Update Finnish stemmer

README.md

@@ -9,6 +9,7 @@ This crate implements some stemmer algorithms found in the [snowball project](ht
 -   Danish
 -   Dutch
 -   English
+-   Finnish
 -   French
 -   German
 -   Greek

algorithms/finnish.sbl

@@ -23,16 +23,17 @@ externals ( stem )
 integers ( p1 p2 )
 strings ( x )
 booleans ( ending_removed )
-groupings ( AEI V1 V2 particle_end )
+groupings ( AEI C V1 V2 particle_end )
 
 stringescapes {}
 
-/* special characters (in ISO Latin I) */
+/* special characters */
 
-stringdef a"   hex 'E4'
-stringdef o"   hex 'F6'
+stringdef a"   '{U+00E4}'
+stringdef o"   '{U+00F6}'
 
 define AEI 'a{a"}ei'
+define C 'bcdfghjklmnpqrstvwxz'
 define V1 'aeiouy{a"}{o"}'
 define V2 'aeiou{a"}{o"}'
 define particle_end V1 + 'nt'
@@ -115,7 +116,7 @@ backwardmode (
                 )
 
             'a' '{a"}'              //-.
-                     (V1 non-V1)    // |
+                     (V1 C)         // |
             'tta' 'tt{a"}'          // Partitive  [32]
                      ('e')          // |
             'ta' 't{a"}'            //-'
@@ -171,11 +172,11 @@ backwardmode (
     define tidy as (
         setlimit tomark p1 for (
             do ( LONG and ([next] delete ) ) // undouble vowel
-            do ( [AEI] non-V1 delete ) // remove trailing a, a", e, i
+            do ( [AEI] C delete ) // remove trailing a, a", e, i
             do ( ['j'] 'o' or 'u' delete )
             do ( ['o'] 'j' delete )
         )
-        goto non-V1 [next] -> x  x delete // undouble consonant
+        goto non-V1 [C] -> x  x delete // undouble consonant
     )
 )