-  gem 'bundler', '~> 1.3'
-  gem 'jeweler', '~> 1.8'
-  gem 'debugger', '~> 1.5'
-  gem 'ruby-prof', '~> 0.13'
-  gem 'shoulda', '~> 3.5'
-  gem 'mocha', '~> 0.13'
-end
+# Specify your gem's dependencies in taxamatch_rb.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2015 Marine Biological Laboratory
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -1,75 +1,102 @@
-Taxamatch_Rb
+taxamatch_rb
 ============
 
 [![Gem Version][1]][2]
 [![Continuous Integration Status][3]][4]
-[![Dependency Status][5]][6]
+[![Coverage Status][5]][6]
+[![CodePolice][7]][8]
+[![Dependency Status][8]][9]
 
-Taxamatch_Rb is a ruby implementation of Taxamatch algorithms
-[developed by Tony Rees][7]:
+`taxamatch_rb` is a ruby implementation of Taxamatch algorithms
+[developed by Tony Rees][10]:
 
 The purpose of Taxamatch gem is to facilitate fuzzy comparison of
 two scientific name renderings to find out if they actually point to
 the same scientific name.
 
-    require 'taxamatch_rb'
-    tm = Taxamatch::Base.new
-    tm.taxamatch('Homo sapien', 'Homo sapiens') #returns true
-    tm.taxamatch('Homo sapiens Linnaeus', 'Hommo sapens (Linn. 1758)') #returns true
-    tm.taxamatch('Homo sapiens Mozzherin', 'Homo sapiens Linnaeus') #returns false
+```ruby
+require 'taxamatch_rb'
+tm = Taxamatch::Base.new
+tm.taxamatch('Homo sapien', 'Homo sapiens') #returns true
+tm.taxamatch('Homo sapiens Linnaeus', 'Hommo sapens (Linn. 1758)') #returns true
+tm.taxamatch('Homo sapiens Mozzherin', 'Homo sapiens Linnaeus') #returns false
+```
 
-Taxamatch_Rb is compatible with ruby versions 1.9.1 and higher
+`taxamatch_rb` is compatible with ruby versions 1.9.1 and higher
 
 Installation
 ------------
 
-    sudo gem install taxamatch_rb
+```bash
+$ sudo gem install taxamatch_rb
+```
 
 Usage
 -----
 
-    require 'taxamatch_rb'
+```ruby
+require "taxamatch_rb"
 
-    tm = Taxamatch::Base.new
+# To find version
+Taxamatch.version
+
+# To start new instance of taxamatch
+tm = Taxamatch::Base.new
+```
 
 * compare full scientific names
 
-    tm.taxamatch('Hommo sapiens L.', 'Homo sapiens Linnaeus')
+```ruby
+tm.taxamatch("Hommo sapiens L.", "Homo sapiens Linnaeus")
+```
 
 * preparse names for the matching (necessary for large databases of scientific names)
 
-    p = Taxamatch::Atomizer.new
-    parsed_name1 = p.parse('Monacanthus fronticinctus Günther 1867 sec. Eschmeyer 2004')
-    parsed_name2 = p.parse('Monacanthus fronticinctus (Gunther, 1867)')
+```ruby
+p = Taxamatch::Atomizer.new
+parsed_name1 = p.parse("Monacanthus fronticinctus Günther 1867 sec. Eschmeyer 2004")
+parsed_name2 = p.parse("Monacanthus fronticinctus (Gunther, 1867)")
+```
 
 * compare preparsed names
 
-    tm.taxamatch_preparsed(parsed_name1, parsed_name2)
+```ruby
+tm.taxamatch_preparsed(parsed_name1, parsed_name2)
+```
 
 * compare genera
 
-    tm.match_genera('Monacanthus', 'MONOCANTUS')
+```ruby
+tm.match_genera("Monacanthus", "MONOCANTUS")
+```
 
 * compare species
 
-    tm.match_species('fronticinctus', 'frontecinctus')
+```ruby
+tm.match_species("fronticinctus", "frontecinctus")
+```
 
 * compare authors and years
 
-    Taxamatch::Authmatch.authmatch(['Linnaeus'], ['L','Muller'], [1786], [1787])
-
+```ruby
+Taxamatch::Authmatch.authmatch(["Linnaeus"], ["L","Muller"], [1786], [1787])
+```
 
 You can find more examples in spec section of the code
 
 Copyright
 ---------
 
-Copyright (c) 2009-2013 Marine Biological Laboratory. See LICENSE for details.
+Copyright (c) 2009-2015 Marine Biological Laboratory. See LICENSE for details.
 
