word_count_analyzer 1.0.0 → 1.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: e5a101dde1b0e3db7728e7c17716ee5e4a3201e7
-  data.tar.gz: e16de9a391248d423b88d24c5e2a835a480f8623
+  metadata.gz: 3e712d9e33ebce0a210f1ae805a63d97e9247d12
+  data.tar.gz: c4ee01b16b5162c959f00470702203b67244b4ab
 SHA512:
-  metadata.gz: cda1823794f39e1b086e93ae62e10cb8db43f6aab8659988a5f391eb4b9af64c898f8224b7e7a4a0689838885c35078f9be4b639eaf237d0175dcd6183783f19
-  data.tar.gz: a0900c47c0a29afd32169bb35fddd1dbb96685c420def00d0b26f8440a0a8b71ddc9e5badfb8683096d7e6ddf475c9f66f3c023959a926a4e1696593c0398f73
+  metadata.gz: 48e15099bf3fbb8ab86203e3fdb92c79a79a1ff156e51320c6c64a4e5629f26ff1f279b6c55a65f7eed6218b9e3fe36daa9a623969f2f15d63c43b2f95ba35d1
+  data.tar.gz: 5e53e7c056ff7ae533fbf1ec9114cf13febc90bb2926ba6004397043bbc3e142cbf82001a9b35c822ab1e30b23013effaedb56a609759b683e94202a0726868b

data/.gitignore

@@ -7,6 +7,7 @@
 /pkg/
 /spec/reports/
 /tmp/
+.idea/
 *.bundle
 *.so
 *.o

data/lib/word_count_analyzer/analyzer.rb

@@ -8,20 +8,20 @@ module WordCountAnalyzer
 
     def analyze
       analysis = {}
-      analysis['ellipsis'] = WordCountAnalyzer::Ellipsis.new.occurences(text)
+      analysis['ellipsis'] = WordCountAnalyzer::Ellipsis.new.occurrences(text)
       contraction_count = 0
       hyphenated_word_count = 0
       WordCountAnalyzer::Xhtml.new(string: text).replace.split(/\s+/).each_with_index do |token, index|
         contraction_count += 1 if WordCountAnalyzer::Contraction.new(token: token, following_token: text.split(/\s+/)[index + 1], tgr: tagger, hyphen: 'single').contraction?
         hyphenated_word_count += 1 if WordCountAnalyzer::HyphenatedWord.new(token: token).hyphenated_word?
       end
-      analysis['hyperlink'] = WordCountAnalyzer::Hyperlink.new.occurences(text)
+      analysis['hyperlink'] = WordCountAnalyzer::Hyperlink.new.occurrences(text)
       analysis['contraction'] = contraction_count
       analysis['hyphenated_word'] = hyphenated_word_count
-      analysis['date'] = WordCountAnalyzer::Date.new.occurences(text)
-      analysis['number'] = WordCountAnalyzer::Number.new(string: text).occurences
-      analysis['numbered_list'] = WordCountAnalyzer::NumberedList.new(string: text).occurences
-      analysis['xhtml'] = WordCountAnalyzer::Xhtml.new(string: text).occurences
+      analysis['date'] = WordCountAnalyzer::Date.new.occurrences(text)
+      analysis['number'] = WordCountAnalyzer::Number.new(string: text).occurrences
+      analysis['numbered_list'] = WordCountAnalyzer::NumberedList.new(string: text).occurrences
+      analysis['xhtml'] = WordCountAnalyzer::Xhtml.new(string: text).occurrences
       analysis['forward_slash'] = WordCountAnalyzer::Slash.new(string: text).forward_slash_occurences
       analysis['backslash'] = WordCountAnalyzer::Slash.new(string: text).backslash_occurences
       analysis['dotted_line'] = WordCountAnalyzer::Punctuation.new(string: text).dotted_line_ocurrances

data/lib/word_count_analyzer/counter.rb

@@ -68,8 +68,8 @@ module WordCountAnalyzer
       processed_text = process_hyperlink(processed_text)
       processed_text = process_contraction(processed_text, @tgr)
       processed_text = process_date(processed_text)
-      processed_text = process_number(processed_text)
       processed_text = process_number_list(processed_text)
+      processed_text = process_number(processed_text)
       processed_text = process_xhtml(processed_text)
       processed_text = process_forward_slash(processed_text)
       processed_text = process_backslash(processed_text)

data/lib/word_count_analyzer/date.rb

@@ -27,7 +27,7 @@ module WordCountAnalyzer
       redact_regex(text)
     end
 
-    def occurences(text)
+    def occurrences(text)
       replace(text).scan(/wsdateword/).size
     end
 

data/lib/word_count_analyzer/ellipsis.rb

@@ -29,7 +29,7 @@ module WordCountAnalyzer
             .gsub(UNICODE_ELLIPSIS, ' wseword ')
     end
 
