Please, apply attached patch for contrib/tsearch to 7.2.1 and current

CVS. It  fix english stemmer's problem with ending words like
'technology'.

We have found one more bug in english stemmer. The bug is with
'irregular'  english words like 'skies' -> 'sky'. Please, apply attached
cumulative patch to  7.2.1 and current CVS instead previous one.

Thank to Thomas T. Thai <tom@minnesota.com> for hard testing. This kind
of bug  has significance only for dump/reload database and viewing, but
searching/indexing works right.

Teodor Sigaev

diff --git a/contrib/tsearch/dict/porter_english.dct b/contrib/tsearch/dict/porter_english.dct
index 1f809df9c8cdd40fd8c998680e5110e8b39e0caf..5158a9b876237ad9bd861612374c1bb1a027e332 100644 (file)
--- a/contrib/tsearch/dict/porter_english.dct
+++ b/contrib/tsearch/dict/porter_english.dct
@@ -577,7 +577,7 @@ static void step_2(struct english_stemmer * z)
         case 'g':
             if (ends(z, "logi", 4))
             {   z->j++;                /*-NEW-*/ /*(Barry Wilkins)*/
-                r(z, "og", 3); break;
+                r(z, "og", 2); break;
             } /*-DEPARTURE-*/
 
      /* To match the published algorithm, delete this line */
@@ -683,7 +683,10 @@ static const char * english_stem(void * z_, const char * q, int i0, int i1)
 
 
     {   const char * t = search_pool(z->irregulars, z->k + 1, z->p);
-        if (t != 0) return t;
+        if (t != 0)  {
+               z->k = strlen(t) - 1;   
+               return t;
+       }
     }
 
     if (z->k > 1) /*-DEPARTURE-*/