dwc-archive 0.9.6 → 1.1.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: a5d4e174cb4ec6df2328fe99abb52b13587c74f22f01efb2a9017db4d9f1d7ba
+  data.tar.gz: e341038db2a23282173cf2e4671750739464dca6076f7560694cc40251bdd036
+SHA512:
+  metadata.gz: 8b51b82724e21acab76e1763dc2375658080a16dc440c9913fd632aff195a45c34e7bf9446cf5d4afc9fc397c8ee562763ab36532ab5992421e5ed3f2df64273
+  data.tar.gz: 04cbcc92c8b565b2c5f8e8bf082d284b65c55520d91f19c16bc63789519ea374f5ed0466c176ce69907a83566caa8efd2f834399f7b57a26801603455cf2b118

data/.gitignore

@@ -0,0 +1,31 @@
+## MAC OS
+.DS_Store
+
+## TEXTMATE
+*.tmproj
+tmtags
+
+## EMACS
+*~
+\#*
+.\#*
+
+## VIM
+*.swp
+
+## PROJECT::GENERAL
+coverage
+rdoc
+pkg
+install
+Gemfile.lock
+
+## PROJECT::SPECIFIC
+tags
+bin
+.bundle
+bundle_bin
+Gemfile.lock
+.byebug_history
+
+

data/.rspec

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

data/.rubocop.yml

@@ -0,0 +1,23 @@
+AllCops:
+  TargetRubyVersion: 2.6
+  Exclude:
+    - features/**/*
+    - .bundle/**/*
+    - bundle_bin/**/*
+    - lib/dwc_archive/ingester.rb
+    - lib/dwc_archive/generator_meta_xml.rb
+    - lib/dwc_archive/generator_eml_xml.rb
+    - lib/dwc_archive/classification_normalizer.rb
+
+Style/StringLiterals:
+  EnforcedStyle: double_quotes
+
+Layout/DotPosition:
+  EnforcedStyle: trailing
+
+Metrics/BlockLength:
+  Exclude:
+    - 'Rakefile'
+    - '*.gemspec'
+    - '**/*.rake'
+    - 'spec/**/*spec.rb'

data/.ruby-version

@@ -0,0 +1 @@
+2.7.1

data/.travis.yml

@@ -1,14 +1,13 @@
 rvm:
-  - 1.9.3
-  - 2.0.0
+  - 2.5
+  - 2.6
+  - 2.7
 before_install:
   - sudo apt-get update
-  - sudo apt-get install redis-server
-bundler_args: --without development
+  - gem install bundler
 script:
   - bundle exec cucumber
   - bundle exec rake
 branches:
   only:
       - master
-

data/CHANGELOG

@@ -1,13 +1,21 @@
-0.9.6 Added support for GNUB DwCA files
+1.1.0  Update name parser to go-based biodiversity
 
-0.9.4 Gem dependencies updated, added travis support
+1.0.1  Cleanup and gems update
 
-0.9.0 Migrated code to ruby 1.9.3
+0.9.11 Removed VERSION duplicate
 
-0.8.3 Updated outdated exception rasing
+0.9.7  Refactoring and tests improvements
 
-0.8.2 Removed species info from linnean classification path
+0.9.6  Added support for GNUB DwCA files
 
-0.8.1 Linnean classification path is now only for species and infraspecies with canonical forms. It ends with a canonical form of the taxon
+0.9.4  Gem dependencies updated, added travis support
 
-0.8.0 Added linnean classification path to normalized data from DwCA. It consists of data associated with clades like 'kingdom', 'order' etc.
+0.9.0  Migrated code to ruby 1.9.3
+
+0.8.3  Updated outdated exception rasing
+
+0.8.2  Removed species info from linnean classification path
+
+0.8.1  Linnean classification path is now only for species and infraspecies with canonical forms. It ends with a canonical form of the taxon
+
+0.8.0  Added linnean classification path to normalized data from DwCA. It consists of data associated with clades like 'kingdom', 'order' etc.