-    def occurences(text)
+    def occurrences(text)
       count = 0
       replace(text).split(' ').map { |token| count += 1 if token.strip.eql?('wseword') }
       count

data/lib/word_count_analyzer/hyperlink.rb

@@ -11,7 +11,7 @@ module WordCountAnalyzer
       !(text !~ URI.regexp) && text !~ NON_HYPERLINK_REGEX && !(text !~ HYPERLINK_REGEX)
     end
 
-    def occurences(text)
+    def occurrences(text)
       text.scan(URI.regexp).map { |link| link.compact.size > 1 ? 1 : 0 }.inject(0) { |sum, x| sum + x }
     end
 

data/lib/word_count_analyzer/number.rb

@@ -1,11 +1,11 @@
 module WordCountAnalyzer
   class Number
     # Rubular: http://rubular.com/r/OGj82uEu8d
-    NUMBER_REGEX = /(?<=\A)\D?\d+((,|\.)*\d)*(\D?\s|\s|\.?\s|\.$)|(?<=\s)\D?\d+((,|\.)*\d)*(\D?\s|\s|\.?\s|\.$)/
+    NUMBER_REGEX = /(?<=\A)\D?\d+((,|\.)*\d)*(\D?\s|\s|\.?\s|\.$)|(?<=\s)\D?\d+((,|\.)*\d)*(\D?\s|\s|\.?\s|\.$|$)/
 
     attr_reader :string
     def initialize(string:)
-      @string = WordCountAnalyzer::NumberedList.new(string: WordCountAnalyzer::Date.new.replace(string)).replace
+      @string = string
     end
 
     def includes_number?
@@ -16,7 +16,7 @@ module WordCountAnalyzer
       string.gsub(NUMBER_REGEX, ' wsnumword ')
     end
 
-    def occurences
+    def occurrences
       replace.scan(/wsnumword/).size
     end
   end

data/lib/word_count_analyzer/numbered_list.rb

@@ -35,7 +35,7 @@ module WordCountAnalyzer
       new_string
     end
 
-    def occurences
+    def occurrences
       count_list_items_in_array
     end
 

data/lib/word_count_analyzer/version.rb

@@ -1,3 +1,3 @@
 module WordCountAnalyzer
-  VERSION = "1.0.0"
+  VERSION = "1.0.1"
 end

data/lib/word_count_analyzer/xhtml.rb

@@ -19,7 +19,7 @@ module WordCountAnalyzer
       string.split(/\s+/).size - replace.strip.split(/\s+/).size
     end
 
-    def occurences
+    def occurrences
       string.gsub(XHTML_REGEX, ' wsxhtmlword ').scan(/wsxhtmlword/).size / 2
     end
   end

data/spec/word_count_analyzer/analyzer_spec.rb

@@ -5,7 +5,7 @@ RSpec.describe WordCountAnalyzer::Analyzer do
     it 'should analyze the gray areas #001' do
       text = "This string has a date: Monday, November 3rd, 2011. I was thinking... it also shouldn't have too many contractions, maybe 2. <html> Some HTML and a hyphenated-word</html>. Don't count punctuation ? ? ? Please visit the ____________ ------------ ........ go-to site: https://www.example-site.com today. Let's add a list 1. item a 2. item b 3. item c. Now let's add he/she/it or a c:\\Users\\john. 2/15/2012 is the date! { HYPERLINK 'http://www.hello.com' }"
       ws = WordCountAnalyzer::Analyzer.new(text: text)
-      expect(ws.analyze).to eq({"ellipsis"=>1, "hyperlink"=>2, "contraction"=>4, "hyphenated_word"=>2, "date"=>2, "number"=>1, "numbered_list"=>3, "xhtml"=>1, "forward_slash"=>1, "backslash"=>1, "dotted_line"=>1, "dashed_line"=>1, "underscore"=>1, "stray_punctuation"=>5})
+      expect(ws.analyze).to eq({"ellipsis"=>1, "hyperlink"=>2, "contraction"=>4, "hyphenated_word"=>2, "date"=>2, "number"=>5, "numbered_list"=>3, "xhtml"=>1, "forward_slash"=>1, "backslash"=>1, "dotted_line"=>1, "dashed_line"=>1, "underscore"=>1, "stray_punctuation"=>5})
     end
 
     it 'should analyze the gray areas #002' do

data/spec/word_count_analyzer/date_spec.rb

@@ -225,28 +225,28 @@ RSpec.describe WordCountAnalyzer::Date do
     end
   end
 
-  context '#occurences' do
-    it 'counts the date occurences in a string #001' do
+  context '#occurrences' do
+    it 'counts the date occurrences in a string #001' do
       string = 'Today is Sunday, 8 November 2014.'
       ws = WordCountAnalyzer::Date.new
-      expect(ws.occurences(string)).to eq(1)
+      expect(ws.occurrences(string)).to eq(1)
     end
 
