Update Danish stemmer for alphanumeric change

See snowballstem/snowball#81
snowballstem · Nov 14, 2018 · 306f4e0 · 306f4e0
1 parent cc24ba5
commit 306f4e0
Show file tree

Hide file tree

Showing 3 changed files with 86 additions and 95 deletions.
diff --git a/algorithms/danish/stemmer.tt b/algorithms/danish/stemmer.tt
@@ -216,7 +216,10 @@ The following letters are vowels:
 </DL>
 
 <p>
-A consonant is defined as a non-vowel.
+A consonant is defined as a character from ASCII a-z which isn't a vowel
+(originally this was "A consonant is defined as a non-vowel" but since
+2018-11-15 we've changed this definition to avoid the stemmer from altering
+alphanumeric codes which end with a repeated digit).
 </p>
 
 <p>

diff --git a/code/danish.sbl b/code/danish.sbl
@@ -12,7 +12,7 @@ strings ( ch )
 
 integers ( p1 x )
 
-groupings ( v s_ending )
+groupings ( c v s_ending )
 
 stringescapes {}
 
@@ -22,6 +22,8 @@ stringdef ae   '{U+00E6}'
 stringdef ao   '{U+00E5}'
 stringdef o/   '{U+00F8}'
 
+define c 'bcdfghjklmnpqrstvwxz'
+
 define v 'aeiouy{ae}{ao}{o/}'
 
 define s_ending  'abcdfghjklmnoprtvyz{ao}'
@@ -73,7 +75,7 @@ backwardmode (
         )
     )
     define undouble as (
-        setlimit tomark p1 for ([non-v] ->ch)
+        setlimit tomark p1 for ([c] ->ch)
         ch
         delete
     )