gnfinder 0.2.2 → 0.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 92d97dc85a5d774323c7e995573c47bf004d606ad61e8b15bb81c0ce492b419e
-  data.tar.gz: 381a9dc59941089bd0620ce24456a4e39944ff7a7decef4ecadd13e5ad918ff4
+  metadata.gz: dffcaa8904b1b9a47761b66aff325c86615aedec1600b9abe13194035c4aa061
+  data.tar.gz: f33a382799901181d3092f2c05585318accd1e5baebb6bb053d6ac7bc015e7d6
 SHA512:
-  metadata.gz: 2851e18f695cffaed64c4da96349e00351da2918160ec16c5dada98a704d4156f9ef694f059a13a5072d7badb05ec30ae373468ee61aa7f0cab9ea81a7901df2
-  data.tar.gz: 72ee313d4327eb6e2f3521438bcc788a24ee86ed412114118e61c3628bedec83cfd089dbb1ee478853e92178ca56572480d264cceba0fad1a096bd63f17f5b22
+  metadata.gz: 7a0358fac8b9f05532be3f5434c07a8fd5bd242d35545f45faa4798d8cc0eb540b21a7e11c292c624cbc6608c633106812fcc1ab219bcd2ce9a72b5e9d17fa66
+  data.tar.gz: 5dfc5b032530c7fea01672bdf3a0a5ce595832110b665a680ca575f1916cd17e84b33991da9462f6c35927513cf6cd71e7df3dd87bd65027480129489e793f1a

data/.rubocop.yml

@@ -1,5 +1,5 @@
 AllCops:
-  TargetRubyVersion: 2.5
+  TargetRubyVersion: 2.6
   Exclude:
     - 'lib/protob_pb.rb'
     - 'lib/protob_services_pb.rb'

data/README.md

@@ -4,6 +4,18 @@ Ruby gem to access functionality of [gnfinder] project written in Go. This gem
 allows to perform fast and accurate scientific name finding in UTF-8 encoded
 plain texts for Ruby-based projects.
 
+- [gnfinder](#gnfinder)
+  - [Requirements](#requirements)
+  - [Installation](#installation)
+  - [Usage](#usage)
+    - [Finding names in a text using default settings](#finding-names-in-a-text-using-default-settings)
+    - [Optionally disable Bayes search](#optionally-disable-bayes-search)
+    - [Set a language for the text](#set-a-language-for-the-text)
+  - [Set automatic detection of text's language](#set-automatic-detection-of-texts-language)
+    - [Set verification option](#set-verification-option)
+    - [Set preferred data-sources list](#set-preferred-data-sources-list)
+    - [Combination of parameters.](#combination-of-parameters)
+  - [Development](#development)
 
 ## Requirements
 
@@ -28,7 +40,7 @@ the original Go-lang [gnfinder] README file.
 First you need to create a instance of a `gnfinder` client
 
 ```ruby
-import 'gnfinder'
+require 'gnfinder'
 
 gf = Gnfinder::Client.new
 ```
@@ -36,60 +48,78 @@ gf = Gnfinder::Client.new
 By default the client will try to connect to `localhost:8778`. If you
 have another location for the server use:
 
-```
-import 'gnfinder'
-gf = Gnfinder.new(host: 123.123.123.123, port: 8000)
+
+
+```ruby
+require 'gnfinder'
+
+# you can use global public gnfinder server
+# located at finder-rpc.globalnames.org
+gf = Gnfinder::Client.new(host = 'finder-rpc.globalnames.org', port = 80)
+
+# localhost, different port
+gf = Gnfinder::Client.new(host = '0.0.0.0', port = 8000)
 ```
 
 ### Finding names in a text using default settings
 
+You can find format of returning result in [proto file] or in [tests]
+
 ```ruby
 txt = File.read('utf8-text-with-names.txt')
 
-names = gf.find_names(txt)
-puts names[0].value
-puts names[0].odds
+res = gf.find_names(txt)
+puts res.names[0].value
+puts res.names[0].odds
 ```
 
 Returned result will have the following methods for each name:
 
-  * value: mame-string cleaned up for verification.
+  * value: name-string cleaned up for verification.
   * verbatim: name-string as it was found in the text.
   * odds: Bayes' odds value. For example odds 0.1 would mean that according to
     the algorithm there is 1 chance out of 10 that the name-string is
     a scientific name. This field will be empty if Bayes algorithms did not run.
 
-### Always enable Bayes search
+### Optionally disable Bayes search
 
-For languages that are not supported by [gnfinder] only heuristic algorithms
-are used by default, because some languages that are close to Latin (Italian,
-French, Portugese) would generate too many false positives. However you can
-override this default setting by running:
+Some languages that are close to Latin (Italian, French, Portugese) would
+generate too many false positives. To decrease amount of false positives you
+can disable Bayes algorithm by running:
 