 [1]: https://badge.fury.io/rb/taxamatch_rb.png
 [2]: http://badge.fury.io/rb/taxamatch_rb
 [3]: https://secure.travis-ci.org/GlobalNamesArchitecture/taxamatch_rb.png
 [4]: http://travis-ci.org/GlobalNamesArchitecture/taxamatch_rb
-[5]: https://gemnasium.com/GlobalNamesArchitecture/taxamatch_rb.png
-[6]: https://gemnasium.com/GlobalNamesArchitecture/taxamatch_rb
-[7]: http://www.cmar.csiro.au/datacentre/taxamatch.htm
+[5]: https://coveralls.io/repos/GlobalNamesArchitecture/taxamatch_rb/badge.png
+[6]: https://coveralls.io/r/GlobalNamesArchitecture/taxamatch_rb
+[7]: https://codeclimate.com/github/GlobalNamesArchitecture/taxamatch_rb.png
+[8]: https://codeclimate.com/github/GlobalNamesArchitecture/taxamatch_rb
+[8]: https://gemnasium.com/GlobalNamesArchitecture/taxamatch_rb.png
+[9]: https://gemnasium.com/GlobalNamesArchitecture/taxamatch_rb
+[10]: http://www.cmar.csiro.au/datacentre/taxamatch.htm

data/Rakefile

@@ -1,47 +1,18 @@
-require 'rubygems'
+require "bundler/gem_tasks"
+require "rake"
+require "rspec/core"
+require "rspec/core/rake_task"
+require "cucumber"
+require "cucumber/rake/task"
 
-require 'bundler'
-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 'rake'
-
-begin
-  require 'jeweler'
-  Jeweler::Tasks.new do |gem|
-    gem.name = 'taxamatch_rb'
-    gem.summary = 'Implementation of Tony Rees Taxamatch algorithms'
-    gem.description = 'This gem implements algorithm ' +
-      'for fuzzy matching scientific names developed by Tony Rees'
-    gem.email = 'dmozzherin@gmail.com'
-    gem.homepage = 'http://github.com/GlobalNamesArchitecture/taxamatch_rb'
-    gem.authors = ['Dmitry Mozzherin']
-    gem.files = FileList['[A-Z]*',
-      '*.gemspec', '{bin,generators,lib,spec}/**/*']
-    gem.files -= FileList['lib/**/*.bundle', 'lib/**/*.dll', 'lib/**/*.so']
-    gem.files += FileList['ext/**/*.c']
-    gem.extensions = FileList['ext/**/extconf.rb']
-  end
-
-rescue LoadError
-  puts 'Jeweler (or a dependency) not available.' +
-  ' Install it with: sudo gem install jeweler'
-end
-
-require 'rspec/core'
-require 'rspec/core/rake_task'
 RSpec::Core::RakeTask.new(:spec) do |spec|
   spec.pattern = FileList['spec/**/*_spec.rb']
 end
 
-RSpec::Core::RakeTask.new(:rcov) do |spec|
-  spec.pattern = 'spec/**/*_spec.rb'
-  spec.rcov = true
+# Cucumber::Rake::Task.new(:features)
+Cucumber::Rake::Task.new(:features) do |t|
+    t.cucumber_opts = "features --format pretty"
 end
 
-task :default => :spec
+task default: [:features, :spec]
+

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "taxamatch_rb"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start

data/bin/setup

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euo pipefail
+IFS=$'\n\t'
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/taxamatch_rb/base.rb

