biodiversity 5.1.0 → 5.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b9df90a14b8fcc999def9b89b58ea277e37749eca303f858ebaee03159bb60d8
-  data.tar.gz: b6f8ed59091c85d12fb660a608444f94c2974c4f7720e7b085b5c02265cad296
+  metadata.gz: b281d6c55701570148a6e42577c6e981c23e2bdf6558dafc27aaa9c89dfdcc0d
+  data.tar.gz: 0e54a072a72fe7f2e5b76917766d044d945a44859b61cdc51247c3ac95f386b8
 SHA512:
-  metadata.gz: b2c749612aed3f60f3fc3041a4685a7f45651ba438d7058687433a8b039443487b3e2e9ff90cf9a976cab5b183bac513ae611d238ceed2353e3ad491f963e81c
-  data.tar.gz: 2765731a3d3a9dfd5bb346246ce8afe741bf9a0b74e9c50bced34d3f82da9ce5e1a56c6d671373b6c0973e4afc63f913bc7badf2f7073f059a2c38aeebfc817c
+  metadata.gz: 5ce44a6dcefcaf1ab262c3d2fd8593d8fabadeab5a5f4c167e6b921f4b66ebf96212bacab809c1765b4eba87a4adc58539449a1aad95cf5e381c87f3edb0326b
+  data.tar.gz: b8c0077f1eaa45fb89055431ab3807869acb7a87c8d4f6955bdbdd9364647cb13dea0bb36f4949f8a571e31d89dd1ce2215cec1c053265376995e229e962e5a7

data/.rubocop.yml

@@ -14,6 +14,10 @@ Metrics/MethodLength:
 Metrics/BlockLength:
   Exclude:
     - spec/**/*
+Metrics/CyclomaticComplexity:
+  Enabled: false
+Metrics/PerceivedComplexity:
+  Enabled: false
 Style/HashEachMethods:
   Enabled: true
 Style/HashTransformKeys:

data/.ruby-version

@@ -1 +1 @@
-3.0.0
+3.0.1

data/CHANGELOG

@@ -1,3 +1,9 @@
+5.1.2 -- upgrade to gnparser v1.0.2
+
+5.1.1 -- simplified signature of methods
+
+5.1.0 -- changed sinature of methods
+
 5.0.0 -- changed GNparser to v 1.0.0
 
 4.0.3 -- fix memory leak in parse_ary method

data/README.md

@@ -1,5 +1,4 @@
-Biodiversity
-============
+# Biodiversity
 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3569596.svg)](https://doi.org/10.5281/zenodo.3569596)
 [![Gem Version][gem_svg]][gem_link]
@@ -8,12 +7,12 @@ Biodiversity
 Parses taxonomic scientific name and breaks it into semantic elements.
 
 **Important**: Biodiversity parser >= 4.0.0 uses binding to
-https://gitlab.com/gogna/gnparser and
+`https://github.com/gnames/gnparser` and
 is not backward compatible with older versions. However it is much much faster
 and better than previous versions.
 
 This gem does not have a remote server or a command line executable anymore.
-For such features use https://gitlab.com/gogna/gnparser.
+For such features use `https://github.com/gnames/gnparser`.
 
 - [Biodiversity](#biodiversity)
   - [Installation](#installation)
@@ -24,7 +23,9 @@ For such features use https://gitlab.com/gogna/gnparser.
 
 ## Installation
 
-    sudo gem install biodiversity
+```bash
+sudo gem install biodiversity
+```
 
 The gem should work on Linux, Mac and Windows (64bit) machines
 
@@ -64,7 +65,6 @@ million names on a 4CPU hyperthreaded laptop:
 
 You can use it as a library in Ruby:
 
-
 ```ruby
 require 'biodiversity'
 
@@ -92,7 +92,6 @@ Biodiversity::Parser.parse("Plantago").to_json
 # to clean name up
 Biodiversity::Parser.parse("      Plantago       major    ")[:normalized]
 
-
 # to get canonical form with or without infraspecies ranks, as well as
 # stemmed version.
 parsed = Biodiversity::Parser.parse("Seddera latifolia H. & S. var. latifolia")
@@ -103,6 +102,9 @@ parsed[:canonicalName][:stem]
 # to get detailed information about elements of the name
 Biodiversity::Parser.parse("Pseudocercospora dendrobii (H.C. Burnett 1883) U. \
 Braun & Crous 2003")[:details]
+
+# to parse a botanical cultivar
+Biodiversity::Parser.parse("Sarracenia flava 'Maxima'", with_cultivars: true)
 ```
 
 'Surrogate' is a broad group which includes 'Barcode of Life' names, and various
@@ -111,6 +113,7 @@ undetermined names with cf. sp. spp. nr. in them:
 ```ruby
 parser.parse("Coleoptera BOLD:1234567")[:surrogate]
 ```
+
 ### What is "nameStringID" in the parsed results?
 
