gn_crossmap 2.3.1 → 3.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 017146ff7e76cd3dedfbf6af0960c043f05ea9d4
-  data.tar.gz: e580a9493d729eb78bbf0d05598aa6c470b70053
+  metadata.gz: 143661fa671afbd77e8f666ef883df2e127356fa
+  data.tar.gz: a809d9b2472bb8577fffc9df78b72557f7ff3200
 SHA512:
-  metadata.gz: b3ceff8590a56778deeeb226faef127b5ae32dc4728c818f2d575d1863d4a527e07278d3de6b6dd5cf59b75ad7d017a1e8032a3f7b7404923d62bc86f6e04866
-  data.tar.gz: f8feb027e0c8333187e83912acedb44e4efc535f1841c612810365e593e7517df89bcd88a1054401dd2ea77489736c4e4300e891fe9cb7686fc1a7a648b8a522
+  metadata.gz: 6dbc394ee6ae8e673f455dba4f789bc0ccded1b5c68ca51e19d1549233effeac417b26f7faa6fcac8a7b7db06f4a4d26e7f0944b5f9553673f82a752452e9048
+  data.tar.gz: 6e4be322cbd94e014ee70c9f009fe28c2da4f1b9012cf5cdfa2c0c8b62772dd69ed41ae1c42e917d2648ba3852a3c819add1f2813f85800156dff93f0d7111c0

data/.rubocop.yml

@@ -5,6 +5,8 @@ AllCops:
     - spec/**/*
   Include:
     - exe/crossmap
+    - "**/Gemfile"
+    - "**/Rakefile"
 Style/StringLiterals:
   EnforcedStyle: double_quotes
 Style/DotPosition:

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 # ``gn_crossmap`` CHANGELOG
 
+## 3.0.0
+
+* @dimus - allow lists without taxonID
+
 ## 2.3.1
 
 * @dimus - show resolver url in log

data/README.md

@@ -56,7 +56,8 @@ crossmap -i my_list.csv -o my_list_if.csv -d 5
 # to use standard intput and/or output
 cat my_list.csv | crossmap -i - -o - > output
 
