taxonifi 0.6.0 → 0.6.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3ea1c5278c07b5da29b0d47833aa5049ea1bf1a67d8ee0e0457e24642c6afe33
-  data.tar.gz: 4e3b2e214b36f2dd861321e9539ff15d0075d4713563b5b170332c55ed51eb37
+  metadata.gz: db4b4d80d379ca1799481144f811c996353461ce352bab60a9d39c895165cd0a
+  data.tar.gz: 0f01744e01b482ac700a8ce4816aa7d7e679b36b0b6bb584898223bbed18132c
 SHA512:
-  metadata.gz: 29a4108207df9f6087a1cc741b226e72ec9273907d5a2e999a316d7fe194a45ccb6c13c9d7594744e510a47939dcc8ccc566bce48798547bd7917e4cdf2dac7d
-  data.tar.gz: cbf0e3345cfee7110b79eff07152ba828f69a20be204aba2c7460597b7295fea61aa6791770ad5a90348e9afa28a50d225e68e885912929880fcb5bb295b1dbc
+  metadata.gz: 35e1cea4409390f2655ec9ba87f648cd8f5073d305c3a702a36797897f9863bdfac38d612cfd2ac10b966adee4a2e570e9190e2b737bf7d44e3c01fd9e4aff65
+  data.tar.gz: c8de99997d43fc409db58697c9060529c38b10d3cce06ffa3786ba0f31d6c67dd1da955640eda336e54ceefc33c4fdfa26b2a85aa74e4f19efcef1232e11e0c0

data/.github/workflows/ruby.yml

@@ -20,15 +20,15 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, macos-latest, windows-latest]
-        ruby: [2.6, 2.7, 3.0]
+        ruby: [3.0, 3.4]
 
     steps:
     - uses: actions/checkout@v2
     - name: Set up Ruby
     # To automatically get bug fixes and new Ruby versions for ruby/setup-ruby,
     # change this to (see https://github.com/ruby/setup-ruby#versioning):
-    # uses: ruby/setup-ruby@v1
-      uses: ruby/setup-ruby@fdcfbcf14ec9672f6f615cb9589a1bc5dd69d262
+      uses: ruby/setup-ruby@v1
+    #  uses: ruby/setup-ruby@fdcfbcf14ec9672f6f615cb9589a1bc5dd69d262
       with:
         ruby-version: ${{ matrix.ruby }}
     - name: Install dependencies

data/.ruby-version

@@ -1 +1 @@
-3.0.2
+3.4.4

data/Gemfile.lock

@@ -1,38 +1,45 @@
 PATH
   remote: .
   specs:
-    taxonifi (0.6.0)
+    taxonifi (0.6.1)
+      csv (~> 3.3.5)
       require_all (~> 3.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
     awesome_print (1.9.2)
-    builder (3.2.4)
+    builder (3.3.0)
     byebug (11.1.3)
-    power_assert (2.0.1)
-    psych (4.0.3)
+    csv (3.3.5)
+    date (3.4.1)
+    erb (5.0.2)
+    power_assert (2.0.5)
+    psych (5.2.6)
+      date
       stringio
-    rake (13.0.6)
-    rdoc (6.4.0)
+    rake (13.3.0)
+    rdoc (6.14.2)
+      erb
       psych (>= 4.0.0)
     require_all (3.0.0)
-    stringio (3.0.1)
-    test-unit (3.3.9)
+    stringio (3.1.7)
+    test-unit (3.7.0)
       power_assert
 
 PLATFORMS
   ruby
+  x86_64-darwin-24
 
 DEPENDENCIES
   awesome_print (~> 1.8)
   builder (~> 3.2)
-  bundler (~> 2.1)
+  bundler (~> 2.7)
   byebug (~> 11)
   rake (~> 13.0)
   rdoc (~> 6.2)
   taxonifi!
-  test-unit (~> 3.3.5)
+  test-unit (~> 3.5)
 