-    it 'counts the date occurences in a string #002' do
+    it 'counts the date occurrences in a string #002' do
       string = 'Today is Sunday, 8 November 2014. Yesterday was 07/Nov/2014.'
       ws = WordCountAnalyzer::Date.new
-      expect(ws.occurences(string)).to eq(2)
+      expect(ws.occurrences(string)).to eq(2)
     end
   end
 
   context '#replace' do
-    it 'replaces the date occurences in a string #001' do
+    it 'replaces the date occurrences in a string #001' do
       string = 'Today is Tues. March 3rd, 2011.'
       ws = WordCountAnalyzer::Date.new
       expect(ws.replace(string)).to eq('Today is  wsdateword ')
     end
 
-    it 'replaces the date occurences in a string #002' do
+    it 'replaces the date occurrences in a string #002' do
       string = 'The scavenger hunt ends on Dec. 31st, 2011.'
       ws = WordCountAnalyzer::Date.new
       expect(ws.replace(string)).to eq('The scavenger hunt ends on  wsdateword ')
@@ -254,7 +254,7 @@ RSpec.describe WordCountAnalyzer::Date do
   end
 
   context '#replace_number_only_date' do
-    it 'replaces only the number date occurences in a string' do
+    it 'replaces only the number date occurrences in a string' do
       string = 'Today is Tues. March 3rd, 2011. 4/28/2013'
       ws = WordCountAnalyzer::Date.new
       expect(ws.replace_number_only_date(string)).to eq("Today is Tues. March 3rd, 2011.  wsdateword ")

data/spec/word_count_analyzer/ellipsis_spec.rb

@@ -95,11 +95,11 @@ RSpec.describe WordCountAnalyzer::Ellipsis do
     end
   end
 
-  context '#occurences' do
+  context '#occurrences' do
     it 'returns a string with the ellipsis replaced #001' do
       string = 'Using an ellipsis … causes different counts…depending on the style . . . that you use. I never meant that.... She left the store. The practice was not abandoned. . . .'
       ws = WordCountAnalyzer::Ellipsis.new
-      expect(ws.occurences(string)).to eq(5)
+      expect(ws.occurrences(string)).to eq(5)
     end
   end
 end

data/spec/word_count_analyzer/hyperlink_spec.rb

@@ -45,11 +45,11 @@ RSpec.describe WordCountAnalyzer::Hyperlink do
     end
   end
 
-  context '#occurences' do
-    it 'returns the occurences of hyperlink tokens in a string #001' do
+  context '#occurrences' do
+    it 'returns the occurrences of hyperlink tokens in a string #001' do
       string = "Today the date is: Jan 1. Visit https://www.example.com/hello or http://www.google.co.uk"
       ws = WordCountAnalyzer::Hyperlink.new
-      expect(ws.occurences(string)).to eq(2)
+      expect(ws.occurrences(string)).to eq(2)
     end
   end
 

data/spec/word_count_analyzer/number_spec.rb

@@ -26,13 +26,19 @@ RSpec.describe WordCountAnalyzer::Number do
       expect(ws.includes_number?).to eq(true)
     end
 
-    it "returns false if the string doesn't includes a number #005" do
+    it 'returns true if the string includes a number #005' do
+      string = 'I was born in 1993'
+      ws = WordCountAnalyzer::Number.new(string: string)
+      expect(ws.includes_number?).to eq(true)
+    end
+
+    it "returns false if the string doesn't includes a number #006" do
       string = 'Hello world.'
       ws = WordCountAnalyzer::Number.new(string: string)
       expect(ws.includes_number?).to eq(false)
     end
 
-    it "returns false if the string doesn't includes a number #006" do
+    it "returns false if the string doesn't includes a number #007" do
       string = 'Today is 2/18/2014.'
       ws = WordCountAnalyzer::Number.new(string: string)
       expect(ws.includes_number?).to eq(false)
@@ -47,17 +53,17 @@ RSpec.describe WordCountAnalyzer::Number do
     end
   end
 