data/Gemfile

@@ -1,17 +1,5 @@
-source 'https://rubygems.org'
+# frozen_string_literal: true
 
-gem 'nokogiri', '~> 1.5'
-gem 'parsley-store', '~> 0.3.2'
-gem 'archive-tar-minitar', '~> 0.5'
+source "https://rubygems.org"
 
-group :development do
-  gem 'debugger', '~> 1.3'
-end
-
-group :test do
-  gem 'rspec', '~> 2.13'
-  gem 'cucumber', '~> 1.3'
-  gem 'bundler', '~> 1.3'
-  gem 'jeweler', '~> 1.8'
-  gem 'jazz_hands', '~> 0.5'
-end
+gemspec

data/LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2010-2012 Marine Biological Laboratory
+Copyright (c) 2010-2020 Dmitry Mozzherin
 
 Permission is hereby granted, free of charge, to any person obtaining
 a copy of this software and associated documentation files (the

data/README.md

@@ -3,145 +3,156 @@ Darwin Core Archive
 
 [![Gem Version][1]][2]
 [![Continuous Integration Status][3]][4]
-[![Dependency Status][5]][6]
+[![Coverage Status][5]][6]
+[![CodePolice][7]][8]
+[![Dependency Status][9]][10]
 
 Darwin Core Archive format is a current standard for information exchange
 between Global Names Architecture modules. This gem allows to work with
 Darwin Core Archive data compressed to either zip or tar.gz files.
-More information about Darwing Core Archive can be found on a [GBIF page:][7]
+More information about Darwing Core Archive can be found on a [GBIF page:][11]
 
 Installation
 ------------
 
     sudo gem install dwc-archive
 
+### System Requirements
+
+You need [Redis Server][12] and unzip library installed
+
+
 Usage
 -----
 
-    require 'rubygems'
-    require 'dwc-archive'
+```ruby
+require 'rubygems'
+require 'dwc_archive'
 
-    dwc = DarwinCore.new('/path_to_file/archive_file.tar.gz')
-    dwc.archive.files      # the archive file list
-    dwc.metadata.data      # summary of metadata from eml.xml if it exists
-    dwc.metadata.authors   # authors of the archive
-    dwc.core.data          # summary of DarwinCore main file
-    dwc.core.file_path     # path to the DarwinCore main file
-    dwc.extensions         # array of DarwinCore Star extensions
-    dwc.extensions[0].data # summary for an extension
+dwc = DarwinCore.new('/path_to_file/archive_file.tar.gz')
+dwc.archive.files      # the archive file list
+dwc.metadata.data      # summary of metadata from eml.xml if it exists
+dwc.metadata.authors   # authors of the archive
+dwc.core.data          # summary of DarwinCore main file
+dwc.core.file_path     # path to the DarwinCore main file
+dwc.extensions         # array of DarwinCore Star extensions
+dwc.extensions[0].data # summary for an extension
 
-    # read content of the core data file into memory or used with a block
-    # it returns array of arrays of data
-    # rows that had a wrong encoding will be collected into errors array
-    data, errors = dwc.core.read
+# read content of the core data file into memory or used with a block
+# it returns array of arrays of data
+# rows that had a wrong encoding will be collected into errors array
+data, errors = dwc.core.read
 
-    # read content using a block, getting back results in sets of 100 rows each
-    results = []
-    tail_data, tail_errors = dwc.core.read(100) do |data, errors|
-      results << [data, errors]
-    end
-    results << [tail_data, tail_errors]
+# read content using a block, getting back results in sets of 100 rows each
+results = []
+tail_data, tail_errors = dwc.core.read(100) do |data, errors|
+  results << [data, errors]
+end
+results << [tail_data, tail_errors]
 