 BUNDLED WITH
-   2.2.22
+   2.7.1

data/lib/taxonifi/lumper.rb

@@ -1,6 +1,6 @@
-# The lumper lumps! Tools for recognizing and using 
-# combinations of column types. 
-module Taxonifi::Lumper 
+# The lumper lumps! Tools for recognizing and using
+# combinations of column types.
+module Taxonifi::Lumper
   # Define groups of columns/fields and include
   # functionality to determine whether your
   # columns match a given set.
@@ -13,8 +13,8 @@ module Taxonifi::Lumper
   # !! Todo: map DwC URIs to these labels (at present they largely correllate with Tokens,
   # perhaps map URIs to tokens!?)
   QUAD =  ['genus', 'subgenus', 'species', 'subspecies']
-  
-  # Columns representing author and year 
+
+  # Columns representing author and year
   AUTHOR_YEAR = ['author', 'year']
 
   # A Hash of named column combinations
@@ -33,15 +33,15 @@ module Taxonifi::Lumper
 
   # Authors, Year, Title, Publication, Volume_Number Pages Cited_Page
 
-  # Lumps for which all columns are represented 
-  # TODO: This is really an assessor method 
+  # Lumps for which all columns are represented
+  # TODO: This is really an assessor method
   def self.available_lumps(columns)
     raise Taxonifi::Lumper::LumperError, 'Array not passed to Lumper.available_lumps.' if !(columns.class == Array)
     LUMPS.keys.select{|k| (LUMPS[k] - columns) == []}
   end
 
-  # Lumps for which any column is represented 
-  # # TODO: This is really an assessor method 
+  # Lumps for which any column is represented
+  # # TODO: This is really an assessor method
   def self.intersecting_lumps(columns)
     raise Taxonifi::Lumper::LumperError, 'Array not passed to Lumper.intersecting_lumps.' if !(columns.class == Array)
     intersections = []
@@ -51,7 +51,7 @@ module Taxonifi::Lumper
     intersections
   end
 
- 
+
   # return [Taxonifi::Model::NameCollection] from a csv file.
   def self.create_name_collection(options = {})
     opts = {
@@ -59,24 +59,24 @@ module Taxonifi::Lumper
       :initial_id => 0,
       :capture_related_fields => true   # Stores other column values in (column_header => value) pairs in Name#properties
     }.merge!(options)
-    
+
     csv = opts[:csv]
     raise Taxonifi::Lumper::LumperError, 'Something that is not a CSV::Table was passed to Lumper.create_name_collection.' if csv.class != CSV::Table
-    
+
     nc = Taxonifi::Model::NameCollection.new(:initial_id => opts[:initial_id])
     row_size = csv.size
 
     # The row index contains a vector of parent ids like
     # [0, 4, 29]
     # This implies that Name with #id 29 has Parent with #id 4
-    # Initialize an empty index. 
+    # Initialize an empty index.
     row_index = Taxonifi::Utils::Array.build_array_of_empty_arrays(row_size)
 
     # The name_index keeps track of unique name per rank like
     # :genus => {'Foo' => [0,2]}
     # This says that "Foo" is instantiated two times in the
     # name collection, with id 0, and id 2.
-    name_index = {} # Taxonifi::Lumper::NameIndex.new # {} 
+    name_index = {} # Taxonifi::Lumper::NameIndex.new # {}
 
     has_ref_fields = ([:citation_basic, :citation_small] & Taxonifi::Lumper.intersecting_lumps(csv.headers)).size > 0
     unused_fields = csv.headers - Taxonifi::Lumper::LUMPS[:names]
@@ -87,21 +87,21 @@ module Taxonifi::Lumper
       name_index[rank] = {}
       csv.each_with_index do |row, i|
         shares_rank = (rank == Taxonifi::Assessor::RowAssessor.lump_name_rank(row).to_s)
-        name = row[rank] 
+        name = row[rank]
 
         if !name.nil?     # cell has data
           n = nil         # a Name if necessary
-          name_id = nil   # index the new or existing Name 
+          name_id = nil   # index the new or existing Name
 
           exists = false
           if name_index[rank][name] # A matching name (String) has been previously added
             name_index[rank][name].each do |id|
               # Compare vectors of parent_ids for name presence
-              if nc.parent_id_vector(id) == row_index[i]      
+              if nc.parent_id_vector(id) == row_index[i]
                 exists = true
                 name_id = id
-                break 
-              end 
+                break
+              end
             end
           end # end name exists
 
