srx-english 0.1.1 → 0.1.2

data/README.rdoc

@@ -41,7 +41,7 @@ over the matched sentences:
 
   sentence = 'My home is my castle.'
   splitter = SRX::English::WordSplitter.new(sentence)
-  splitter.each do |word,type|
+  splitter.each do |word,type,start_offset,end_offset|
     puts "'#{word}' #{type}"
   end
   # 'My' word 

data/changelog.txt

@@ -1,3 +1,5 @@
+0.1.2
+- Word splitter reports positions of the word
 0.1.1
 - Use getc instead of readchar
 0.1.0

data/features/steps/word_splitter.rb

@@ -1,6 +1,6 @@
 # encoding: utf-8
 $:.unshift "lib"
-#require 'srx/english/word_splitter'
+require 'srx/english/word_splitter'
 
 Given /^a sentence '([^']+)'$/ do |sentence|
   @sentence = sentence.force_encoding('utf-8')
@@ -14,6 +14,8 @@ Then /^the following segments should be detected$/ do |table|
   table.hashes.zip(@splitter.to_a).each do |expected,returned|
     returned[0].should == expected[:segment].gsub(/'/,"")
     returned[1].should == expected[:type].to_sym
+    returned[2].should == expected[:start].to_i
+    returned[3].should == expected[:end].to_i
   end
 end
 

data/features/word_splitter.feature

@@ -3,15 +3,15 @@ Feature: word splitter
     Given a sentence 'My home is my castle.'
     When the sentence is split
     Then the following segments should be detected
-      | segment | type  |
-      #-----------------#
-      | My      | word  |
-      | ' '     | other |
-      | home    | word  |
-      | ' '     | other |
-      | is      | word  |
-      | ' '     | other |
-      | my      | word  |
-      | ' '     | other |
-      | castle  | word  |
-      | .       | punct |
+      | segment | type  | start | end |
+      #-------------------------------#
+      | My      | word  | 0     | 1   |
+      | ' '     | other | 2     | 2   |
+      | home    | word  | 3     | 6   |
+      | ' '     | other | 7     | 7   |
+      | is      | word  | 8     | 9   |
+      | ' '     | other | 10    | 10  |
+      | my      | word  | 11    | 12  |
+      | ' '     | other | 13    | 13  |
+      | castle  | word  | 14    | 19  |
+      | .       | punct | 20    | 20  |

data/lib/srx/english/word_splitter.rb

@@ -38,16 +38,18 @@ module SRX
       def each
         raise "Invalid argument - sentence is nil" if @sentence.nil?
         @sentence.scan(SPLIT_RE) do |word,number,punct,graph,other|
+          start_offset = $~.begin(0)
+          end_offset = $~.end(0)-1
           if !word.nil?
-            yield word, :word
+            yield word, :word, start_offset, end_offset
           elsif !number.nil?
-            yield number, :number
+            yield number, :number, start_offset, end_offset
           elsif !punct.nil?
-            yield punct, :punct
+            yield punct, :punct, start_offset, end_offset
           elsif !graph.nil?
-            yield graph, :graph
+            yield graph, :graph, start_offset, end_offset
           else
-            yield other, :other
+            yield other, :other, start_offset, end_offset
           end
         end
       end

data/srx-english.gemspec

@@ -3,7 +3,7 @@ $:.push File.expand_path("../lib", __FILE__)
 
 Gem::Specification.new do |s|
   s.name        = "srx-english"
-  s.version     = "0.1.1"
+  s.version     = "0.1.2"
   s.platform    = Gem::Platform::RUBY
   s.authors     = ["Aleksander Pohl"]
   s.email       = ["apohllo@o2.pl"]

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: srx-english
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-10-22 00:00:00.000000000 Z
+date: 2012-11-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: term-ansicolor