-# to keep only taxonID from original input
+# to keep only taxonID (if given) from original input
+# no original fields will be kept without taxonID
 cat my_list.csv | crossmap -i my_list.csv -s
 ```
 
@@ -85,8 +86,9 @@ designates `STDIN`
 : (integer) id of a data source from [GN resolver][resolver]
 
 ``skip_original``
-: (boolean) if true only `taxonID` is preserved from original data. Otherwise
-all original data is preserved
+: (boolean) if true only `taxonID` (if given) is preserved
+from original data. Otherwise all original data is preserved. If there is no
+``taxonID``, no original data will be preserved.
 
 ``alt_headers``
 : (array) empty array by default. If `alt_headers` are not empty they are used
@@ -184,7 +186,14 @@ Match types dictionary can be accessed with `GnCrossmap::MATCH_TYPES` constant
 `subspecies` `variety` `form scientificNameAuthorship` `scientificName`
 `taxonRank`
 
-#### Simple Example
+#### simplest Example -- only scientificName
+
+| scientificName                                          |
+|---------------------------------------------------------|
+| Animalia                                                |
+| Macrobiotus echinogenitus subsp. areolatus Murray, 1907 |
+
+#### taxonID and scientificName Example
 
     taxonID;scientificName
     1;Macrobiotus echinogenitus subsp. areolatus Murray, 1907

data/Rakefile

@@ -8,4 +8,4 @@ end
 
 RuboCop::RakeTask.new
 
-task default: [:rubocop, :rspec]
+task default: %i(rubocop rspec)

data/gn_crossmap.gemspec

@@ -1,8 +1,12 @@
 # coding: utf-8
+
 lib = File.expand_path("../lib", __FILE__)
+
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require "gn_crossmap/version"
 
+# rubocop:disable Metrics/BlockLength:
+
 Gem::Specification.new do |gem|
   gem.required_ruby_version = ">= 2.1"
   gem.name          = "gn_crossmap"
@@ -12,7 +16,7 @@ Gem::Specification.new do |gem|
   gem.email         = ["dmozzherin@gmail.com"]
 
   gem.summary       = "Crossmaps a list of scientific names to names from " \
-                       "a data source in GN Index"
+                      "a data source in GN Index"
   gem.description   = "Gem uses a checklist in a comma-separated format as " \
                       "an input, and returns back a new comma-separated " \
                       "list crossmapping the scientific names to one of the " \
@@ -30,11 +34,13 @@ Gem::Specification.new do |gem|
   gem.add_dependency "biodiversity", "~> 3.1"
   gem.add_dependency "rest-client", "~> 2.0"
   gem.add_dependency "logger-colors", "~> 1.0"
+  gem.add_dependency "gn_uuid", "~> 0.5"
 
   gem.add_development_dependency "bundler", "~> 1.7"
   gem.add_development_dependency "rake", "~> 11.0"
   gem.add_development_dependency "rspec", "~> 3.2"
   gem.add_development_dependency "rubocop", "~> 0.31"
   gem.add_development_dependency "coveralls", "~> 0.8"
-  gem.add_development_dependency "gn_uuid", "~> 0.5"
 end
+
+# rubocop:enable Metrics/BlockLength:

data/lib/gn_crossmap.rb

@@ -5,6 +5,7 @@ require "tempfile"
 require "logger"
 require "logger/colors"
 require "biodiversity"
+require "gn_uuid"
 require "gn_crossmap/errors"
 require "gn_crossmap/version"
 require "gn_crossmap/reader"
@@ -57,6 +58,10 @@ module GnCrossmap
       logger.info(message)
     end
 
+    def find_id(row, name)
+      row.key?(:taxonid) ? row[:taxonid].strip : GnUUID.uuid(name)
+    end
+
     private
 
     def create_resolver(writer, opts)

data/lib/gn_crossmap/collector.rb

@@ -21,13 +21,6 @@ module GnCrossmap
     def init_fields_collector
       @fields = @row.map { |f| prepare_field(f) }
       @collector = collector_factory
-      err = "taxonID must be present in the csv header"
-      raise GnCrossmapError, err unless taxon_id?
-    end
-
-    def taxon_id?
-      @taxon_id_index = @fields.index(:taxonid)
-      !@taxon_id_index.nil?
     end
 
     def prepare_field(field)

data/lib/gn_crossmap/column_collector.rb

@@ -16,12 +16,12 @@ module GnCrossmap
 
     def id_name_rank(row)
       @row = row
-      id = @row[:taxonid]
-      return nil if id.to_s.strip == ""
       rank = find_rank
       return nil unless rank
       name = assemble_name(rank)
       return nil unless name
+      id = GnCrossmap.find_id(@row, name)
+      return nil if id.strip.to_s == ""
       { id: id, name: name, rank: rank.to_s }
     end
 

data/lib/gn_crossmap/sci_name_collector.rb

@@ -8,8 +8,8 @@ module GnCrossmap
 
     def id_name_rank(row)
       @row = row
-      id = @row[:taxonid]
       name = find_name
+      id = GnCrossmap.find_id(@row, name)
       rank = @row[:taxonrank]
       rank = parse_rank if rank.nil?
       id && name ? { id: id, name: name, rank: rank } : nil

data/lib/gn_crossmap/version.rb

@@ -1,6 +1,6 @@
 # Namespace module for crossmapping checklists to GN sources
 module GnCrossmap
-  VERSION = "2.3.1".freeze
+  VERSION = "3.0.0".freeze
 
   def self.version
     VERSION

data/lib/gn_crossmap/writer.rb

@@ -22,10 +22,10 @@ module GnCrossmap
     private
 
     def output_fields(original_fields)
-      original_fields + [:matchedType, :inputName, :matchedName,
-                         :matchedCanonicalForm, :inputRank, :matchedRank,
-                         :synonymStatus, :acceptedName, :matchedEditDistance,
-                         :matchedScore, :matchTaxonID]
+      original_fields + %i(matchedType inputName matchedName
+                           matchedCanonicalForm inputRank matchedRank
+                           synonymStatus acceptedName matchedEditDistance
+                           matchedScore matchTaxonID)
     end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: gn_crossmap
 version: !ruby/object:Gem::Version
-  version: 2.3.1
+  version: 3.0.0
 platform: ruby
 authors:
 - Dmitry Mozzherin
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-03-07 00:00:00.000000000 Z
+date: 2017-03-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: trollop
@@ -66,6 +66,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: gn_uuid
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.5'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.5'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -136,20 +150,6 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.8'
-- !ruby/object:Gem::Dependency
-  name: gn_uuid
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.5'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.5'
 description: Gem uses a checklist in a comma-separated format as an input, and returns
   back a new comma-separated list crossmapping the scientific names to one of the
   data sources from http://resolver.globalnames.org