@@ -110,22 +110,27 @@ module Taxonifi::Lumper
           unused_data = row.to_hash.select{|f| unused_fields.include?(f)}
           row_identifier = (row['identifier'] ? row['identifier'] : i)
 
-          # Populate the new name if created.  Previously matched names are not effected. 
-          if !n.nil? 
+          # Populate the new name if created.  Previously matched names are not effected.
+          if !n.nil?
             n.rank = rank
             n.name = name
-            n.parent = nc.object_by_id(row_index[i].last) if row_index[i].size > 0 # it's parent is the previous id in this row 
+            n.parent = nc.object_by_id(row_index[i].last) if row_index[i].size > 0 # it's parent is the previous id in this row
             n.row_number = i
 
             # Name/year needs to be standardized / cased out
             # headers are overlapping at times
 
             # Check to see if metadata (e.g. author year) apply to this rank, attach if so.
-            if shares_rank 
-              if row['author_year'] 
-                builder = Taxonifi::Splitter::Builder.build_author_year(row['author_year'])                
+            if shares_rank
+              if row['author_year']
+                begin
+                  builder = Taxonifi::Splitter::Builder.build_author_year(row['author_year'])
+                rescue Taxonifi::Splitter::SplitterError => e
+                  # Map i to user's row number: +1 for 1-based, +1 to account for header row.
+                  raise LumperError, "Failed to parse author_year string '#{row['author_year']}' in row #{i + 2}", e.backtrace
+                end
                 n.authors              = builder.people  # was author!?
-                n.year                 = builder.year 
+                n.year                 = builder.year
                 n.parens               = builder.parens
               end
 
@@ -135,29 +140,29 @@ module Taxonifi::Lumper
 
             name_id = nc.add_object(n).id
             name_index[rank][name] ||= []
-            name_index[rank][name].push name_id                
+            name_index[rank][name].push name_id
 
             $DEBUG && $stderr.puts("added #{nc.collection.size - 1} | #{n.name} | #{n.rank} | #{n.parent ? n.parent.name : '-'} | #{n.parent ? n.parent.id : '-'}")
           else
             $DEBUG && $stderr.puts("already present #{rank} | #{name}")
-            if shares_rank 
-              # original:: 
+            if shares_rank
+              # original::
               nc.add_duplicate_entry_metadata(name_id, row_identifier, unused_data)
 
-              # hack 
-              # nc.add_duplicate_entry_metadata(name_id, row_identifier, row.to_hash) 
-            
+              # hack
+              # nc.add_duplicate_entry_metadata(name_id, row_identifier, row.to_hash)
+
             end
           end
 
           # build a by row vector of parent child relationships
-          row_index[i].push name_id                       
+          row_index[i].push name_id
         end # end cell has data
 
       end
     end
     nc
-  end 
+  end
 
   # return [Taxonifi::Model::RefCollection] from a CSV file.
   def self.create_ref_collection(options = {})
@@ -180,7 +185,7 @@ module Taxonifi::Lumper
           :year => row['year'],
           :title => row['title'],
           :publication => row['publication']
-        ) 
+        )
 
         # TODO: break out each of these lexes to a builder
         if row['authors'] && !row['authors'].empty?
@@ -216,16 +221,16 @@ module Taxonifi::Lumper
             r.pages = row['pages']
           end
         end
-       
+
         r.add_properties(row.to_hash.select{|f| unused_fields.include?(f)}) if opts[:capture_related_fields]
 
