lingua-it-readability 1.1.7 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 70d0c15fa6f6d656f1b9c469ff01f43f93e829cb
-  data.tar.gz: a05872a83574d05452b149dc1c26de9e9bd41e4d
+  metadata.gz: a882ae84c810b0133e6ef76d2bac16205b411954
+  data.tar.gz: c9f681c724fbb40f91b068dd30c1fee500f37c6d
 SHA512:
-  metadata.gz: f90e12a1c086aa7c2159e72cc7c1a61aa852d7b8780f5385140b1d70250ccec8dee8f531682724bf20c3b372ebba0a85e4f11d62a6de4cdcbf09ab4ad522983f
-  data.tar.gz: e64f4d121377fc221a6d07731c9c1639bbef64ca3e37da8e946e676859ee1a50f3411b96457424dc4341765f5393284fd46fe5841cf196d6ebb0491bb927197e
+  metadata.gz: 9df4807ecb56e41cf2c700fc603c4b0263d19ec29d13e6261c948f29cea85262732bdf43572d4d2703879958a375383cc95e7b0d7c627f7c5c361bbab657fe91
+  data.tar.gz: 48518468c89a5e3d29a67fb5d28fbe8845f6b5633f982b86b27ed437a10bc62acf8d0f0931ca2324d9dac049de0db54e54d2cad6f91b13858c2e4930124cb341

data/CHANGELOG.md

@@ -1,3 +1,11 @@
+#### 1.2.0 - 2016-02-11
+###### Added
+- Analyze_file method
+- More accurate report
+
+###### Fixed
+- Escaped delimiters in sentence regex
+
 #### 1.1.7 - 2016-02-11
 ###### Fixed
 - Minor bugs

data/lib/lingua/it/readability.rb

@@ -60,6 +60,18 @@ module Lingua
         count_words
       end
 
+      # Analyze file content with optional delimiters
+      def analyze_file(file_name, *delimiters)
+        # check that file exists
+        if !File.exists?(file_name)
+          raise "An error has occured"
+          return
+        end
+        # slurp file into string and pass it to analyze method
+        text = File.open(file_name) { |f| f.read }.strip
+        analyze(text, delimiters)
+      end
+
       # Reset Lingua::IT::Sentence symbols delimiter cache
       def reset_delimiter!
         @sentence.reset_delimiter!
@@ -149,6 +161,7 @@ module Lingua
         sprintf "Sentence delimiters            %s \n" <<
                 "Number of paragraphs           %d \n" <<
                 "Number of sentences            %d \n" <<
+                "Number of syllables            %d \n" <<
                 "Number of words                %d \n" <<
                 "Number of characters           %d \n\n" <<
                 "Average words per sentence     %.2f \n" <<
@@ -156,7 +169,7 @@ module Lingua
                 "Gulpease score                 %d \n" <<
                 "Flesch score                   %2.2f \n",
                 sentence.delim_regex.gsub(/\\/,''), num_paragraphs, num_sentences,
-                num_words, num_characters, words_per_sentence,
+                num_syllables, num_words, num_characters, words_per_sentence,
                 syllables_per_word, gulpease, flesch
       end
 

data/lib/lingua/it/readability/version.rb

@@ -1,7 +1,7 @@
 module Lingua
   module It
     module Readability
-      VERSION = "1.1.7"
+      VERSION = "1.2.0"
     end
   end
 end

data/lib/lingua/it/sentence.rb

@@ -29,7 +29,7 @@ module Lingua
       def self.sentences(text)
         txt = text.dup
         txt.gsub!(/\b(#{@abbr_regex})(\.)\B/i, '\10002')
-        txt.gsub!(/["']?[A-Z][^#{@delim_regex}]+((?![#{@delim_regex}]['"]?\s["']?[A-Z][^#{@delim_regex}]).)+[#{@delim_regex}'"]+/, '\2\001')
+        txt.gsub!(/["']?[A-Z][^\Q#{@delim_regex}\E]+((?![\Q#{@delim_regex}\E]['"]?\s["']?[A-Z][^\Q#{@delim_regex}\E]).)+[\Q#{@delim_regex}\E'"]+/, '\2\001')
         txt.gsub!(/\b(#{@abbr_regex})(0002)/i, '\1.')
         txt.split(/01/).map { |sentence| sentence.strip }
       end
@@ -72,7 +72,7 @@ module Lingua
       # Utility method, join all elements of the delimiters arrays
       # without a separator, making suitable for a regex.
       def self.set_delim_regex!
-        @delim_regex = "#{@delimiters.join('\\')}"
+        @delim_regex = "#{@delimiters.join('')}"
       end
 
       initialize_abbreviations!

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: lingua-it-readability
 version: !ruby/object:Gem::Version
-  version: 1.1.7
+  version: 1.2.0
 platform: ruby
 authors:
 - Andrea Giacomo Baldan