-    # read content of an extension data file into memory
-    data, errors = dwc.core.extensions[0].read
+# read content of an extension data file into memory
+data, errors = dwc.core.extensions[0].read
 
-    # read content of an extension data using block
-    results = []
-    tail_data, tail_errors = dwc.core.extensions[0](100) do |data, errors|
-      results << [data, errors]
-    end
-    results << [tail_data, tail_errors]
+# read content of an extension data using block
+results = []
+tail_data, tail_errors = dwc.core.extensions[0](100) do |data, errors|
+  results << [data, errors]
+end
+results << [tail_data, tail_errors]
 
-    # normalize names in classification collecting together synonyms,
-    # canonical names, vernacular names and associating paths to taxons
-    # in a classification distributed as DwCA file
+# normalize names in classification collecting together synonyms,
+# canonical names, vernacular names and associating paths to taxons
+# in a classification distributed as DwCA file
 
-    result = dwc.normalize_classification
+result = dwc.normalize_classification
 
-    # for a finer control over normalization:
+# for a finer control over normalization:
 
-    cn = DarwinCore::ClassificationNormalizer.new(dwc)
-    cn.normalize
-    # if you don't want to generate path consisting of canonical forms
-    # of ancestors to a taxon
-    cn.normalize(:with_canonical_names => false)
+cn = DarwinCore::ClassificationNormalizer.new(dwc)
+cn.normalize
+# if you don't want to generate path consisting of canonical forms
+# of ancestors to a taxon
+cn.normalize(:with_canonical_names => false)
 
-    # if you don't want to ingest information from extensions
-    cn.normalize(:with_extensions => false)
+# if you don't want to ingest information from extensions
+cn.normalize(:with_extensions => false)
 
-    # to get a flat hash of nodes with attached vernacular names and synonyms
-    normalized_data = cn.normalized_data
+# to get a flat hash of nodes with attached vernacular names and synonyms
+normalized_data = cn.normalized_data
 
-    # to get a representation of tree organization as a hash
-    classification_tree = cn.tree
+# to get a representation of tree organization as a hash
+classification_tree = cn.tree
 
-    # to get list of all name strings used as scientific or vernacular names
-    all_name_strings = cn.name_strings
+# to get list of all name strings used as scientific or vernacular names
+all_name_strings = cn.name_strings
 
-    # to get list of errors generated during the normalization
-    errors = cn.error_names
+# to get list of errors generated during the normalization
+errors = cn.error_names
 
-    DarwinCore.clean_all   # remove all expanded archives
+DarwinCore.clean_all   # remove all expanded archives
+```
 