-  context '#occurences' do
-    it 'returns the number of occurences of a number in the string #001' do
+  context '#occurrences' do
+    it 'returns the number of occurrences of a number in the string #001' do
       string = 'It was only 50 % of the total. 500 total. That costs $300 and is 50% off.'
       ws = WordCountAnalyzer::Number.new(string: string)
-      expect(ws.occurences).to eq(4)
+      expect(ws.occurrences).to eq(4)
     end
 
-    it 'ignores dates #002' do
+    it 'does not ignore dates #002' do
       string = 'It was only 50 % of the total on Wednesday, June 4 2015. 500 total. That costs $300 and is 50% off only on Apr 5th 1999.'
       ws = WordCountAnalyzer::Number.new(string: string)
-      expect(ws.occurences).to eq(4)
+      expect(ws.occurrences).to eq(7)
     end
   end
 end

data/spec/word_count_analyzer/numbered_list_spec.rb

@@ -35,35 +35,35 @@ RSpec.describe WordCountAnalyzer::NumberedList do
     end
   end
 
-  context '#occurences' do
-    it 'counts the occurences of numbered lists #001' do
+  context '#occurrences' do
+    it 'counts the occurrences of numbered lists #001' do
       string = "1. List item a\n\n2. List item b\n\n3. List item c."
       ws = WordCountAnalyzer::NumberedList.new(string: string)
-      expect(ws.occurences).to eq(3)
+      expect(ws.occurrences).to eq(3)
     end
 
-    it 'counts the occurences of numbered lists #002' do
+    it 'counts the occurrences of numbered lists #002' do
       string = "I have 2."
       ws = WordCountAnalyzer::NumberedList.new(string: string)
-      expect(ws.occurences).to eq(0)
+      expect(ws.occurrences).to eq(0)
     end
 
-    it 'counts the occurences of numbered lists #003' do
+    it 'counts the occurrences of numbered lists #003' do
       string = "1. List item a\n\n2. List item b\n\n3. List item c. Then more text. Ok start a new list. 1. item a 2. item b."
       ws = WordCountAnalyzer::NumberedList.new(string: string)
-      expect(ws.occurences).to eq(5)
+      expect(ws.occurrences).to eq(5)
     end
 
-    it 'counts the occurences of numbered lists #004' do
+    it 'counts the occurrences of numbered lists #004' do
       string = "1. List item a\n\n2. List item b\n\n3. List item c. Then more text. Ok start a new non-list. I have 2."
       ws = WordCountAnalyzer::NumberedList.new(string: string)
-      expect(ws.occurences).to eq(3)
+      expect(ws.occurrences).to eq(3)
     end
 
-    it 'counts the occurences of numbered lists #005' do
+    it 'counts the occurrences of numbered lists #005' do
       string = "It also shouldn't have too many contractions, maybe 2. Let's add a list 1. item a 2. item b 3. item c."
       ws = WordCountAnalyzer::NumberedList.new(string: string)
-      expect(ws.occurences).to eq(3)
+      expect(ws.occurrences).to eq(3)
     end
   end
 end

data/spec/word_count_analyzer/punctuation_spec.rb

@@ -2,13 +2,13 @@ require 'spec_helper'
 
 RSpec.describe WordCountAnalyzer::Punctuation do
   context '#dotted_line_ocurrances' do
-    it 'returns the number of dotted line occurences #001' do
+    it 'returns the number of dotted line occurrences #001' do
       string = "Here is one …………………………………………………………………… and another ......"
       ws = WordCountAnalyzer::Punctuation.new(string: string)
       expect(ws.dotted_line_ocurrances).to eq(2)
     end
 
-    it 'returns the number of dotted line occurences #002' do
+    it 'returns the number of dotted line occurrences #002' do
       string = "Hello world"
       ws = WordCountAnalyzer::Punctuation.new(string: string)
       expect(ws.dotted_line_ocurrances).to eq(0)
@@ -16,13 +16,13 @@ RSpec.describe WordCountAnalyzer::Punctuation do
   end
 
   context '#dashed_line_ocurrances' do
-    it 'returns the number of dotted line occurences #001' do
+    it 'returns the number of dotted line occurrences #001' do
       string = "Here is one ----- and another -----"
       ws = WordCountAnalyzer::Punctuation.new(string: string)
       expect(ws.dashed_line_ocurrances).to eq(2)
     end
 
-    it 'returns the number of dotted line occurences #002' do
+    it 'returns the number of dotted line occurrences #002' do
       string = "Hello world"
       ws = WordCountAnalyzer::Punctuation.new(string: string)
       expect(ws.dashed_line_ocurrances).to eq(0)
@@ -30,13 +30,13 @@ RSpec.describe WordCountAnalyzer::Punctuation do
   end
 
   context '#underscore_ocurrances' do
-    it 'returns the number of undescore occurences #001' do
+    it 'returns the number of undescore occurrences #001' do
       string = "Here is one ______ and another ______"
       ws = WordCountAnalyzer::Punctuation.new(string: string)
       expect(ws.underscore_ocurrances).to eq(2)
     end
 
