llt-tokenizer 0.0.6 → 0.0.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 9a9abfc5e79b148f497749053c8ccfa7ac9653af
-  data.tar.gz: 1c9fe20eb2824eccc1840602beae6552415eb5d2
+  metadata.gz: cd490c0611dc9cd5ed2f2aad95631b500e7e7d35
+  data.tar.gz: fe8162ded4cecfda383f3919576ec19ca14f5a38
 SHA512:
-  metadata.gz: 3cd367d754d75f895240c709aed9697140c8359490bc634e56f118b77cc015c2a08c80d7fa4fa74448084844beec4749a7b01b1789c0805a3a5a8fa8d465d5e9
-  data.tar.gz: 21c50a75955cab805fb81bc1435963e047171936c015981121de1405378fb4af9c21a69153c0c043d3a504986e1022437690cedb60b88e0b8246ca6fce20565b
+  metadata.gz: a8a90a133ccd0c27fbbd20e64df0a8e560ad183010ae55716362e0909c737a6d5359c51a647da387ddade71a3bd50545381c899cd3fcea095001ef0e27c42483
+  data.tar.gz: 2d81412a66b473206d23aec3128d3321ff736f3a9d5ab8fca0349bcc347e8d692b3ee33d0fd2c67f87f031335113c1a54caef80b5aa0a4eaca4c5bd2320d6778

data/lib/llt/tokenizer/version.rb

@@ -1,5 +1,5 @@
 module LLT
   class Tokenizer
-    VERSION = "0.0.6"
+    VERSION = "0.0.7"
   end
 end

data/lib/llt/tokenizer.rb

@@ -169,7 +169,7 @@ module LLT
     ENCLITICS = %w{ que ne ve c }
     def split_enklitika_and_change_their_position
       split_with_force
-      split_nec
+      split_nec_and_oute
       make_frequent_corrections
     end
 
@@ -202,16 +202,22 @@ module LLT
       "#{@enclitics_marker}#{val}"
     end
 
-    def split_nec
-      indices = []
+    def split_nec_and_oute
+      nec_indices  = []
+      oute_indices = []
       @worker.each_with_index do |token, i|
-        if token =~ /^nec$/i
+        case token
+        when /^nec$/i
           token.slice!(-1)
-          indices << (i + indices.size + @shift_range)
+          nec_indices << (i + nec_indices.size + @shift_range)
+        when /^οὐτε$/i
+          token.slice!(-2, 2)
+          oute_indices << (i + oute_indices.size + @shift_range)
         end
       end
 
-      indices.each { |i| @worker.insert(i, enclitic('c')) }
+      nec_indices.each  { |i| @worker.insert(i, enclitic('c')) }
+      oute_indices.each { |i| @worker.insert(i, enclitic('τε')) }
     end
 
     def make_frequent_corrections

data/spec/lib/llt/tokenizer_spec.rb

@@ -260,6 +260,18 @@ describe LLT::Tokenizer do
           end
         end
       end
+
+      context "when confronted with -τε" do
+        examples = {
+          'οὐτε'  => '-τε οὐ'
+        }
+
+        examples.each do |example, expected|
+          it "transforms #{example} to #{expected}" do
+            enklitika_test(example).should be_transformed_to expected
+          end
+        end
+      end
     end
 
     describe "#merge_what_needs_merging" do

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: llt-tokenizer
 version: !ruby/object:Gem::Version
-  version: 0.0.6
+  version: 0.0.7
 platform: ruby
 authors:
 - LFDM
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-08-11 00:00:00.000000000 Z
+date: 2014-08-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -190,7 +190,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.0
+rubygems_version: 2.2.2
 signing_key: 
 specification_version: 4
 summary: Breaks latin sentences into tokens