 ID field contains UUID v5 hexadecimal string. ID is generated out of bytes
@@ -118,18 +121,16 @@ from the name string itself, and identical id can be generated using [any
 popular programming language][uuid_examples]. You can read more about UUID
 version 5 in a [blog post][uuid_blog]
 
-For example "Homo sapiens" should generate "16f235a0-e4a3-529c-9b83-bd15fe722110" UUID
+For example "Homo sapiens" should generate
+"16f235a0-e4a3-529c-9b83-bd15fe722110" UUID
 
-Copyright
----------
+## Copyright
 
 Authors: [Dmitry Mozzherin][dimus]
 
 Contributors: [Patrick Leary][pleary], [Hernán Lucas Pereira][hernan]
 
-
-
-Copyright (c) 2008-2020 Dmitry Mozzherin. See [LICENSE][license]
+Copyright (c) 2008-2021 Dmitry Mozzherin. See [LICENSE][license]
 for further details.
 
 [gem_svg]: https://badge.fury.io/rb/biodiversity.svg

data/clib/linux/libgnparser.h

@@ -19,7 +19,7 @@ typedef struct { const char *p; ptrdiff_t n; } _GoString_;
 /* Start of preamble from import "C" comments.  */
 
 
-#line 3 "main.go"
+#line 5 "main.go"
 
 	#include "stdlib.h"
 
@@ -80,7 +80,7 @@ extern "C" {
 // 'csv', 'compact', 'pretty'. If withDetails argument is 0, additional
 // parsed details are ommited, if it is 1 -- they are included.
 // true.
-extern char* ParseToString(char* name, char* f, int details);
+extern char* ParseToString(char* name, char* f, int details, int cultivars);
 
 // FreeMemory takes a string pointer and frees its memory.
 extern void FreeMemory(char* p);
@@ -90,7 +90,7 @@ extern void FreeMemory(char* p);
 // either CSV or JSON format.  Format argument can take values of 'csv',
 // 'compact', or 'pretty'. For withDetails argument 0 means false, 1 means
 // true.
-extern char* ParseAryToString(char** in, int length, char* f, int details);
+extern char* ParseAryToString(char** in, int length, char* f, int details, int cultivars);
 
 #ifdef __cplusplus
 }

data/clib/mac/libgnparser.h

@@ -19,7 +19,7 @@ typedef struct { const char *p; ptrdiff_t n; } _GoString_;
 /* Start of preamble from import "C" comments.  */
 
 
-#line 3 "main.go"
+#line 5 "main.go"
 
 	#include "stdlib.h"
 
@@ -80,20 +80,17 @@ extern "C" {
 // 'csv', 'compact', 'pretty'. If withDetails argument is 0, additional
 // parsed details are ommited, if it is 1 -- they are included.
 // true.
-
-extern char* ParseToString(char* p0, char* p1, int p2);
+extern char* ParseToString(char* name, char* f, int details, int cultivars);
 
 // FreeMemory takes a string pointer and frees its memory.
-
-extern void FreeMemory(char* p0);
+extern void FreeMemory(char* p);
 
 // ParseAryToString function takes an array of names, parsing format, and a
 // withDetails flag as 0|1 integer.  Parsed outputs are sent as a string in
 // either CSV or JSON format.  Format argument can take values of 'csv',
 // 'compact', or 'pretty'. For withDetails argument 0 means false, 1 means
 // true.
-
-extern char* ParseAryToString(char** p0, int p1, char* p2, int p3);
+extern char* ParseAryToString(char** in, int length, char* f, int details, int cultivars);
 
 #ifdef __cplusplus
 }

data/clib/win/libgnparser.h

@@ -19,7 +19,7 @@ typedef struct { const char *p; ptrdiff_t n; } _GoString_;
 /* Start of preamble from import "C" comments.  */
 
 
-#line 3 "main.go"
+#line 5 "main.go"
 
 	#include "stdlib.h"
 
@@ -80,17 +80,17 @@ extern "C" {
 // 'csv', 'compact', 'pretty'. If withDetails argument is 0, additional
 // parsed details are ommited, if it is 1 -- they are included.
 // true.
-extern char* ParseToString(char* name, char* f, int details);
+extern __declspec(dllexport) char* ParseToString(char* name, char* f, int details, int cultivars);
 