         # Do some indexing.
-        ref_str = r.compact_string 
+        ref_str = r.compact_string
         if !ref_index.keys.include?(ref_str)
           ref_id = rc.add_object(r).id
           ref_index.merge!(ref_str => ref_id)
           # puts "#{i} : #{ref_id}"
-          rc.row_index[i] = r 
+          rc.row_index[i] = r
         else
           rc.row_index[i] = rc.object_by_id(ref_index[ref_str])
           # puts "#{i} : #{ref_index[ref_str]}"
@@ -267,9 +272,9 @@ module Taxonifi::Lumper
         name = row[rank]
         if !name.nil? && !name.empty?  # cell has data
           o = nil                      # a Name if necessary
-          name_id = nil                # index the new or existing name 
+          name_id = nil                # index the new or existing name
 
-          if name_index[rank][name] # Matching name is found 
+          if name_index[rank][name] # Matching name is found
 
             exists = false
             name_index[rank][name].each do |id|
@@ -287,25 +292,25 @@ module Taxonifi::Lumper
             o = Taxonifi::Model::GenericObject.new()
           end
 
-          if !o.nil? 
+          if !o.nil?
             o.name = name
             o.rank = rank
             o.row_number = i
-            o.parent = c.object_by_id(row_index[i].last) if row_index[i].size > 0 # it's parent is the previous id in this row 
+            o.parent = c.object_by_id(row_index[i].last) if row_index[i].size > 0 # it's parent is the previous id in this row
 
-            name_id = c.add_object(o).id 
+            name_id = c.add_object(o).id
             name_index[rank][name] ||= []
-            name_index[rank][name].push name_id                
+            name_index[rank][name].push name_id
           end
 
-          row_index[i].push name_id                       
+          row_index[i].push name_id
         end
       end
     end
     c
   end
 
-  # Return a geog collection from a csv file. 
+  # Return a geog collection from a csv file.
   def self.create_geog_collection(csv)
     raise Taxonifi::Lumper::LumperError, 'Something that is not a CSV::Table was passed to Lumper.create_geog_collection.' if csv.class != CSV::Table
     gc = Taxonifi::Model::GeogCollection.new
@@ -320,7 +325,7 @@ module Taxonifi::Lumper
     end
 
     # We don't have the same problems as with taxon names, i.e.
-    # boo in 
+    # boo in
     #  Foo nil boo
     #  Foo bar boo
     # is the same thing wrt geography, not the case for taxon names.
@@ -331,28 +336,28 @@ module Taxonifi::Lumper
         name = row[level]
         if !name.nil? && !name.empty?  # cell has data
           g = nil         # a Name if necessary
-          name_id = nil   # index the new or existing name 
+          name_id = nil   # index the new or existing name
 
           if name_index[level][name] # name exists
-            name_id  = name_index[level][name] 
+            name_id  = name_index[level][name]
           else
             g = Taxonifi::Model::Geog.new()
             name_id = gc.add_object(g).id
           end
 
-          if !g.nil? 
+          if !g.nil?
             g.name = name
             g.rank = level
-            g.parent = gc.object_by_id(row_index[i].last) if row_index[i].size > 0 # it's parent is the previous id in this row 
+            g.parent = gc.object_by_id(row_index[i].last) if row_index[i].size > 0 # it's parent is the previous id in this row
           end
 
           name_index[level][name] = name_id
-          row_index[i].push name_id                       
+          row_index[i].push name_id
         end
       end
     end
     gc
-  end 
+  end
 
-end # end Lumper Module 
+end # end Lumper Module
 

data/lib/taxonifi/splitter/builder.rb

@@ -1,4 +1,4 @@
-# Builder functionality for parsing/lexing framework. 
+# Builder functionality for parsing/lexing framework.
 module Taxonifi::Splitter::Builder
 
