text_rank 1.1.7 → 1.2.5

data/lib/text_rank/tokenizer.rb

@@ -31,7 +31,7 @@ module TextRank
       tokens = []
       text.scan(Regexp.new(regular_expressions.flatten.join('|'))) do |matches|
         m = matches.compact.first
-        tokens << m if m && m.size > 0
+        tokens << m if m&.size&.positive?
       end
       tokens
     end

data/lib/text_rank/tokenizer/money.rb

@@ -1,4 +1,3 @@
-#encoding: UTF-8
 module TextRank
   module Tokenizer
 
@@ -12,7 +11,7 @@ module TextRank
       "\u20a4", # Lira Symbol
       "\u20a7", # Peseta Sign
       "\u20ac", # Euro Symbol
-      "\u20B9", # Rupee 
+      "\u20B9", # Rupee
       "\u20a9", # Won Sign
       "\u20b4", # Hryvnia Sign
       "\u20af", # Drachma Sign
@@ -34,6 +33,8 @@ module TextRank
     # A tokenizer regex that preserves money or formatted numbers as a single token. This
     # currently supports 24 different currency symbols:
     #
+    # rubocop:disable Style/AsciiComments
+    #
     # * ¤
     # * $
     # * ¢
@@ -58,19 +59,23 @@ module TextRank
     # * ₫
     # * %
     # * ‰
+
+    # rubocop:enable Style/AsciiComments
     #
     # It also supports two alternative formats for negatives as well as optional three digit comma
     # separation and optional decimals.
     ##
-    Money = %r{
+    # rubocop:disable Naming/ConstantName
+    Money = /
       (
-        #{CURRENCY_SYMBOLS} \-? #{Number}      # $-45,231.21
+        #{CURRENCY_SYMBOLS} -? #{Number}       # $-45,231.21
         |
-        \-? #{CURRENCY_SYMBOLS} #{Number}      # -$45,231.21
+        -? #{CURRENCY_SYMBOLS} #{Number}       # -$45,231.21
         |
         \( #{CURRENCY_SYMBOLS} #{Number} \)    # ($45,231.21)
       )
-    }x
+    /x
+    # rubocop:enable Naming/ConstantName
 
   end
 end

data/lib/text_rank/tokenizer/number.rb

@@ -1,11 +1,11 @@
-#encoding: UTF-8
 module TextRank
   module Tokenizer
 
     ##
     # A tokenizer regex that preserves (optionally formatted) numbers as a single token.
     ##
-    Number = %r{
+    # rubocop:disable Naming/ConstantName
+    Number = /
       (
         [1-9]\d{3,}       # 453231162
         (?:\.\d+)?        # 453231162.17
@@ -25,7 +25,8 @@ module TextRank
 
         (?:\.\d+)         # .17
       )
-    }x
+    /x
+    # rubocop:enable Naming/ConstantName
 
   end
 end

data/lib/text_rank/tokenizer/punctuation.rb

@@ -1,11 +1,14 @@
 module TextRank
   module Tokenizer
+
     ##
     # A tokenizer regex that preserves single punctuation symbols as a token. Use
     # this if one or more of your TokenFilter classes need punctuation in order to
     # make decisions.
     ##
-    Punctuation = %r{([\p{Punct}])}
+    # rubocop:disable Naming/ConstantName
+    Punctuation = /(\p{Punct})/
+    # rubocop:enable Naming/ConstantName
 
   end
 end

data/lib/text_rank/tokenizer/url.rb

@@ -1,8 +1,10 @@
 module TextRank
   module Tokenizer
+
     ##
     # A tokenizer regex that preserves entire URL's as a token (rather than split them up)
     ##
+    # rubocop:disable Naming/ConstantName
     Url = %r{
       (
         (?:[\w-]+://?|www[.])
@@ -16,6 +18,7 @@ module TextRank
         )
       )
     }xi
+    # rubocop:enable Naming/ConstantName
 
   end
 end

data/lib/text_rank/tokenizer/whitespace.rb

@@ -1,11 +1,14 @@
 module TextRank
   module Tokenizer
+
     ##
     # A tokenizer regex that preserves single whitespace characters as a token. Use
     # this if one or more of your TokenFilter classes need whitespace in order to
     # make decisions.
     ##
-    Whitespace = %r{\s}
+    # rubocop:disable Naming/ConstantName
+    Whitespace = /\s/
+    # rubocop:enable Naming/ConstantName
 
   end
 end

data/lib/text_rank/tokenizer/word.rb

@@ -1,14 +1,17 @@
 module TextRank
   module Tokenizer
+
     ##
     # A tokenizer regex that preserves a non-space, non-punctuation "word".  It does
     # allow hyphens and numerals, but the first character must be an A-Z character.
     ##
-    Word = %r{
+    # rubocop:disable Naming/ConstantName
+    Word = /
       (
         [a-z][a-z0-9-]*
       )
-    }xi
+    /xi
+    # rubocop:enable Naming/ConstantName
 
   end
 end

data/lib/text_rank/version.rb

@@ -1,4 +1,6 @@
 module TextRank
+
   # Current gem version
-  VERSION = '1.1.7'
+  VERSION = '1.2.5'
+
 end

data/text_rank.gemspec

@@ -1,4 +1,3 @@
-# coding: utf-8
 lib = File.expand_path('../lib', __FILE__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require 'text_rank/version'
@@ -9,8 +8,8 @@ Gem::Specification.new do |spec|
   spec.authors       = ['David McCullars']
   spec.email         = ['david.mccullars@gmail.com']
 
