gnfinder 0.15.4 → 0.17.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b44ef459356568026904e4b42664ab39b3b7cfef043c33e62d95c47f7081ec7b
-  data.tar.gz: 5da9930ce9d03c4184b51055a6a17d5d63510246460a742b768b56d940f6f536
+  metadata.gz: 184b18622694218dde5a93d5aeaec67b4653761ab4be512e79df7be1d8f1b67d
+  data.tar.gz: 2a3be26a7008ee7e5e4834cb62146d95c2d15cf069d2a9df50d327da4813f8fd
 SHA512:
-  metadata.gz: 2d37282d56d4d41d913f74765d86b6ea38ccb8ececcd957a672bf1296fb3dfb5fb50a373fb64f4e0c981cfd658eb884a4eb6179434e82c7b619cd54c8dcf21f0
-  data.tar.gz: 27ac046cd874aa9a099d44290d818d61d85282e9bd10f3fb384c37293ace1dd4f50b47f2693ee2220b46c4980535d7a8936b29c01c3ca597cf577ad3ffd0f91a
+  metadata.gz: d3b61878fa159a360ef5825bb807084ffbc4b0fc1b3e1cc6af9b82012ff487951df0d017e9dbf3b560b08dc281c354b134d6c3a3201912d158cdff2910b80d5c
+  data.tar.gz: 25b30a86f4b4c54ece188ffe41db5c35c5467ebde0699b74f5b3205170e4e84924909990733e18a1e331d1b1c26b1c5a2de2ea3f1416dbff8a2dfb61efb9edea

data/.github/workflows/ruby.yml

@@ -0,0 +1,41 @@
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+# This workflow will download a prebuilt Ruby version, install dependencies and run tests with Rake
+# For more information see: https://github.com/marketplace/actions/setup-ruby-jruby-and-truffleruby
+
+name: Ruby
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+jobs:
+  test:
+
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        ruby: [2.6, 2.7, 3.0]
+
+    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
+      with:
+        ruby-version: ${{ matrix.ruby }}
+    - name: Install dependencies
+      run: bundle install
+    - name: Show environment
+      run: gem environment
+    - name: Run tests
+      run: bundle exec rake
+    - name: Checking install works
+      run: rake install

data/.rubocop.yml

@@ -1,6 +1,6 @@
 AllCops:
   NewCops: disable
-  TargetRubyVersion: 3.0
+  TargetRubyVersion: 2.6
   Exclude:
     - 'lib/protob_pb.rb'
     - 'lib/protob_services_pb.rb'

data/CHANGELOG.md

@@ -2,6 +2,14 @@
 
 ## Unreleased
 
+## [v0.17.0]
+
+- Update to gnfinder v0.17.0
+
+## [v0.15.5]
+
+- Add [#16]: Search names using URL.
+
 ## [v0.15.4]
 
 - Add [#14]: Compatibility with gnfider v0.15.4, switching to REST API.

data/README.md

@@ -1,43 +1,49 @@
 # gnfinder
 
-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)
+Ruby gem to access functionality of [GNfinder] project written in Go. This gem
+allows to perform fast and accurate scientific name finding in texts,
+web-pages, as well as a large variety of documents. Document files can be
+accessed either locally or via a URL.
+
+
+<!-- vim-markdown-toc GFM -->
+
+* [Requirements](#requirements)
+* [Installation](#installation)
+* [Usage](#usage)
+  * [Finding names in a text using default settings](#finding-names-in-a-text-using-default-settings)
+  * [Finding names by a URL](#finding-names-by-a-url)
+  * [Finding names in a file](#finding-names-in-a-file)
+  * [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)
+
+<!-- vim-markdown-toc -->
 
 ## Requirements
 
-This gem uses gRPC to access a running [gnfinder] server. You can find how
-to run it in [gnfinder] README file.
+This gem uses REST API to access a running [GNfinder] server. You can find how
+to run it in [GNfinder] README file. By default it uses
+`https://gnfinder.globalnames.org/api/v0`
 
 ## Installation
 
-To use the gem from Ruby proect install it using Gemfile, or manually:
-
 ```bash
 gem install gnfinder
 ```
 
 ## Usage
 
-The purpose of this gem is to access [gnfinder] functionality out of Ruby
+The purpose of this gem is to access [GNfinder] functionality from Ruby
 applications. If you need to find names using other languages, use the
 [source code][client] of this gem for reference. For other usages read
-the original Go-lang [gnfinder] README file.
+the original Go-lang [GNfinder] README file.
 
-First you need to create a instance of a `gnfinder` client
+First you need to create an instance of a `gnfinder` client
 
 ```ruby
 require 'gnfinder'
@@ -45,25 +51,24 @@ require 'gnfinder'
 gf = Gnfinder::Client.new
 ```
 
-By default the client will try to connect to `localhost:8778`. If you
-have another location for the server use:
-
-
+By default the client will try to connect to
+`https://gnfinder.globalnames.org/api/v0`. If you have another location for the
+server use:
 
 ```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)
+gf = Gnfinder::Client.new(host = 'finder.example.org', port = 80)
 
-# localhost, different port
+# localhost, port 8000
 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]
+You can find format of returning result in [GNfinder API docs]
 
 ```ruby
 txt = File.read('utf8-text-with-names.txt')
@@ -73,7 +78,39 @@ puts res.names[0].value
 puts res.names[0].odds
 ```
 
-Returned result will have the following methods for each name:
+### Finding names by a URL
+
+If you need to find names in an HTML page, or a PDF document available on
+Internet, use `find_url` method.
+
+```ruby
+url = 'https://en.wikipedia.org/wiki/Monochamus_galloprovincialis'
+res = gf.find_url(url)
+puts res.names[0].value
+puts res.names[0].odds
+```
+
+### Finding names in a file
+
+Many different file types are supported (PDF, JPB, TIFF, MS Word, MS Excel
+etc).
+
+```ruby
+path = "/path/to/file.pdf"
+res = gf.find_file(path)
+puts res.names[0].value
+```
+
+Support of file-uploading uses 'multipart/form' approach. Here is an
+illustration for `curl`:
+
+```bash
+curl -v -F sources[]=1 -F sources[]=12 -F file=@file.pdf \
+    https://finder.globalnames.org/api/v0/find
+```
+
+Returned result is quite detailed and contains many accessor methods, for
+example:
 
   * value: name-string cleaned up for verification.
   * verbatim: name-string as it was found in the text.
@@ -173,21 +210,6 @@ res = gf.find_names(txt, language: 'eng', sources: [1, 4, 179])
 
 ## Development
 
-This gem uses gRPC to access [gnfinder] server. gRPC in turn depends on a
-protobuf library. If you need to compile Ruby programs with protobuf you need
-to install [Go] language and download [gnfinder] project.
-
-```bash
-go get github.com/gnames/gnfinder
-```
-Then you need to run bundle from the root of the project and generate
-grpc files:
-
-```bash
-bundle
-rake grpc
-```
-
 If you get an error, you might need to set a ``GOPATH`` environment variable.
 
 After starting the server with default host and port (localhost:8778) you will
@@ -208,10 +230,10 @@ To run tests without rubocop
 bundle exec rspec
 ```
 
-[gnfinder]: https://github.com/gnames/gnfinder
+[GNfinder]: https://github.com/gnames/gnfinder
 [gnfinder recent release]: https://github.com/gnames/gnfinder/releases
 [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
+[GNfinder API docs]: https://apidoc.globalnames.org/gnfinder

data/Rakefile

@@ -24,16 +24,7 @@ RSpec::Core::RakeTask.new(:rcov) do |spec|
   spec.rcov = true
 end
 
-task :grpc do
-  cmd = 'grpc_tools_ruby_protoc ' \
-    '-I $GOPATH/src/github.com/gnames/gnfinder/protob ' \
-        '--ruby_out=lib --grpc_out=lib ' \
-        '$GOPATH/src/github.com/gnames/gnfinder/protob/protob.proto'
-  puts cmd
-  `#{cmd}`
-end
-
 require 'rubocop/rake_task'
 RuboCop::RakeTask.new
 
-task default: %i[rubocop grpc spec]
+task default: %i[rubocop spec]

data/gnfinder.gemspec

@@ -20,12 +20,14 @@ Gem::Specification.new do |gem|
                       .reject { |f| f.match(%r{^(test|spec|features)/}) }
 
   gem.require_paths = ['lib']
-  gem.required_ruby_version = '~> 3.0'
+  gem.required_ruby_version = '>= 2.6', '< 4'
   gem.add_dependency 'rest-client', '~> 2.1'
   gem.add_development_dependency 'bundler', '~> 2.2'
   gem.add_development_dependency 'byebug', '~> 11.1'
   gem.add_development_dependency 'rake', '~> 13.0'
   gem.add_development_dependency 'rspec', '~> 3.10'
-  gem.add_development_dependency 'rubocop', '~> 1.20'
+  gem.add_development_dependency 'rubocop', '~> 1.21'
+  gem.add_development_dependency 'rubocop-rake', '~> 0.6.0'
+  gem.add_development_dependency 'rubocop-rspec', '~> 2.4'
   gem.add_development_dependency 'solargraph', '~> 0.43'
 end

data/lib/gnfinder/client.rb

@@ -4,7 +4,7 @@ module Gnfinder
   # Gnfinder::Client connects to gnfinder server
   class Client
     def initialize(host = 'https://gnfinder.globalnames.org', port = '')
-      api_path = '/api/v1'
+      api_path = '/api/v0'
       url = host + api_path
       url = "#{host}:#{port}#{api_path}" if port.to_s != ''
       @site = RestClient::Resource.new(url, read_timeout: 60)
@@ -21,41 +21,63 @@ module Gnfinder
       @site['/ping'].get.body
     end
 
-    # rubocop:disable all
+    def find_file(path, opts = {})
+      params = {}
+      update_params(params, opts)
+      file = File.new(path, 'rb')
+      params = params.merge(file: file)
+      resp = @site['find'].post(params)
+      prepare_result(resp)
+    end
+
+    def find_url(url, opts = {})
+      return to_open_struct({ "names": [] }) if url.to_s.strip == ''
+
+      params = { url: url }
+      find(params, opts)
+    end
+
     def find_names(text, opts = {})
-      if text.to_s.strip == ''
-        return to_open_struct({ "names": [] })
-      end
+      return to_open_struct({ "names": [] }) if text.to_s.strip == ''
 
       params = { text: text }
+      find(params, opts)
+    end
+
+    private
+
+    # rubocop:disable all
+    def find(params, opts = {})
+      update_params(params, opts)
+
+      resp = @site['find'].post params.to_json, {content_type: :json, accept: :json}
+      prepare_result(resp)
+    end
+    # rubocop:enable all
+
+    def prepare_result(response)
+      output = JSON.parse(response.body)
+      res = output['metadata']
+      res['names'] = output['names'] || []
+      res = res.deep_transform_keys(&:underscore)
+      res['names'] = [] if res['names'].nil?
+      to_open_struct(res)
+    end
+
+    # rubocop:disable all
+    def update_params(params, opts)
       params[:noBayes] = true if opts[:no_bayes]
       params[:oddsDetails] = true if opts[:odds_details]
       params[:language] = opts[:language] if opts[:language].to_s.strip != ''
 
-      if opts[:words_around] && opts[:words_around] > 0
-        params[:wordsAround] = opts[:words_around]
-      end
+      params[:wordsAround] = opts[:words_around] if opts[:words_around] && opts[:words_around].positive?
 
       params[:verification] = true if opts[:verification]
 
-      if opts[:sources] && !opts[:sources].empty?
-        params[:sources] = opts[:sources]
-      end
-
-      res = @site['find'].post params.to_json, {content_type: :json, accept: :json}
-      output = JSON.parse(res.body)
-      res = output["metadata"]
-      res["names"] = output["names"] || []
-      res = res.deep_transform_keys(&:underscore)
-      if res["names"].nil?
-        res["names"] = []
-      end
-      to_open_struct(res)
+      params[:sources] = opts[:sources] if opts[:sources] && !opts[:sources].empty?
     end
     # rubocop:enable all
 
-    private
-
     def to_open_struct(obj)
       case obj
       when Hash

data/lib/gnfinder/version.rb

@@ -3,7 +3,7 @@
 # Gnfinder is a namespace module for gndinfer gem.
 module Gnfinder
   # Version corresponds to the minimal supported version of Go gnfinder
-  VERSION = '0.15.4'
+  VERSION = '0.17.0'
 
   def self.version
     VERSION

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: gnfinder
 version: !ruby/object:Gem::Version
-  version: 0.15.4
+  version: 0.17.0
 platform: ruby
 authors:
 - Dmitry Mozzherin
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-09-16 00:00:00.000000000 Z
+date: 2022-01-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rest-client
@@ -86,14 +86,42 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.20'
+        version: '1.21'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.20'
+        version: '1.21'
+- !ruby/object:Gem::Dependency
+  name: rubocop-rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.6.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.6.0
+- !ruby/object:Gem::Dependency
+  name: rubocop-rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.4'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.4'
 - !ruby/object:Gem::Dependency
   name: solargraph
   requirement: !ruby/object:Gem::Requirement
@@ -116,6 +144,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/workflows/ruby.yml"
 - ".gitignore"
 - ".rspec"
 - ".rubocop.yml"
@@ -139,9 +168,12 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - "~>"
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '2.6'
+  - - "<"
     - !ruby/object:Gem::Version
-      version: '3.0'
+      version: '4'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="