-    it 'returns the number of undescore occurences #002' do
+    it 'returns the number of undescore occurrences #002' do
       string = "Hello world"
       ws = WordCountAnalyzer::Punctuation.new(string: string)
       expect(ws.underscore_ocurrances).to eq(0)
@@ -44,19 +44,19 @@ RSpec.describe WordCountAnalyzer::Punctuation do
   end
 
   context '#stray_punctuation_occurences' do
-    it 'returns the number of stray punctuation occurences #001' do
+    it 'returns the number of stray punctuation occurrences #001' do
       string = "Hello world ? This is another - sentence ."
       ws = WordCountAnalyzer::Punctuation.new(string: string)
       expect(ws.stray_punctuation_occurences).to eq(3)
     end
 
-    it 'returns the number of stray punctuation occurences #002' do
+    it 'returns the number of stray punctuation occurrences #002' do
       string = "Hello world. Great?"
       ws = WordCountAnalyzer::Punctuation.new(string: string)
       expect(ws.stray_punctuation_occurences).to eq(0)
     end
 
-    it 'returns the number of stray punctuation occurences #003' do
+    it 'returns the number of stray punctuation occurrences #003' do
       string = "."
       ws = WordCountAnalyzer::Punctuation.new(string: string)
       expect(ws.stray_punctuation_occurences).to eq(1)

data/spec/word_count_analyzer/slash_spec.rb

@@ -42,13 +42,13 @@ RSpec.describe WordCountAnalyzer::Slash do
   end
 
   context '#forward_slash_occurences' do
-    it 'returns the number of occurences of tokens with a forward slash #001' do
+    it 'returns the number of occurrences of tokens with a forward slash #001' do
       string = "Using the solidus for he/she/it is often discouraged, except in this case she/he said."
       ws = WordCountAnalyzer::Slash.new(string: string)
       expect(ws.forward_slash_occurences).to eq(2)
     end
 
-    it 'returns the number of occurences of tokens with a forward slash #002' do
+    it 'returns the number of occurrences of tokens with a forward slash #002' do
       string = "Hello world."
       ws = WordCountAnalyzer::Slash.new(string: string)
       expect(ws.forward_slash_occurences).to eq(0)
@@ -56,19 +56,19 @@ RSpec.describe WordCountAnalyzer::Slash do
   end
 
   context '#backslash_occurences' do
-    it 'returns the number of occurences of tokens with a backslash #001' do
+    it 'returns the number of occurrences of tokens with a backslash #001' do
       string = 'The file location is c:\Users\johndoe or d:\Users\john\www'
       ws = WordCountAnalyzer::Slash.new(string: string)
       expect(ws.backslash_occurences).to eq(2)
     end
 
-    it 'returns the number of occurences of tokens with a backslash #002' do
+    it 'returns the number of occurrences of tokens with a backslash #002' do
       string = "Hello world."
       ws = WordCountAnalyzer::Slash.new(string: string)
       expect(ws.backslash_occurences).to eq(0)
     end
 
-    it 'returns the number of occurences of tokens with a backslash #003' do
+    it 'returns the number of occurrences of tokens with a backslash #003' do
       string = "<span>Hello world.</span>"
       ws = WordCountAnalyzer::Slash.new(string: string)
       expect(ws.backslash_occurences).to eq(0)

data/spec/word_count_analyzer/xhtml_spec.rb

@@ -55,11 +55,11 @@ RSpec.describe WordCountAnalyzer::Xhtml do
     end
   end
 
-  context '#occurences' do
+  context '#occurrences' do
     it 'counts the number of tags (1 opening set and 1 closing set of tags counts as 1)' do
       string = '<span class=”cool-text”>Hello world</span> Hello there. Another sentence <tuv>Sentence</tuv> here. Hello world.'
       ws = WordCountAnalyzer::Xhtml.new(string: string)
-      expect(ws.occurences).to eq(2)
+      expect(ws.occurrences).to eq(2)
     end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: word_count_analyzer
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.1
 platform: ruby
 authors:
 - Kevin S. Dias
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-03-07 00:00:00.000000000 Z
+date: 2017-12-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -147,7 +147,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.1
+rubygems_version: 2.6.14
 signing_key: 
 specification_version: 4
 summary: A word count analyzer - see what word count gray areas might be affecting