 ```ruby
-names = gf.find_names(txt, with_bayes: true)
+names = gf.find_names(txt, no_bayes: true).names
 ```
 
 ### Set a language for the text
 
-Sometimes gnfinder cannot determine the language of a text correctly. For
-example it happens when the text mostly consists of scientific names, or has
-large citations or list of references in a different language. It is possible
-to set a language for a text by hand. For supported languages
-(English and German) it will enable Bayes algorithm. For other languages
-this setting will be ignored.
+It is possible to supply the prevalent language to set a language for a text
+by hand. That might Bayes algorithms work better
 
 List of supported languages will increase with time.
 
 ```ruby
-names = gf.find_names(txt, language: 'eng')
-names = gf.find_names(txt, language: 'deu')
-
-# setting is ignored, only known by gnfinder
-# 3-character notations iso-639-2 code are supported
-names = gf.find_names(txt, language: 'english')
-names = gf.find_names(txt, language: 'rus')
+res = gf.find_names(txt, language: 'eng')
+puts res.language
+res = gf.find_names(txt, language: 'deu')
+puts res.language
+
+# Setting is ignored if language string is not known by gnfinder.
+# Only 3-character notations iso-639-2 code are supported
+res = gf.find_names(txt, language: 'rus')
+puts res.language
 ```
+## Set automatic detection of text's language
+
+To enable automatic detection of prevalent language of a text use:
+
+res = gf.find_names(txt, detect_language: true)
+puts res.language
+puts res.detect_language
+puts res.language_detected
+
+If detected language is not yet supported by Bayes algorithm, default
+language (English) will be used.
 
 ### Set verification option
 
@@ -113,7 +143,7 @@ return the following information:
   * path: the classification path of a matched name (if available)
 
 ```ruby
-names = gf.find_names(txt, with_verification: true)
+res = gf.find_names(txt, verification: true)
 ```
 
 ### Set preferred data-sources list
@@ -124,7 +154,7 @@ data-source (data-sources). There is a parameter that takes IDs from the
 results will be returned back.
 
 ```ruby
-names = gf.find_names(txt, with_verification: true, sources: [1, 4, 179])
+res = gf.find_names(txt, verification: true, sources: [1, 4, 179])
 ```
 ### Combination of parameters.
 
@@ -134,11 +164,11 @@ a particular context. It is silently ignored.
 ```ruby
 # Runs Bayes' algorithms using English training set, runs verification and
 # returns matched results for 3 data-sources if they are available.
-names = gf.find_names(txt, language: eng, with_verification: true,
+res = gf.find_names(txt, language: eng, verification: true,
                            sources: [1, 4, 179])
 