 Creating a DarwinCore Archive file
 ----------------------------------
 
-    gen = DarwinCore::Generator.new('/tmp/dwc_birches.tar.gz')
-
-    core = [
-      ["http://rs.tdwg.org/dwc/terms/taxonID",
-       "http://rs.tdwg.org/dwc/terms/parentNameUsageID",
-       "http://rs.tdwg.org/dwc/terms/scientificName",
-       "http://rs.tdwg.org/dwc/terms/taxonRank"],
-      [1, 0, "Plantae", "kingdom"],
-      [2, 1, "Betula", "genus"],
-      [3, 2, "Betula verucosa", "species"]
-    ]
-
-    vernacular_names = [
-      ["http://rs.tdwg.org/dwc/terms/TaxonID",
-      "http://rs.tdwg.org/dwc/terms/vernacularName"],
-      [1, "Plants"],
-      [1, "Растения"],
-      [2, "Birch"],
-      [2, "Береза"],
-      [3, "Wheeping Birch"],
-      [3, "Береза плакучая"]
-    ]
-
-    eml = {
-      :id => '1234',
-      :license => 'http://creativecommons.org/licenses/by-sa/3.0/',
-      :title => 'Test Classification',
-      :authors => [
-        { :first_name => 'John',
-          :last_name => 'Doe',
-          :email => 'jdoe@example.com',
-          :organization => 'Example',
-          :position => 'Assistant Professor',
-          :url => 'http://example.org' },
-          { :first_name => 'Jane',
-            :last_name => 'Doe',
-            :email => 'jane@example.com' }
-    ],
-      :metadata_providers => [
-        { :first_name => 'Jim',
-          :last_name => 'Doe',
-          :email => 'jimdoe@example.com',
-          :url => 'http://aggregator.example.org' }],
-      :abstract => 'test classification',
-      :citation =>
-        'Test classification: Doe John, Doe Jane, Taxnonmy, 10, 1, 2010',
-      :url => 'http://example.com'
-    }
-
-    gen.add_core(core, 'core.txt')
-    gen.add_extension(vernacular_names,
-                      'vernacular_names.txt',
-                      true, 'http://rs.gbif.org/terms/1.0/VernacularName')
-    gen.add_meta_xml
-    gen.add_eml_xml(eml)
-    gen.pack
+```ruby
+gen = DarwinCore::Generator.new('/tmp/dwc_birches.tar.gz')
+
+core = [
+  ["http://rs.tdwg.org/dwc/terms/taxonID",
+   "http://rs.tdwg.org/dwc/terms/parentNameUsageID",
+   "http://rs.tdwg.org/dwc/terms/scientificName",
+   "http://rs.tdwg.org/dwc/terms/taxonRank"],
+  [1, 0, "Plantae", "kingdom"],
+  [2, 1, "Betula", "genus"],
+  [3, 2, "Betula verucosa", "species"]
+]
+
+vernacular_names = [
+  ["http://rs.tdwg.org/dwc/terms/TaxonID",
+  "http://rs.tdwg.org/dwc/terms/vernacularName"],
+  [1, "Plants"],
+  [1, "Растения"],
+  [2, "Birch"],
+  [2, "Береза"],
+  [3, "Wheeping Birch"],
+  [3, "Береза плакучая"]
+]
+
+eml = {
+  :id => '1234',
+  :license => 'http://creativecommons.org/licenses/by-sa/3.0/',
+  :title => 'Test Classification',
+  :authors => [
+    { :first_name => 'John',
+      :last_name => 'Doe',
+      :email => 'jdoe@example.com',
+      :organization => 'Example',
+      :position => 'Assistant Professor',
+      :url => 'http://example.org' },
+      { :first_name => 'Jane',
+        :last_name => 'Doe',
+        :email => 'jane@example.com' }
+],
+  :metadata_providers => [
+    { :first_name => 'Jim',
+      :last_name => 'Doe',
+      :email => 'jimdoe@example.com',
+      :url => 'http://aggregator.example.org' }],
+  :abstract => 'test classification',
+  :citation =>
+    'Test classification: Doe John, Doe Jane, Taxnonmy, 10, 1, 2010',
+  :url => 'http://example.com'
+}
+
+gen.add_core(core, 'core.txt')
+gen.add_extension(vernacular_names,
+                  'vernacular_names.txt',
+                  true, 'http://rs.gbif.org/terms/1.0/VernacularName')
+gen.add_meta_xml
+gen.add_eml_xml(eml)
+gen.pack
+```
 
 Logging
 -------
@@ -168,12 +179,25 @@ Note on Patches/Pull Requests
 Copyright
 ---------
 
-Copyright (c) 2010-2013 Marine Biological Laboratory. See LICENSE for details.
+Author -- [@dimus][13]
+
+Contributors -- [@mjy][14], [@LocoDelAssembly][16]
+
+Copyright (c) 2010-2020 [@dimus][15]. See LICENSE for details.
 