 // FreeMemory takes a string pointer and frees its memory.
-extern void FreeMemory(char* p);
+extern __declspec(dllexport) void FreeMemory(char* p);
 
 // ParseAryToString function takes an array of names, parsing format, and a
 // withDetails flag as 0|1 integer.  Parsed outputs are sent as a string in
 // either CSV or JSON format.  Format argument can take values of 'csv',
 // 'compact', or 'pretty'. For withDetails argument 0 means false, 1 means
 // true.
-extern char* ParseAryToString(char** in, int length, char* f, int details);
+extern __declspec(dllexport) char* ParseAryToString(char** in, int length, char* f, int details, int cultivars);
 
 #ifdef __cplusplus
 }

data/lib/biodiversity/parser.rb

@@ -28,47 +28,56 @@ module Biodiversity
     callback(:parser_callback, %i[string], :void)
 
     attach_function(:parse_go, :ParseToString,
-                    %i[string string int], :strptr)
+                    %i[string string int int], :strptr)
     attach_function(:parse_ary_go, :ParseAryToString,
-                    %i[pointer int string int], :strptr)
+                    %i[pointer int string int int], :strptr)
     attach_function(:free_mem, :FreeMemory, %i[pointer], :void)
 
-    def self.parse(name, simple: false, details: false)
+    def self.parse(name, simple: false, with_cultivars: false)
       format = simple ? 'csv' : 'compact'
-      with_details = details ? 1 : 0
+      with_details = simple ? 0 : 1
+      with_cultivars = with_cultivars ? 1 : 0
 
-      parsed, ptr = parse_go(name, format, with_details)
+      parsed, ptr = parse_go(name, format, with_details, with_cultivars)
       free_mem(ptr)
       output(parsed, simple)
     end
 
-    def self.parse_ary(ary, simple: false, details: false)
+    def self.parse_ary(ary, simple: false, with_cultivars: false)
       format = simple ? 'csv' : 'compact'
-      with_details = details ? 1 : 0
+      with_details = simple ? 0 : 1
+      with_cultivars = with_cultivars ? 1 : 0
 
       in_ptr = FFI::MemoryPointer.new(:pointer, ary.length)
       in_ptr.write_array_of_pointer(
         ary.map { |s| FFI::MemoryPointer.from_string(s) }
       )
 
-      parsed, ptr = parse_ary_go(in_ptr, ary.length, format, with_details)
+      parsed, ptr = parse_ary_go(in_ptr, ary.length, format,
+                                 with_details, with_cultivars)
       free_mem(ptr)
       if simple
-        CSV.new(parsed).map do |row|
+        CSV.new(parsed.force_encoding('UTF-8')).map do |row|
           csv_row(row)
         end
       else
-        JSON.parse(parsed, symbolize_names: true)
+        JSON.parse(parsed, symbolize_names: true).map do |item|
+          item[:parserVersion] = Biodiversity.gnparser_version
+          item
+        end
       end
     end
 
     def self.output(parsed, simple)
       if simple
+        parsed = parsed.force_encoding('UTF-8')
         csv = CSV.new(parsed)
         row = csv.readlines[0]
         csv_row(row)
       else
-        JSON.parse(parsed, symbolize_names: true)
+        parsed = JSON.parse(parsed, symbolize_names: true)
+        parsed[:parserVersion] = Biodiversity.gnparser_version
+        parsed
       end
     end
 
@@ -76,7 +85,7 @@ module Biodiversity
       {
         id: row[0],
         verbatim: row[1],
-        cardinality: row[2],
+        cardinality: row[2].to_i,
         canonical: {
           stem: row[3],
           simple: row[4],
@@ -84,7 +93,7 @@ module Biodiversity
         },
         authorship: row[6],
         year: row[7],
-        quality: row[8]
+        quality: row[8].to_i
       }
     end
   end

data/lib/biodiversity/version.rb

@@ -2,9 +2,14 @@
 
 # Biodiversity module provides a namespace for scientific name parser.
 module Biodiversity
-  VERSION = '5.1.0'
+  VERSION = '5.3.1'
+  GNPARSER_VERSION = 'GNparser 1.3.0+'
 
   def self.version
     VERSION
   end
+
+  def self.gnparser_version
+    GNPARSER_VERSION
+  end
 end

data/spec/lib/parser_spec.rb

@@ -4,46 +4,80 @@
 
 describe Biodiversity::Parser do
   describe('parse') do
-    it 'parses name in simple format' do
+    it 'parses name in simple form' do
       parsed = subject.parse('Homo sapiens Linn.', simple: true)
       expect(parsed[:canonical][:simple]).to eq 'Homo sapiens'
       expect(parsed[:normalized]).to be_nil
     end
 
