textoken 1.1.0 → 1.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 80a781929cd70c8b3dc465e584c52e03a0a741ae
-  data.tar.gz: dddb77f4f78bef3e14fb337ffddc8552791e5375
+  metadata.gz: e530e61af20068c0e361856680b8df0ce9ace2e9
+  data.tar.gz: a94c443c5db50d0270916e8966c212e0321e8579
 SHA512:
-  metadata.gz: a710083d4674593e17d811413d3439785a206d8c38ef69c6b4b30ea03db1d63e03a97590b3bd00e2f07181c748f0f4592c1ec9d705365f84d7b8665f3f46b571
-  data.tar.gz: 9c93000700578a98cf0348afe3356622b8e740d7f97511e55710d3cf71b3a4e642628969f1391ded74f64714d2717d9492d2a493ae6568fc7f13748ff2002ea5
+  metadata.gz: 923e3261959c09b20f497f6b5d24a0495220265a23e23cd583f55db7d4eba65f5fe441374d4d11d56fc4a3e5856bb5baeda83c3c0f4994b522659121e207bd4e
+  data.tar.gz: 6ccac85435c7192ee2c83bfbc49d2efcff4e8fb695a4e78af5e35d7083ccc4ac4d13930ab9766d906fe41b98f4a50552a9a2aad62fe76a8f66e7cd925bfb6603

data/lib/textoken/options/exclude.rb

@@ -4,11 +4,12 @@ module Textoken
   class Exclude
     include ConditionalOption
 
+    private
+
     # base.text is raw tokens splitted with ' '
     # values are Regexps array to search
     # base.findings, Findings object for pushing matching tokens
-    def tokenize(base)
-      @base = base
+    def tokenize_condition
       tokenize_if { |word, regexp| !word.match(regexp) }
     end
   end

data/lib/textoken/options/less_than.rb

@@ -4,15 +4,14 @@ module Textoken
   class LessThan
     include NumericOption
 
-    def tokenize(base)
-      @base = base
+    private
+
+    def tokenize_condition
       tokenize_if { |word| word.length < number }
     end
 
-    private
-
-    def validate_option_value(value)
-      validate { value.class == Fixnum && value > 1 }
+    def validate_option_value
+      validate { |value| value > 1 }
     end
   end
 end

data/lib/textoken/options/modules/conditional_option.rb

@@ -1,6 +1,8 @@
 module Textoken
   # This module will be shared in options like, only and exclude
   module ConditionalOption
+    include TokenizableOption
+
     attr_reader :regexps, :findings, :base
 
     def priority
@@ -12,6 +14,8 @@ module Textoken
       @findings = Findings.new
     end
 
+    private
+
     def tokenize_if(&block)
       regexps.each do |r|
         base.text.each_with_index do |w, i|

data/lib/textoken/options/modules/numeric_option.rb

@@ -1,18 +1,22 @@
 module Textoken
   # This module will be shared in options like, more_than and less_than
   module NumericOption
-    attr_reader :number, :findings, :base
+    include TokenizableOption
+
+    attr_reader :number, :findings
 
     def priority
       2
     end
 
     def initialize(value)
-      validate_option_value(value)
       @number = value
       @findings = Findings.new
+      validate_option_value
     end
 
+    private
+
     def tokenize_if(&code)
       base.text.each_with_index do |w, i|
         findings.push(i, w) if code.call(w)
@@ -21,7 +25,7 @@ module Textoken
     end
 
     def validate(&code)
-      return if code.call
+      return if number.class == Fixnum && code.call(number)
       Textoken.expression_err "value #{number} is not permitted for
         #{self.class.name} option."
     end

data/lib/textoken/options/modules/tokenizable_option.rb

@@ -0,0 +1,18 @@
+module Textoken
+  # This module will be shared in options like, only_regexp and exclude_regexp
+  module TokenizableOption
+    attr_reader :base
+
+    def tokenize(base)
+      @base = base
+      tokenize_condition
+    end
+
+    private
+
+    def tokenize_condition
+      Textoken.type_err('tokenize_condition method has to be implemented
+        for Options.')
+    end
+  end
+end

data/lib/textoken/options/more_than.rb

@@ -4,15 +4,14 @@ module Textoken
   class MoreThan
     include NumericOption
 
-    def tokenize(base)
-      @base = base
+    private
+
+    def tokenize_condition
       tokenize_if { |word| word.length > number }
     end
 
-    private
-
-    def validate_option_value(value)
-      validate { value.class == Fixnum && value >= 0 }
+    def validate_option_value
+      validate { |value| value >= 0 }
     end
   end
 end

data/lib/textoken/options/only.rb

@@ -4,11 +4,12 @@ module Textoken
   class Only
     include ConditionalOption
 
+    private
+
     # base.text is raw tokens splitted with ' '
     # values are Regexps array to search
     # base.findings, Findings object for pushing matching tokens
-    def tokenize(base)
-      @base = base
+    def tokenize_condition
       tokenize_if { |word, regexp| word.match(regexp) }
     end
   end

data/lib/textoken/version.rb

@@ -1,3 +1,3 @@
 module Textoken
-  VERSION = "1.1.0"
+  VERSION = "1.1.1"
 end

data/lib/textoken.rb

@@ -9,6 +9,7 @@ require 'textoken/findings'
 require 'textoken/tokenizer'
 require 'textoken/scanner'
 
+require 'textoken/options/modules/tokenizable_option'
 require 'textoken/options/modules/numeric_option'
 require 'textoken/options/modules/conditional_option'
 require 'textoken/options/modules/regexp_option'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: textoken
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 1.1.1
 platform: ruby
 authors:
 - Mehmet Cetin
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-10-06 00:00:00.000000000 Z
+date: 2015-10-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -44,23 +44,9 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '10.0'
-- !ruby/object:Gem::Dependency
-  name: pry
-  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'
-description: "Textoken is a Ruby library for text tokenization. \n  This gem extracts
-  words from text with many customizations. \n  It can be used in many fields like
-  crawling and Natural Language Processing."
+description: Textoken is a Ruby library for text tokenization. This gem extracts words
+  from text with many customizations. It can be used in many fields like Web Crawling
+  and Natural Language Processing.
 email:
 - mcetin.cm@gmail.com
 executables: []
@@ -80,6 +66,7 @@ files:
 - lib/textoken/options/modules/conditional_option.rb
 - lib/textoken/options/modules/numeric_option.rb
 - lib/textoken/options/modules/regexp_option.rb
+- lib/textoken/options/modules/tokenizable_option.rb
 - lib/textoken/options/more_than.rb
 - lib/textoken/options/only.rb
 - lib/textoken/options/only_regexp.rb
@@ -108,7 +95,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.5.1
+rubygems_version: 2.4.8
 signing_key: 
 specification_version: 4
 summary: Simple and customizable text tokenization gem.