 [1]: https://badge.fury.io/rb/dwc-archive.png
 [2]: http://badge.fury.io/rb/dwc-archive
 [3]: https://secure.travis-ci.org/GlobalNamesArchitecture/dwc-archive.png
 [4]: http://travis-ci.org/GlobalNamesArchitecture/dwc-archive
-[5]: https://gemnasium.com/GlobalNamesArchitecture/dwc-archive.png
-[6]: https://gemnasium.com/GlobalNamesArchitecture/dwc-archive
-[7]: http://bit.ly/2IxcBA
+[5]: https://coveralls.io/repos/GlobalNamesArchitecture/dwc-archive/badge.png
+[6]: https://coveralls.io/r/GlobalNamesArchitecture/dwc-archive
+[7]: https://codeclimate.com/github/GlobalNamesArchitecture/dwc-archive.png
+[8]: https://codeclimate.com/github/GlobalNamesArchitecture/dwc-archive
+[9]: https://gemnasium.com/GlobalNamesArchitecture/dwc-archive.png
+[10]: https://gemnasium.com/GlobalNamesArchitecture/dwc-archive
+[11]: http://bit.ly/2IxcBA
+[12]: http://redis.io/topics/quickstart
+[13]: https://github.com/dimus
+[14]: https://github.com/mjy
+[15]: http://mbl.edu
+[16]: https://github.com/LocoDelAssembly

data/Rakefile

@@ -1,62 +1,21 @@
-require 'rubygems'
-require 'rake'
+# frozen_string_literal: true
 
-begin
-  require 'jeweler'
-  Jeweler::Tasks.new do |gem|
-    gem.name = "dwc-archive"
-    gem.summary = %Q{Handler of Darwin Core Archive files}
-    gem.description = 'Darwin Core Archive is the current standard exchange ' +
-      'format for GLobal Names Architecture modules. ' +
-      'This gem makes it easy to incorporate files in ' +
-      'Darwin Core Archive format into a ruby project.'
-    gem.email = "dmozzherin at gmail dot com"
-    gem.homepage = "http://github.com/GlobalNamesArchitecture/dwc-archive"
-    gem.authors = ["Dmitry Mozzherin"]
-    #gem.add_dependency "fastercsv" if RUBY_VERSION.match /^1.8/
-    gem.add_dependency 'parsley-store', ">= 0.3.0"
-    gem.add_development_dependency "rspec", ">= 1.2.9"
-    gem.add_development_dependency "cucumber", ">= 0"
-  end
-  Jeweler::GemcutterTasks.new
-rescue LoadError
-  puts 'Jeweler (or a dependency) not available. ' +
-    'Install it with: gem install jeweler'
-end
-
-require 'rspec/core/rake_task'
-RSpec::Core::RakeTask.new(:spec) do |spec|
-  spec.pattern = 'spec/**/*_spec.rb'
-end
-
-RSpec::Core::RakeTask.new(:rcov) do |spec|
-  spec.pattern = 'spec/**/*_spec.rb'
-  spec.rcov = true
-end
-
-# task :spec => :check_dependencies
-
-begin
-  require 'cucumber/rake/task'
-  Cucumber::Rake::Task.new(:features)
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+require "cucumber/rake/task"
 
-  task :features => :check_dependencies
-rescue LoadError
-  task :features do
-    abort 'Cucumber is not available. In order to run features, ' +
-      'you must: sudo gem install cucumber'
-  end
+RSpec::Core::RakeTask.new(:rspec) do |rspec|
+  rspec.pattern = "spec/**/*_spec.rb"
 end
 
-desc 'Run an IRB session with CSL loaded'
-task :irb, [:script] do |t, args|
-  ARGV.clear
+Cucumber::Rake::Task.new(:features)
 
-  require 'irb'
-  require_relative 'lib/dwc-archive'
+# task rspec: :check_dependencies
+task features: :check_dependencies
 
-  IRB.conf[:SCRIPT] = args.script
-  IRB.start
+desc "open an irb session preloaded with this library"
+task :console do
+  sh "irb -I lib -I extra -r dwc_archive.rb"
 end
 
-task :default => :spec
+task default: :rspec