-    it 'parsed name in full format' do
-      parsed = subject.parse('Homo sapiens  Linn.')
+    it 'parsed name in full form' do
+      parsed = subject.parse('Homo sapiens  Linn. 1758')
       expect(parsed[:canonical][:simple]).to eq 'Homo sapiens'
-      expect(parsed[:normalized]).to eq 'Homo sapiens Linn.'
+      expect(parsed[:normalized]).to eq 'Homo sapiens Linn. 1758'
+      expect(parsed[:authorship][:year]).to eq '1758'
+      expect(parsed[:words].size).to eq 4
     end
 
     it 'gets quality and year correctly in simple form' do
-      parsed = subject.parse('Homo sapiens Linn. 1758', simple: true)
+      parsed = subject.parse('Homo sapiens Foo & Bar. 1758', simple: true)
       expect(parsed[:canonical][:simple]).to eq 'Homo sapiens'
       expect(parsed[:year]).to eq '1758'
-      expect(parsed[:quality]).to eq '1'
+      expect(parsed[:authorship]).to eq 'Foo & Bar. 1758'
+      expect(parsed[:quality]).to eq 1
       expect(parsed[:normalized]).to be_nil
     end
+
+    it 'parses botanical cultivars in full form' do
+      parsed = subject.parse('Aus bus "White Russian"',
+                             simple: false, with_cultivars: true)
+      expect(parsed[:canonical][:simple]).to eq 'Aus bus ‘White Russian’'
+      expect(parsed[:quality]).to eq 1
+    end
+
+    it 'parses botanical cultivars in simple form' do
+      parsed = subject.parse('Aus bus "White Russian"',
+                             simple: true, with_cultivars: true)
+      expect(parsed[:canonical][:simple]).to eq 'Aus bus ‘White Russian’'
+      expect(parsed[:quality]).to eq 1
+      parsed = subject.parse('Aus bus "White Russian"',
+                             simple: true, with_cultivars: false)
+      expect(parsed[:canonical][:simple]).to eq 'Aus bus'
+      expect(parsed[:quality]).to eq 2
+    end
   end
 
   describe('parse_ary') do
     it 'parses names in simple format' do
       parsed = subject.parse_ary(
-        ['Homo sapiens Linn.', 'Pardosa moesta'],
-        simple: true
+        ['Homo sapiens Linn.', 'Pardosa moesta', 'Aus bus "White Russian"'],
+        simple: true, with_cultivars: true
       )
       expect(parsed[0][:canonical][:simple]).to eq 'Homo sapiens'
-      expect(parsed[1][:canonical][:simple]).to eq 'Pardosa moesta'
       expect(parsed[0][:normalized]).to be_nil
+
+      expect(parsed[1][:canonical][:simple]).to eq 'Pardosa moesta'
+      expect(parsed[2][:canonical][:simple]).to eq 'Aus bus ‘White Russian’'
+      expect(parsed[2][:quality]).to eq 1
     end
 
     it 'parsed name in full format' do
       parsed = subject.parse_ary(
-        ['Homo sapiens  Linn.', 'Tobacco Mosaic Virus']
+        [
+          'Homo sapiens  Linn.',
+          'Tobacco Mosaic Virus',
+          "Aus bus 'White Russian'"
+        ],
+        with_cultivars: true
       )
       expect(parsed[0][:canonical][:simple]).to eq 'Homo sapiens'
       expect(parsed[0][:normalized]).to eq 'Homo sapiens Linn.'
+      expect(parsed[0][:words].size).to eq 3
       expect(parsed[1][:parsed]).to be false
       expect(parsed[1][:virus]).to be true
+      expect(parsed[1][:words]).to be_nil
+      expect(parsed[2][:canonical][:simple]).to eq 'Aus bus ‘White Russian’'
+      expect(parsed[2][:quality]).to eq 1
+      expect(parsed[2][:parserVersion]).to match(/GNparser/)
     end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: biodiversity
 version: !ruby/object:Gem::Version
-  version: 5.1.0
+  version: 5.3.1
 platform: ruby
 authors:
 - Dmitry Mozzherin
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-01-19 00:00:00.000000000 Z
+date: 2021-07-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ffi
@@ -142,7 +142,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.3
+rubygems_version: 3.2.15
 signing_key:
 specification_version: 4
 summary: Parser of scientific names