   # Load all builders (= models)
@@ -7,8 +7,11 @@ module Taxonifi::Splitter::Builder
 
   # Build and return Taxonifi::Model::AuthorYear from a string.
   def self.build_author_year(text)
-    lexer = Taxonifi::Splitter::Lexer.new(text)
+    text = text&.strip
     builder = Taxonifi::Model::AuthorYear.new
+    return builder if text.nil? || text.empty?
+
+    lexer = Taxonifi::Splitter::Lexer.new(text)
     Taxonifi::Splitter::Parser.new(lexer, builder).parse_author_year
     builder
   end

data/lib/taxonifi/version.rb

@@ -1,3 +1,3 @@
 module Taxonifi 
-  VERSION = "0.6.0"
+  VERSION = "0.6.1"
 end

data/taxonifi.gemspec

@@ -25,17 +25,19 @@ Gem::Specification.new do |s|
   s.homepage = "https://github.com/SpeciesFile/taxonifi"
   s.licenses = ["MIT"]
   s.require_paths = ["lib"]
-  s.rubygems_version = "2.4.5"
+  s.rubygems_version = "3.2.22"
   s.metadata = { "source_code_uri" => "https://github.com/SpeciesFileGroup/taxonifi" }
 
   s.add_dependency "require_all", "~> 3.0"
-  s.required_ruby_version = '>= 2.6', '< 4'
+  s.add_dependency "csv", "~> 3.3.5"
+
+  s.required_ruby_version = '>= 3.0', '< 4'
 
   s.add_development_dependency "rake", '~> 13.0'
   s.add_development_dependency "byebug", "~> 11"
-  s.add_development_dependency "bundler", "~> 2.1"
+  s.add_development_dependency "bundler", "~> 2.7"
   s.add_development_dependency 'awesome_print', '~> 1.8'
-  s.add_development_dependency 'test-unit', '~> 3.3.5'
+  s.add_development_dependency 'test-unit', '~> 3.5'
   s.add_development_dependency "rdoc", "~> 6.2"
   s.add_development_dependency "builder", "~> 3.2"
 

data/test/test_lumper_names.rb

@@ -25,7 +25,7 @@ class Test_TaxonifiLumperNames < Test::Unit::TestCase
   def test_available_lumps
     assert Taxonifi::Lumper.available_lumps( Taxonifi::Lumper::QUAD ).include?(:quadrinomial)
     assert Taxonifi::Lumper.available_lumps( Taxonifi::Lumper::AUTHOR_YEAR + Taxonifi::Lumper::QUAD ).include?(:quad_author_year)
-    assert !Taxonifi::Lumper.available_lumps( Taxonifi::Lumper::AUTHOR_YEAR + Taxonifi::Lumper::QUAD ).include?(:names) 
+    assert !Taxonifi::Lumper.available_lumps( Taxonifi::Lumper::AUTHOR_YEAR + Taxonifi::Lumper::QUAD ).include?(:names)
   end
 
   def test_create_name_collection_creates_a_name_collection
@@ -49,7 +49,7 @@ class Test_TaxonifiLumperNames < Test::Unit::TestCase
     assert_equal 0, nc.collection.first.row_number
     assert_equal 0, nc.collection.last.row_number
   end
-  
+
   def test_that_create_name_collection_parentifies
     nc = Taxonifi::Lumper.create_name_collection(:csv => @csv)
     assert_equal nc.collection[0], nc.collection[1].parent
@@ -87,18 +87,18 @@ class Test_TaxonifiLumperNames < Test::Unit::TestCase
       csv << ["Fooidae", "Foo", "bar", "Smith, 1854"]
       csv << ["Fooidae", "Foo", "foo", "(Smith and Jones, 1854)"]
     end
-   
+
     # 0  Fooidae
     # 1  Foo
     # 2  bar
-    # 3  foo 
+    # 3  foo
 
     csv = CSV.parse(string, headers: true)
     nc = Taxonifi::Lumper.create_name_collection(:csv => csv)
     assert_equal 2, nc.collection[3].authors.size
     assert_equal 'Smith', nc.collection[3].authors.first.last_name
     assert_equal 1854, nc.collection[3].year
-    
+
     assert_equal 'Smith, 1854', nc.collection[2].author_year
     assert_equal 'Smith', nc.collection[2].author_with_parens
 