@@ -0,0 +1,154 @@
+module Taxamatch
+  # Matches name strings of scientific names
+  class Base
+    def initialize
+      @parser = Taxamatch::Atomizer.new
+      @dlm = DamerauLevenshtein
+    end
+
+    def taxamatch(str1, str2, return_boolean = true)
+      preparsed_1 = @parser.parse(str1)
+      preparsed_2 = @parser.parse(str2)
+      match = taxamatch_preparsed(preparsed_1, preparsed_2)
+      return_boolean ? (!!match && match["match"]) : match
+    end
+
+    def taxamatch_preparsed(preparsed_1, preparsed_2)
+      result = nil
+      if preparsed_1[:uninomial] && preparsed_2[:uninomial]
+        result =  match_uninomial(preparsed_1, preparsed_2)
+      elsif preparsed_1[:genus] && preparsed_2[:genus]
+        result =  match_multinomial(preparsed_1, preparsed_2)
+      end
+      if result && result["match"]
+        result["match"] = match_authors(preparsed_1, preparsed_2)
+      end
+      result
+    rescue StandardError
+      nil
+    end
+
+    def match_uninomial(preparsed_1, preparsed_2)
+      match_genera(preparsed_1[:uninomial], preparsed_2[:uninomial])
+    end
+
+    def match_multinomial(preparsed_1, preparsed_2)
+      gen_match = match_genera(preparsed_1[:genus], preparsed_2[:genus])
+      sp_match = match_species(preparsed_1[:species], preparsed_2[:species])
+      total_length = preparsed_1[:genus][:string].size +
+        preparsed_2[:genus][:string].size +
+        preparsed_1[:species][:string].size +
+        preparsed_2[:species][:string].size
+      if preparsed_1[:infraspecies] && preparsed_2[:infraspecies]
+        infrasp_match = match_species(preparsed_1[:infraspecies][0],
+                                      preparsed_2[:infraspecies][0])
+        total_length += preparsed_1[:infraspecies][0][:string].size +
+          preparsed_2[:infraspecies][0][:string].size
+        match_hash = match_matches(gen_match, sp_match, infrasp_match)
+      elsif (preparsed_1[:infraspecies] && !preparsed_2[:infraspecies]) ||
+        (!preparsed_1[:infraspecies] && preparsed_2[:infraspecies])
+        match_hash = { "match" => false,
+          "edit_distance" => 5,
+          "phonetic_match" => false }
+        total_length += preparsed_1[:infraspecies] ?
+          preparsed_1[:infraspecies][0][:string].size :
+          preparsed_2[:infraspecies][0][:string].size
+      else
+        match_hash = match_matches(gen_match, sp_match)
+      end
+      match_hash.merge({ "score" =>
+                       (1 - match_hash["edit_distance"]/(total_length/2)) })
+      match_hash
+    end
+
+    def match_genera(genus1, genus2, opts = {})
+      genus1_length = genus1[:normalized].size
+      genus2_length = genus2[:normalized].size
+      opts = { with_phonetic_match: true }.merge(opts)
+      min_length = [genus1_length, genus2_length].min
+      unless opts[:with_phonetic_match]
+        genus1[:phonetized] = "A"
+        genus2[:phonetized] = "B"
+      end
+      match = false
+      ed = @dlm.distance(genus1[:normalized],
+                         genus2[:normalized], 1, 3) #TODO put block = 2
+      return { "edit_distance" => ed,
+        "phonetic_match" => false,
+        "match" => false } if ed/min_length.to_f > 0.2
+      return { "edit_distance" => ed,
+        "phonetic_match" => true,
+        "match" => true } if genus1[:phonetized] == genus2[:phonetized]
+
+      match = true if ed <= 3 && (min_length > ed * 2) &&
+        (ed < 2 || genus1[0] == genus2[0])
+      { "edit_distance" => ed, "match" => match, "phonetic_match" => false }
+    end
+
+    def match_species(sp1, sp2, opts = {})
+      sp1_length = sp1[:normalized].size
+      sp2_length = sp2[:normalized].size
+      opts = { with_phonetic_match: true }.merge(opts)
+      min_length = [sp1_length, sp2_length].min
+      unless opts[:with_phonetic_match]
+        sp1[:phonetized] = "A"
+        sp2[:phonetized] = "B"
+      end
+      sp1[:phonetized] = Taxamatch::Phonetizer.normalize_ending sp1[:phonetized]
+      sp2[:phonetized] = Taxamatch::Phonetizer.normalize_ending sp2[:phonetized]
+      match = false
+      ed = @dlm.distance(sp1[:normalized],
+                         sp2[:normalized], 1, 4) #TODO put block 4
+      return { "edit_distance" => ed,
+        "phonetic_match" => false,
+        "match" => false } if ed/min_length.to_f > 0.3334
+      return {"edit_distance" => ed,
+        "phonetic_match" => true,
+        "match" => true} if sp1[:phonetized] == sp2[:phonetized]
+
+      match = true if ed <= 4 &&
+        (min_length >= ed * 2) &&
+        (ed < 2 || sp1[:normalized][0] == sp2[:normalized][0]) &&
+        (ed < 4 || sp1[:normalized][0...3] == sp2[:normalized][0...3])
+      { "edit_distance" => ed, "match" => match, "phonetic_match" => false }
+    end
+
+    def match_authors(preparsed_1, preparsed_2)
+      p1 = { normalized_authors: [], years: [] }
+      p2 = { normalized_authors: [], years: [] }
+      if preparsed_1[:infraspecies] || preparsed_2[:infraspecies]
+        p1 = preparsed_1[:infraspecies].last if preparsed_1[:infraspecies]
+        p2 = preparsed_2[:infraspecies].last if preparsed_2[:infraspecies]
+      elsif preparsed_1[:species] || preparsed_2[:species]
+        p1 = preparsed_1[:species] if preparsed_1[:species]
+        p2 = preparsed_2[:species] if preparsed_2[:species]
+      elsif preparsed_1[:uninomial] && preparsed_2[:uninomial]
+        p1 = preparsed_1[:uninomial]
+        p2 = preparsed_2[:uninomial]
+      end
+      au1 = p1[:normalized_authors]
+      au2 = p2[:normalized_authors]
+      yr1 = p1[:years]
+      yr2 = p2[:years]
+      return true if au1.empty? || au2.empty?
+      score = Taxamatch::Authmatch.authmatch(au1, au2, yr1, yr2)
+      score == 0 ? false : true
+    end
+
+    def match_matches(genus_match, species_match, infraspecies_match = nil)
+      match = species_match
+      if infraspecies_match
+        match["edit_distance"] += infraspecies_match["edit_distance"]
+        match["match"] &&= infraspecies_match["match"]
+        match["phonetic_match"] &&= infraspecies_match["phonetic_match"]
+      end
+      match["edit_distance"] += genus_match["edit_distance"]
+      if match["edit_distance"] > (infraspecies_match ? 6 : 4)
+        match["match"] = false
+      end
+      match["match"] &&= genus_match["match"]
+      match["phonetic_match"] &&= genus_match["phonetic_match"]
+      match
+    end
+  end
+end

data/lib/taxamatch_rb/version.rb

@@ -0,0 +1,7 @@
+module Taxamatch
+  VERSION = "1.1.0"
+
+  def self.version
+    VERSION
+  end
+end