word_count_analyzer 0.0.5 → 0.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 7e0495c86a5d6731ba74d17ee091a8d0b9b7f225
-  data.tar.gz: 400039a69d59b118fa4e42c96fc59e4d796bf0f3
+  metadata.gz: b715b4c2304ae956644121693d584b0b37638845
+  data.tar.gz: 3b6d753132d5b9e511378ec06f990efa21fcc86b
 SHA512:
-  metadata.gz: 80ef57f5085d9ceb8b6de3f516313109e872a6f0cbaf3749417d5108ba51d0711bc9bfa8575593db46968d2f9d35ff0aef7be0f1613a546968d851d122a840f2
-  data.tar.gz: 4c6b1843507d4774183345b59ea7c44b3aca8e967965f79c96ae187ca069c48986bb7ef892b20959feb8ce2566ff62dbefda6232c396fb754fbd85bd989657cb
+  metadata.gz: 504f3e98b336ebcce4129b137e5293f3fbe38593fd935d55b56d9807f77c17a7e5ae955c4fba41fde8fe8a9e725232253038e5b912ff892eed8ece89f1819b34
+  data.tar.gz: 2ae63d08ea641d00f60f4d83f07e1a376cd51cdc632bafcf96a1c3e6b7b173c5e970625fa51749b879893e0386a202bebf799448703373cccd6c855bf8c56040

data/README.md

@@ -151,6 +151,8 @@ WordCountAnalyzer::Counter.new(
 
 ##### `date`
   **default** = `'no_special_treatment'`
+- `'no_special_treatment'`   
+  Dates will not be searched for in the string. Therefore, how a date is handled in the word count will depend on other settings.
 - `'count_as_one'`  
   Counts a date as one word. This is more commonly seen in translation CAT tools where a date is thought of as a *placeable* that can usually be automatically translated. Examples:
   - Monday, April 4th, 2011 (1 word)
@@ -163,8 +165,6 @@ WordCountAnalyzer::Counter.new(
   - 2003 November 9 (1 word)
   - 2003-Nov-9 (1 word)
   - and others...
-- `'no_special_treatment'`   
-  Dates will not be searched for in the string. Therefore, how a date is handled in the word count will depend on other settings.
 
 <hr>
 
@@ -197,15 +197,15 @@ WordCountAnalyzer::Counter.new(
 
 ##### `forward_slash`
   **default** = `'count_as_multiple_except_dates'`
-- `'count_as_one'`  
-  Counts any tokens that include a forward slash as one word. Example:
-  - she/he/it (1 word)
-- `'count_as_multiple'`   
-  Separates any tokens that include a forward slash at the slash(s) and counts each token individually. Whether dates, hyperlinks and xhtml are included depends on what is set for those options. Example:
-  - she/he/it (3 words)
 - `'count_as_multiple_except_dates'`   
   Separates any tokens that include a forward slash (except dates) at the slash(s) and counts each token individually. Example:
   - she/he/it 4/25/2014 (4 words)  
+- `'count_as_multiple'`   
+  Separates any tokens that include a forward slash at the slash(s) and counts each token individually. Whether dates, hyperlinks and xhtml are included depends on what is set for those options. Example:
+  - she/he/it (3 words)  
+- `'count_as_one'`  
+  Counts any tokens that include a forward slash as one word. Example:
+  - she/he/it (1 word)
 
 <hr>
 
@@ -222,37 +222,37 @@ WordCountAnalyzer::Counter.new(
 
 ##### `dotted_line`
   **default** = `'ignore'`
-- `'count'`  
-  Counts a dotted line as one word.
 - `'ignore'`   
   Ignores any dotted lines in the string and does not count them towards the word count.
+- `'count'`  
+  Counts a dotted line as one word.
 
 <hr>
 
 ##### `dashed_line`
   **default** = `'ignore'`
+- `'ignore'`   
+  Ignores any dashed lines in the string and does not count them towards the word count.  
 - `'count'`  
   Counts a dashed line as one word.
-- `'ignore'`   
-  Ignores any dashed lines in the string and does not count them towards the word count.
 
 <hr>
 
 ##### `underscore`
   **default** = `'ignore'`
+- `'ignore'`   
+  Ignores any series of underscores in the string and does not count them towards the word count.     
 - `'count'`  
   Counts a series of underscores as one word.
-- `'ignore'`   
-  Ignores any series of underscores in the string and does not count them towards the word count.      
 
 <hr>
 
 ##### `stray_punctuation`
   **default** = `'ignore'`
+- `'ignore'`   
+  Ignores any punctuation marks surrounded on both sides by a whitespace in the string and does not count them towards the word count.    
 - `'count'`  
   Counts a punctuation mark surrounded on both sides by a whitespace as one word.
-- `'ignore'`   
-  Ignores any punctuation marks surrounded on both sides by a whitespace in the string and does not count them towards the word count.     
 
 ### Gray Area Details
 

data/lib/word_count_analyzer/ellipsis.rb

@@ -9,7 +9,7 @@ module WordCountAnalyzer
     # Rubular: http://rubular.com/r/2VvZ8wRbd8
     FOUR_SPACE_REGEX = /(?<=[a-z])(\.\s){3}\.(\z|$|\n)/
 
-    OTHER_THREE_PERIOD_REGEX = /[^\.]\.{3}([^\.]|$)/
+    OTHER_THREE_PERIOD_REGEX = /(?<=[^\.])\.{3}(?=([^\.]|$))/
 
     UNICODE_ELLIPSIS = /(?<=[^…])…{1}(?=[^…])/
 

data/lib/word_count_analyzer/slash.rb

@@ -60,6 +60,7 @@ module WordCountAnalyzer
       processed_string.gsub!(FORWARD_SLASH_REGEX).each do |match|
         match.split(/\/+/).join(' ')
       end
+      processed_string
     end
 
     def replace_forward_slashes_except_dates
@@ -68,6 +69,7 @@ module WordCountAnalyzer
       except_date_string.gsub!(FORWARD_SLASH_REGEX).each do |match|
         match.split(/\/+/).join(' ')
       end
+      except_date_string
     end
 
     def backslash_occurences
@@ -79,6 +81,7 @@ module WordCountAnalyzer
       processed_string.gsub!(BACKSLASH_REGEX).each do |match|
         ' word ' * match.split(/\\+/).length
       end
+      processed_string
     end
   end
 end

data/lib/word_count_analyzer/version.rb

@@ -1,3 +1,3 @@
 module WordCountAnalyzer
-  VERSION = "0.0.5"
+  VERSION = "0.0.6"
 end

data/spec/word_count_analyzer/counter_spec.rb

@@ -553,6 +553,12 @@ RSpec.describe WordCountAnalyzer::Counter do
     expect(ws.count).to eq(66)
   end
 
+  it 'counts the words in a string #005' do
+    text = "Hello world... 11/22/2013"
+    ws = WordCountAnalyzer::Counter.new(text: text)
+    expect(ws.count).to eq(3)
+  end
+
   context 'Pages Word Count' do
     it 'reverse engineers Pages word count #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' }"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: word_count_analyzer
 version: !ruby/object:Gem::Version
-  version: 0.0.5
+  version: 0.0.6
 platform: ruby
 authors:
 - Kevin S. Dias