Changes in trunk/gsdl/packages/mg-1.3d/lib/frenchstem.c [13:29]

File:

• trunk/gsdl/packages/mg-1.3d/lib/frenchstem.c (modified) (1 diff)

trunk/gsdl/packages/mg-1.3d/lib/frenchstem.c

@@ +1 @@
+/**************************************************************************
+ *
+ * frenchstem.c -- a simple french stemmer
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * $Id$
+ *
+ **************************************************************************/
 
-static char * frenchstem (word)
-char *word;
-{      
-  int len = strlen(word)-1;
-  if (len > 4) {
-    if (word[len]=='x') {
-      if (word[len-1]=='u' && word[len-2]=='a') {
-    word[len-1]='l';
+#include "frenchstem.h"
+
+
+
+/* =========================================================================
+ * Function: frenchstem
+ * Description: a simple french stemmer
+ * Input: a word string with the length in the first byte
+ * Output: the stemmed word
+ * ========================================================================= */
+
+void frenchstem (unsigned char *word) {      
+  unsigned char *wordstart = word + 1; /* points to first letter of word */
+  int last = (int)word[0]-1;           /* last points to the last character */
+
+  if (last > 4) {
+    if (wordstart[last]=='x') {
+      if (wordstart[last-1]=='u' && wordstart[last-2]=='a') {
+    wordstart[last-1]='l';
       }
-      word[len]='\0';
-      return(word);
-    }
-    else {
-      if (word[len]=='s')
-    {word[len]='\0';len--;}
-      if (word[len]=='r')
-    {word[len]='\0';len--;}
-      if (word[len]=='e')
-    {word[len]='\0';len--;}
-      if (word[len]=='é')    /* letter with accent e + ' */
-    {word[len]='\0';len--;}
-      if (word[len] == word[len-1])
-    word[len]='\0';
+      wordstart[last]='\0';
+      last--;
+
+    } else {
+      if (wordstart[last]=='s' && last>=0) 
+    {wordstart[last]='\0'; last--;}
+      if (wordstart[last]=='r' && last>=0)
+    {wordstart[last]='\0'; last--;}
+      if (wordstart[last]=='e' && last>=0)
+    {wordstart[last]='\0'; last--;}
+      if (wordstart[last]=='é' && last>=0) /* letter with accent e + ' */
+    {wordstart[last]='\0'; last--;}
+      if (wordstart[last]==wordstart[last-1] && last>=1)
+    {wordstart[last]='\0'; last--;}
     }  /* end else */
+
+    word[0] = (unsigned char)(last+1);
   } /* end if (len > 4) */
-  return(word);
 }