@@ -115,12 +115,38 @@ class Test_TaxonifiLumperNames < Test::Unit::TestCase
     assert_equal true, nc.collection[3].parens
   end
 
+  def test_that_create_a_name_collection_ignores_whitespace_author_year
+    string = CSV.generate() do |csv|
+      csv << %w{family genus species author_year}
+      csv << ["Fooidae", "Foo", "bar", " "]
+    end
+
+    csv = CSV.parse(string, headers: true)
+    nc = Taxonifi::Lumper.create_name_collection(:csv => csv)
+    assert_equal 0, nc.collection[2].authors.size
+    assert_equal nil, nc.collection[2].author_year
+  end
+
+  def test_that_create_a_name_collection_throws_lumper_error_on_bad_author_year
+    string = CSV.generate() do |csv|
+      csv << %w{family genus species author_year}
+      csv << ["Fooidae", "Foo", "bar", ")Smith)"]
+    end
+
+    csv = CSV.parse(string, headers: true)
+    e = assert_raises Taxonifi::Lumper::LumperError do
+      Taxonifi::Lumper.create_name_collection(:csv => csv)
+    end
+
+    assert_match("')Smith)' in row 2", e.message)
+  end
+
   def test_that_create_a_name_collection_handles_related_columns
     string = CSV.generate() do |csv|
       csv << %w{family genus species author_year foo bar Stuff}
       csv << ["Fooidae", "Foo", "bar", "Smith, 1854"  , nil,  1 , "one"]
     end
-   
+
     # 0  Fooidae
     # 1  Foo
     # 2  bar
@@ -145,9 +171,9 @@ class Test_TaxonifiLumperNames < Test::Unit::TestCase
     # 1  Foo
     # 2  bar
     # 3  foo
-    # 4  varblorf 
-    # 5  varblorf 
-    # 6  varbliff 
+    # 4  varblorf
+    # 5  varblorf
+    # 6  varbliff
 
     csv = CSV.parse(string, headers: true)
     nc = Taxonifi::Lumper.create_name_collection(:csv => csv)
@@ -176,5 +202,5 @@ class Test_TaxonifiLumperNames < Test::Unit::TestCase
 
 #--- reference collections
 
-end 
+end
 

metadata

@@ -1,11 +1,10 @@
 --- !ruby/object:Gem::Specification
 name: taxonifi
 version: !ruby/object:Gem::Version
-  version: 0.6.0
+  version: 0.6.1
 platform: ruby
 authors:
 - Matt Yoder
-autorequire:
 bindir: bin
 cert_chain: []
 date: 2013-03-27 00:00:00.000000000 Z
@@ -24,6 +23,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: csv
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.3.5
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.3.5
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -58,14 +71,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.1'
+        version: '2.7'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.1'
+        version: '2.7'
 - !ruby/object:Gem::Dependency
   name: awesome_print
   requirement: !ruby/object:Gem::Requirement
@@ -86,14 +99,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 3.3.5
+        version: '3.5'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 3.3.5
+        version: '3.5'
 - !ruby/object:Gem::Dependency
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
@@ -207,7 +220,6 @@ licenses:
 - MIT
 metadata:
   source_code_uri: https://github.com/SpeciesFileGroup/taxonifi
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -215,7 +227,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.6'
+      version: '3.0'
   - - "<"
     - !ruby/object:Gem::Version
       version: '4'
@@ -225,8 +237,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.22
-signing_key:
+rubygems_version: 3.7.1
 specification_version: 4
 summary: A general purpose framework for scripted handling of taxonomic names or other
   heirarchical metadata.