Fix greek splittings of oude, mede, eite

latin-language-toolkit · Aug 25, 2014 · a4a810f · a4a810f
1 parent 6f406b5
commit a4a810f
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 5 deletions.
diff --git a/lib/llt/tokenizer.rb b/lib/llt/tokenizer.rb
@@ -206,8 +206,8 @@ def enclitic(val)
       /^(ne)(c)$/i,
       /^(ne|se)(u)$/i,
       /^(ni)(si)$/i,
-      /^(οὐ|μή|εἰ)(τε)$/i,
-      /^(οὐ|μή)(δε)$/i
+      /^(οὔ|μή|εἴ)(τε)$/i,
+      /^(οὐ|μή)(δ[ὲέε])$/i
     ]
     def split_frequent_enclitics
       container = []

diff --git a/spec/lib/llt/tokenizer_spec.rb b/spec/lib/llt/tokenizer_spec.rb
@@ -288,9 +288,9 @@ def enklitika_test(example)
 
       context "when confronted with -τε" do
         examples = {
-          'οὐτε'  => '-τε οὐ',
+          'οὔτε'  => '-τε οὔ',
           'μήτε'  => '-τε μή',
-          'εἰτε'  => '-τε εἰ'
+          'εἴτε'  => '-τε εἴ'
         }
 
         examples.each do |example, expected|
@@ -302,7 +302,8 @@ def enklitika_test(example)
 
       context "when confronted with -δε" do
         examples = {
-          'οὐδε'  => '-δε οὐ',
+          'οὐδέ'  => '-δέ οὐ',
+          'οὐδὲ'  => '-δὲ οὐ',
           'μήδε'  => '-δε μή'
         }