text_rank 1.2.3 → 1.3.0

data/lib/text_rank/token_filter/stopwords.yml

@@ -0,0 +1,317 @@
+- a
+- about
+- above
+- across
+- after
+- afterwards
+- again
+- against
+- all
+- almost
+- alone
+- along
+- already
+- also
+- although
+- always
+- am
+- among
+- amongst
+- amoungst
+- amount
+- an
+- and
+- another
+- any
+- anyhow
+- anyone
+- anything
+- anyway
+- anywhere
+- are
+- around
+- as
+- at
+- back
+- be
+- became
+- because
+- become
+- becomes
+- becoming
+- been
+- before
+- beforehand
+- behind
+- being
+- below
+- beside
+- besides
+- between
+- beyond
+- bill
+- both
+- bottom
+- but
+- by
+- call
+- can
+- cannot
+- cant
+- co
+- con
+- could
+- couldnt
+- cry
+- de
+- describe
+- detail
+- do
+- done
+- down
+- due
+- during
+- each
+- eg
+- eight
+- either
+- eleven
+- else
+- elsewhere
+- empty
+- enough
+- etc
+- even
+- ever
+- every
+- everyone
+- everything
+- everywhere
+- except
+- few
+- fifteen
+- fify
+- fill
+- find
+- fire
+- first
+- five
+- for
+- former
+- formerly
+- forty
+- found
+- four
+- from
+- front
+- full
+- further
+- get
+- give
+- go
+- had
+- has
+- hasnt
+- have
+- he
+- hence
+- her
+- here
+- hereafter
+- hereby
+- herein
+- hereupon
+- hers
+- herself
+- him
+- himself
+- his
+- how
+- however
+- hundred
+- ie
+- if
+- in
+- inc
+- indeed
+- interest
+- into
+- is
+- it
+- its
+- itself
+- keep
+- last
+- latter
+- latterly
+- least
+- less
+- ltd
+- made
+- many
+- may
+- me
+- meanwhile
+- might
+- mill
+- mine
+- more
+- moreover
+- most
+- mostly
+- move
+- much
+- must
+- my
+- myself
+- name
+- namely
+- neither
+- never
+- nevertheless
+- next
+- nine
+- no
+- nobody
+- none
+- noone
+- nor
+- not
+- nothing
+- now
+- nowhere
+- of
+- off
+- often
+- on
+- once
+- one
+- only
+- onto
+- or
+- other
+- others
+- otherwise
+- our
+- ours
+- ourselves
+- out
+- over
+- own
+- part
+- per
+- perhaps
+- please
+- put
+- rather
+- re
+- same
+- see
+- seem
+- seemed
+- seeming
+- seems
+- serious
+- several
+- she
+- should
+- show
+- side
+- since
+- sincere
+- six
+- sixty
+- so
+- some
+- somehow
+- someone
+- something
+- sometime
+- sometimes
+- somewhere
+- still
+- such
+- system
+- take
+- ten
+- than
+- that
+- the
+- their
+- them
+- themselves
+- then
+- thence
+- there
+- thereafter
+- thereby
+- therefore
+- therein
+- thereupon
+- these
+- they
+- thickv
+- thin
+- third
+- this
+- those
+- though
+- three
+- through
+- throughout
+- thru
+- thus
+- to
+- together
+- too
+- top
+- toward
+- towards
+- twelve
+- twenty
+- two
+- un
+- under
+- until
+- up
+- upon
+- us
+- very
+- via
+- was
+- we
+- well
+- were
+- what
+- whatever
+- when
+- whence
+- whenever
+- where
+- whereafter
+- whereas
+- whereby
+- wherein
+- whereupon
+- wherever
+- whether
+- which
+- while
+- whither
+- who
+- whoever
+- whole
+- whom
+- whose
+- why
+- will
+- with
+- within
+- without
+- would
+- yet
+- you
+- your
+- yours
+- yourself
+- yourselves

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/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/version.rb

@@ -1,4 +1,6 @@
 module TextRank
+
   # Current gem version
-  VERSION = '1.2.3'
+  VERSION = '1.3.0'
+
 end

data/lib/text_rank.rb

@@ -1,4 +1,6 @@
 require 'page_rank'
+require 'set'
+require 'yaml'
 