 # Ignores `sources:` settings, because `with_verification` is not set to `true`
-names = gf.find_names(txt, language: eng, sources: [1, 4, 179])
+res = gf.find_names(txt, language: eng, sources: [1, 4, 179])
 ```
 
 ## Development
@@ -183,3 +213,5 @@ bundle exec rspec
 [Go]: https://golang.org/doc/install
 [client]: https://github.com/GlobalNamesArchitecture/gnfinder/blob/master/lib/gnfinder/client.rb
 [data-source list]: http://index.globalnames.org/datasource
+[proto file]: https://github.com/GlobalNamesArchitecture/gnfinder/blob/master/lib/protob_pb.rb
+[tests]: https://github.com/GlobalNamesArchitecture/gnfinder/blob/master/spec/lib/client_spec.rb

data/gnfinder.gemspec

@@ -20,7 +20,7 @@ Gem::Specification.new do |gem|
                       .reject { |f| f.match(%r{^(test|spec|features)/}) }
 
   gem.require_paths = ['lib']
-  gem.required_ruby_version = '~> 2.5'
+  gem.required_ruby_version = '~> 2.6'
   gem.add_development_dependency 'bundler', '~> 2.0'
   gem.add_development_dependency 'byebug', '~> 10.0'
   gem.add_development_dependency 'grpc', '~> 1.15'

data/lib/gnfinder/client.rb

@@ -1,31 +1,45 @@
 # frozen_string_literal: true
 
 module Gnfinder
+  GNFINDER_MIN_VERSION = 'v0.9.0'
+
   # Gnfinder::Client connects to gnfinder server
   class Client
     def initialize(host = '0.0.0.0', port = '8778')
       @stub = Protob::GNFinder::Stub.new("#{host}:#{port}",
                                          :this_channel_is_insecure)
+      return if gnfinder_version.version >= GNFINDER_MIN_VERSION
+
+      raise 'gRPC server of gnfinder should be at least ' \
+            ' #{GNFINDER_MIN_VERSION}.\n Download latest version from ' \
+            'https://github.com/gnames/gnfinder/releases/latest.'
+    end
+
+    def gnfinder_version
+      @stub.ver(Protob::Void.new)
     end
 
     def ping
       @stub.ping(Protob::Void.new).value
     end
 
-    # rubocop:disable Metrics/AbcSize, Metrics/CyclomaticComplexity
+    # rubocop:disable all
     def find_names(text, opts = {})
       raise 'Text cannot be empty' if text.to_s.strip == ''
 
       params = { text: text }
-      params[:with_bayes] = true if opts[:with_bayes]
+      params[:no_bayes] = true if opts[:no_bayes]
       params[:language] = opts[:language] if opts[:language].to_s.strip != ''
-      params[:with_verification] = true if opts[:with_verification]
+      if opts[:detect_language]
+        params[:detect_language] = opts[:detect_language]
+      end
+      params[:verification] = true if opts[:verification]
       if opts[:sources] && !opts[:sources].empty?
         params[:sources] = opts[:sources]
       end
 
-      @stub.find_names(Protob::Params.new(params)).names
+      @stub.find_names(Protob::Params.new(params))
     end
-    # rubocop:enable Metrics/AbcSize, Metrics/CyclomaticComplexity
+    # rubocop:enable all
   end
 end

data/lib/gnfinder/version.rb

@@ -2,7 +2,8 @@
 
 # Gnfinder is a namespace module for gndinfer gem.
 module Gnfinder
-  VERSION = '0.2.2'
+  # Version corresponds to the minimal supported version of Go gnfinder
+  VERSION = '0.9.0'
 
   def self.version
     VERSION

data/lib/protob_pb.rb

@@ -4,72 +4,83 @@
 require 'google/protobuf'
 
 Google::Protobuf::DescriptorPool.generated_pool.build do
-  add_message "protob.Pong" do
-    optional :value, :string, 1
-  end
-  add_message "protob.Void" do
-  end
-  add_message "protob.Params" do
-    optional :text, :string, 1
-    optional :with_bayes, :bool, 3
-    optional :language, :string, 4
-    optional :with_verification, :bool, 5
-    repeated :sources, :int32, 6
-  end
-  add_message "protob.NameStrings" do
-    optional :date, :string, 1
-    optional :language, :string, 2
-    optional :total_tokens, :int32, 3
-    optional :total_candidates, :int32, 4
-    optional :total_names, :int32, 5
-    repeated :names, :message, 6, "protob.NameString"
-  end
-  add_message "protob.NameString" do
-    optional :type, :string, 1
-    optional :verbatim, :string, 2
-    optional :name, :string, 3
-    optional :odds, :float, 4
-    optional :offset_start, :int32, 5
-    optional :offset_end, :int32, 6
-    optional :verification, :message, 7, "protob.Verification"
-  end
-  add_message "protob.Verification" do
-    optional :best_result, :message, 1, "protob.ResultData"
-    repeated :preferred_results, :message, 2, "protob.ResultData"
-    optional :data_sources_num, :int32, 3
-    optional :data_source_quality, :string, 4
-    optional :retries, :int32, 5
-    optional :error, :string, 6
-  end
-  add_message "protob.ResultData" do
-    optional :data_source_id, :int32, 1
-    optional :data_source_title, :string, 2
-    optional :taxon_id, :string, 3
-    optional :matched_name, :string, 4
-    optional :matched_canonical, :string, 5
-    optional :current_name, :string, 6
-    optional :synonym, :bool, 7
-    optional :classification_path, :string, 8
-    optional :classification_rank, :string, 9
-    optional :classification_ids, :string, 10
-    optional :edit_distance, :int32, 11
-    optional :stem_edit_distance, :int32, 12
-    optional :match_type, :enum, 13, "protob.MatchType"
-  end
-  add_enum "protob.MatchType" do
-    value :NONE, 0
-    value :EXACT, 1
-    value :FUZZY, 2
-    value :PARTIAL_EXACT, 3
-    value :PARTIAL_FUZZY, 4
+  add_file("protob.proto", :syntax => :proto3) do
+    add_message "protob.Void" do
+    end
+    add_message "protob.Pong" do
+      optional :value, :string, 1
+    end
+    add_message "protob.Version" do
+      optional :version, :string, 1
+      optional :build, :string, 2
+    end
+    add_message "protob.Params" do
+      optional :text, :string, 1
+      optional :no_bayes, :bool, 3
+      optional :language, :string, 4
+      optional :detect_language, :bool, 5
+      optional :verification, :bool, 6
+      repeated :sources, :int32, 7
+    end
+    add_message "protob.Output" do
+      optional :date, :string, 1
+      optional :finder_version, :string, 2
+      optional :language, :string, 3
+      optional :language_detected, :string, 4
+      optional :detect_language, :bool, 5
+      optional :total_tokens, :int32, 6
+      optional :total_candidates, :int32, 7
+      optional :total_names, :int32, 8
+      repeated :names, :message, 9, "protob.NameString"
+    end
+    add_message "protob.NameString" do
+      optional :type, :string, 1
+      optional :verbatim, :string, 2
+      optional :name, :string, 3
+      optional :odds, :float, 4
+      optional :offset_start, :int32, 5
+      optional :offset_end, :int32, 6
+      optional :verification, :message, 7, "protob.Verification"
+    end
+    add_message "protob.Verification" do
+      optional :best_result, :message, 1, "protob.ResultData"
+      repeated :preferred_results, :message, 2, "protob.ResultData"
+      optional :data_sources_num, :int32, 3
+      optional :data_source_quality, :string, 4
+      optional :retries, :int32, 5
+      optional :error, :string, 6
+    end
+    add_message "protob.ResultData" do
+      optional :data_source_id, :int32, 1
+      optional :data_source_title, :string, 2
+      optional :taxon_id, :string, 3
+      optional :matched_name, :string, 4
+      optional :matched_canonical, :string, 5
+      optional :current_name, :string, 6
+      optional :synonym, :bool, 7
+      optional :classification_path, :string, 8
+      optional :classification_rank, :string, 9
+      optional :classification_ids, :string, 10
+      optional :edit_distance, :int32, 11
+      optional :stem_edit_distance, :int32, 12
+      optional :match_type, :enum, 13, "protob.MatchType"
+    end
+    add_enum "protob.MatchType" do
+      value :NONE, 0
+      value :EXACT, 1
+      value :FUZZY, 2
+      value :PARTIAL_EXACT, 3
+      value :PARTIAL_FUZZY, 4
+    end
   end
 end
 
 module Protob
-  Pong = Google::Protobuf::DescriptorPool.generated_pool.lookup("protob.Pong").msgclass
   Void = Google::Protobuf::DescriptorPool.generated_pool.lookup("protob.Void").msgclass
+  Pong = Google::Protobuf::DescriptorPool.generated_pool.lookup("protob.Pong").msgclass
+  Version = Google::Protobuf::DescriptorPool.generated_pool.lookup("protob.Version").msgclass
   Params = Google::Protobuf::DescriptorPool.generated_pool.lookup("protob.Params").msgclass
-  NameStrings = Google::Protobuf::DescriptorPool.generated_pool.lookup("protob.NameStrings").msgclass
+  Output = Google::Protobuf::DescriptorPool.generated_pool.lookup("protob.Output").msgclass
   NameString = Google::Protobuf::DescriptorPool.generated_pool.lookup("protob.NameString").msgclass
   Verification = Google::Protobuf::DescriptorPool.generated_pool.lookup("protob.Verification").msgclass
   ResultData = Google::Protobuf::DescriptorPool.generated_pool.lookup("protob.ResultData").msgclass

data/lib/protob_services_pb.rb

@@ -15,7 +15,8 @@ module Protob
       self.service_name = 'protob.GNFinder'
 
       rpc :Ping, Void, Pong
-      rpc :FindNames, Params, NameStrings
+      rpc :Ver, Void, Version
+      rpc :FindNames, Params, Output
     end
 
     Stub = Service.rpc_stub_class

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: gnfinder
 version: !ruby/object:Gem::Version
-  version: 0.2.2
+  version: 0.9.0
 platform: ruby
 authors:
 - Dmitry Mozzherin
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-04-23 00:00:00.000000000 Z
+date: 2019-10-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -142,15 +142,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - "~>"
     - !ruby/object:Gem::Version
-      version: '2.5'
+      version: '2.6'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: Scientific names finder