text_parser 0.1.3 → 0.1.4

data/lib/text_parser/version.rb

@@ -2,7 +2,7 @@ module TextParser
   module Version
     MAJOR = 0
     MINOR = 1
-    PATCH = 3
+    PATCH = 4
     STRING = "#{MAJOR}.#{MINOR}.#{PATCH}"
   end
 end

data/lib/text_parser.rb

@@ -1,3 +1,4 @@
+require 'iconv'  
 module TextParser
   # Returns a parsed text with the words and its occurrences.
   # @param [Hash] [args]
@@ -14,10 +15,10 @@ module TextParser
     text = process_text
     options[:dictionary] = text.split(" ") unless options[:dictionary]
     return [] if options[:dictionary].count < 1
-    regex = Regexp.new(options[:dictionary].join("|"), Regexp::IGNORECASE)
-    match_result = text.scan(regex).map{|i| i.downcase}
+    regex = Regexp.new("(\\b#{options[:dictionary].join('\\b|\\b')}\\b)", Regexp::IGNORECASE)
+    match_result = text.scan(regex).map{|i| i.shift.downcase}   
     match_result.each do |w|
-      result << {:hits => match_result.count(w), :word => w} unless result.select{|r| r[:word] == w}.shift unless options[:negative_dictionary].map{|i| i.downcase}.include?(w)
+      result << {:hits => match_result.count(w), :word => w} unless result.select{|r| r[:word] == w}.shift || options[:negative_dictionary].map{|i| i.downcase}.include?(w)
     end 
     result = result.sort_by{|i| i[options[:order]]}
     result.reverse! if options[:order_direction] == :desc
@@ -27,7 +28,8 @@ module TextParser
   private
   
   def process_text
-    self.gsub(/[^\w\s\-]/, "")
+    text = self.gsub(/\s{2,}/," ")
+    text = text.gsub(/[^\w\s\-]/, "")
   end
 end
 

data/test/text_parser_test.rb

@@ -2,7 +2,6 @@ require "test/unit"
 require "text_parser"
 
 class TextParserTest < Test::Unit::TestCase
-
   def test_should_have_method_parse
     assert "some text".methods.select{|a| a == "parse"}.count > 0
   end
@@ -79,4 +78,28 @@ class TextParserTest < Test::Unit::TestCase
     assert_equal "text".parse(args), [{:word => "text", :hits => 1}]
   end
 
-end
+  def test_should_work_with_many_spaces
+    text = "e se    eu     encher      de    espacos"
+    assert_equal [{:word => "de",  :hits => 1},
+                              {:word => "e", :hits => 1},
+                              {:word => "encher", :hits => 1},
+                              {:word => "espacos", :hits => 1},
+                              {:word => "eu", :hits => 1},
+                              {:word => "se", :hits => 1}], text.parse
+  end   
+end
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

data/text_parser.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name        = "text_parser"
-  s.version     = "0.1.3"
+  s.version     = "0.1.4"
   s.author      = "Frederico de Paula"
   s.email       = "fpaula@gmail.com"
   s.summary     = "A easy way to parse text."

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: text_parser
 version: !ruby/object:Gem::Version 
-  hash: 29
+  hash: 19
   prerelease: 
   segments: 
   - 0
   - 1
-  - 3
-  version: 0.1.3
+  - 4
+  version: 0.1.4
 platform: ruby
 authors: 
 - Frederico de Paula
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-12-07 00:00:00 -02:00
+date: 2011-12-08 00:00:00 -02:00
 default_executable: 
 dependencies: []