 ##
 # Provides convenience methods for quickly extracting keywords.
@@ -7,17 +9,18 @@ require 'page_rank'
 ##
 module TextRank
 
-  autoload :CharFilter,       'text_rank/char_filter'
-  autoload :Fingerprint,      'text_rank/fingerprint'
-  autoload :GraphStrategy,    'text_rank/graph_strategy'
-  autoload :KeywordExtractor, 'text_rank/keyword_extractor'
-  autoload :RankFilter,       'text_rank/rank_filter'
-  autoload :TokenFilter,      'text_rank/token_filter'
-  autoload :Tokenizer,        'text_rank/tokenizer'
-  autoload :VERSION,          'text_rank/version'
+  autoload :CharFilter,         'text_rank/char_filter'
+  autoload :Fingerprint,        'text_rank/fingerprint'
+  autoload :FingerprintOverlap, 'text_rank/fingerprint_overlap'
+  autoload :GraphStrategy,      'text_rank/graph_strategy'
+  autoload :KeywordExtractor,   'text_rank/keyword_extractor'
+  autoload :RankFilter,         'text_rank/rank_filter'
+  autoload :TokenFilter,        'text_rank/token_filter'
+  autoload :Tokenizer,          'text_rank/tokenizer'
+  autoload :VERSION,            'text_rank/version'
 
   # A convenience method for quickly extracting keywords from text with default options
-  # @param text [String] text from which to extract keywords
+  # @param text [String,Array<String>] text from which to extract keywords
   # @option (see KeywordExtractor.basic)
   # @return [Hash<String, Float>] of tokens and text rank (in descending order)
   def self.extract_keywords(text, **options)
@@ -37,3 +40,5 @@ module TextRank
   end
 
 end
+
+require 'text_rank/text_rank'

data/text_rank.gemspec

@@ -16,13 +16,16 @@ Gem::Specification.new do |spec|
   spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
   spec.bindir        = 'exe'
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.extensions    = ['ext/text_rank/extconf.rb']
   spec.require_paths = ['lib']
 
   spec.add_development_dependency 'bundler'
   spec.add_development_dependency 'rake'
+  spec.add_development_dependency 'rake-compiler'
   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 'simplecov'
+  spec.add_development_dependency 'yard'
 
   spec.add_development_dependency 'engtagger' # Optional runtime dependency but needed for specs
   spec.add_development_dependency 'nokogiri'  # Optional runtime dependency but needed for specs

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: text_rank
 version: !ruby/object:Gem::Version
-  version: 1.2.3
+  version: 1.3.0
 platform: ruby
 authors:
 - David McCullars
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2020-06-10 00:00:00.000000000 Z
+date: 2021-12-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -38,6 +38,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: rake-compiler
+  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: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -70,16 +84,30 @@ dependencies:
   name: simplecov
   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: yard
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.17.0
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.17.0
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: engtagger
   requirement: !ruby/object:Gem::Requirement
@@ -113,7 +141,8 @@ description: Implementation of TextRank solution to ranked keyword extraction.
 email:
 - david.mccullars@gmail.com
 executables: []
-extensions: []
+extensions:
+- ext/text_rank/extconf.rb
 extra_rdoc_files: []
 files:
 - ".codeclimate.yml"
@@ -129,10 +158,15 @@ files:
 - Rakefile
 - bin/console
 - bin/setup
+- ext/text_rank/extconf.rb
+- ext/text_rank/page_rank_sparse_native.c
+- ext/text_rank/page_rank_sparse_native.h
+- ext/text_rank/text_rank.c
 - lib/page_rank.rb
 - lib/page_rank/base.rb
 - lib/page_rank/dense.rb
 - lib/page_rank/sparse.rb
+- lib/page_rank/sparse_native.rb
 - lib/text_rank.rb
 - lib/text_rank/char_filter.rb
 - lib/text_rank/char_filter/ascii_folding.rb
@@ -141,7 +175,9 @@ 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 +190,7 @@ 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 +204,7 @@ homepage: https://github.com/david-mccullars/text_rank
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -182,9 +219,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6
-signing_key: 
+rubygems_version: 3.2.32
+signing_key:
 specification_version: 4
 summary: Implementation of TextRank solution to ranked keyword extraction
 test_files: []