-  spec.summary       = %q{Implementation of TextRank solution to ranked keyword extraction}
-  spec.description   = %q{Implementation of TextRank solution to ranked keyword extraction.  See https://web.eecs.umich.edu/~mihalcea/papers/mihalcea.emnlp04.pdf}
+  spec.summary       = 'Implementation of TextRank solution to ranked keyword extraction'
+  spec.description   = 'Implementation of TextRank solution to ranked keyword extraction.  See https://web.eecs.umich.edu/~mihalcea/papers/mihalcea.emnlp04.pdf'
   spec.homepage      = 'https://github.com/david-mccullars/text_rank'
   spec.license       = 'MIT'
 
@@ -19,12 +18,13 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ['lib']
 
-  spec.add_development_dependency 'bundler',    '~> 1.11'
-  spec.add_development_dependency 'rake',       '~> 10.0'
-  spec.add_development_dependency 'rspec',      '~> 3.0'
-  spec.add_development_dependency 'simplecov',  '~> 0.11'
-  spec.add_development_dependency 'codeclimate-test-reporter'
+  spec.add_development_dependency 'bundler'
+  spec.add_development_dependency 'rake'
+  spec.add_development_dependency 'rspec'
+  spec.add_development_dependency 'rubocop'
+  spec.add_development_dependency 'simplecov', '~> 0.17.0' # 0.18 not supported by code climate
+  spec.add_development_dependency 'yard'
 
-  spec.add_development_dependency 'engtagger',  '~> 0.2.0' # Optional runtime dependency but needed for specs
-  spec.add_development_dependency 'nokogiri',   '~> 1.0'   # Optional runtime dependency but needed for specs
+  spec.add_development_dependency 'engtagger' # Optional runtime dependency but needed for specs
+  spec.add_development_dependency 'nokogiri'  # Optional runtime dependency but needed for specs
 end

metadata

@@ -1,73 +1,87 @@
 --- !ruby/object:Gem::Specification
 name: text_rank
 version: !ruby/object:Gem::Version
-  version: 1.1.7
+  version: 1.2.5
 platform: ruby
 authors:
 - David McCullars
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2016-07-05 00:00:00.000000000 Z
+date: 2021-01-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.11'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.11'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: simplecov
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.11'
+        version: 0.17.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.11'
+        version: 0.17.0
 - !ruby/object:Gem::Dependency
-  name: codeclimate-test-reporter
+  name: yard
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -84,30 +98,30 @@ dependencies:
   name: engtagger
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.2.0
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.2.0
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '0'
 description: Implementation of TextRank solution to ranked keyword extraction.  See
   https://web.eecs.umich.edu/~mihalcea/papers/mihalcea.emnlp04.pdf
 email:
@@ -124,7 +138,7 @@ files:
 - ".travis.yml"
 - CODE_OF_CONDUCT.md
 - Gemfile
-- LICENSE.txt
+- LICENSE
 - README.md
 - Rakefile
 - bin/console
@@ -141,7 +155,9 @@ files:
 - lib/text_rank/char_filter/strip_html.rb
 - lib/text_rank/char_filter/strip_possessive.rb
 - lib/text_rank/char_filter/undo_contractions.rb
+- lib/text_rank/char_filter/undo_contractions.yml
 - lib/text_rank/fingerprint.rb
+- lib/text_rank/fingerprint_overlap.rb
 - lib/text_rank/graph_strategy.rb
 - lib/text_rank/graph_strategy/coocurrence.rb
 - lib/text_rank/keyword_extractor.rb
@@ -154,6 +170,7 @@ files:
 - lib/text_rank/token_filter/min_length.rb
 - lib/text_rank/token_filter/part_of_speech.rb
 - lib/text_rank/token_filter/stopwords.rb
+- lib/text_rank/token_filter/stopwords.yml
 - lib/text_rank/tokenizer.rb
 - lib/text_rank/tokenizer/money.rb
 - lib/text_rank/tokenizer/number.rb
@@ -167,7 +184,7 @@ homepage: https://github.com/david-mccullars/text_rank
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -182,10 +199,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.5.1
-signing_key: 
+rubyforge_project:
+rubygems_version: 2.7.6
+signing_key:
 specification_version: 4
 summary: Implementation of TextRank solution to ranked keyword extraction
 test_files: []
-has_rdoc: