| 1 | /**************************************************************************
|
|---|
| 2 | *
|
|---|
| 3 | * frenchstem.c -- a simple french stemmer
|
|---|
| 4 | *
|
|---|
| 5 | * This program is free software; you can redistribute it and/or modify
|
|---|
| 6 | * it under the terms of the GNU General Public License as published by
|
|---|
| 7 | * the Free Software Foundation; either version 2 of the License, or
|
|---|
| 8 | * (at your option) any later version.
|
|---|
| 9 | *
|
|---|
| 10 | * This program is distributed in the hope that it will be useful,
|
|---|
| 11 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|---|
| 12 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|---|
| 13 | * GNU General Public License for more details.
|
|---|
| 14 | *
|
|---|
| 15 | * You should have received a copy of the GNU General Public License
|
|---|
| 16 | * along with this program; if not, write to the Free Software
|
|---|
| 17 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|---|
| 18 | *
|
|---|
| 19 | * $Id: frenchstem.c 29 1998-11-24 06:37:53Z rjmcnab $
|
|---|
| 20 | *
|
|---|
| 21 | **************************************************************************/
|
|---|
| 22 |
|
|---|
| 23 | #include "frenchstem.h"
|
|---|
| 24 |
|
|---|
| 25 |
|
|---|
| 26 |
|
|---|
| 27 | /* =========================================================================
|
|---|
| 28 | * Function: frenchstem
|
|---|
| 29 | * Description: a simple french stemmer
|
|---|
| 30 | * Input: a word string with the length in the first byte
|
|---|
| 31 | * Output: the stemmed word
|
|---|
| 32 | * ========================================================================= */
|
|---|
| 33 |
|
|---|
| 34 | void frenchstem (unsigned char *word) {
|
|---|
| 35 | unsigned char *wordstart = word + 1; /* points to first letter of word */
|
|---|
| 36 | int last = (int)word[0]-1; /* last points to the last character */
|
|---|
| 37 |
|
|---|
| 38 | if (last > 4) {
|
|---|
| 39 | if (wordstart[last]=='x') {
|
|---|
| 40 | if (wordstart[last-1]=='u' && wordstart[last-2]=='a') {
|
|---|
| 41 | wordstart[last-1]='l';
|
|---|
| 42 | }
|
|---|
| 43 | wordstart[last]='\0';
|
|---|
| 44 | last--;
|
|---|
| 45 |
|
|---|
| 46 | } else {
|
|---|
| 47 | if (wordstart[last]=='s' && last>=0)
|
|---|
| 48 | {wordstart[last]='\0'; last--;}
|
|---|
| 49 | if (wordstart[last]=='r' && last>=0)
|
|---|
| 50 | {wordstart[last]='\0'; last--;}
|
|---|
| 51 | if (wordstart[last]=='e' && last>=0)
|
|---|
| 52 | {wordstart[last]='\0'; last--;}
|
|---|
| 53 | if (wordstart[last]=='é' && last>=0) /* letter with accent e + ' */
|
|---|
| 54 | {wordstart[last]='\0'; last--;}
|
|---|
| 55 | if (wordstart[last]==wordstart[last-1] && last>=1)
|
|---|
| 56 | {wordstart[last]='\0'; last--;}
|
|---|
| 57 | } /* end else */
|
|---|
| 58 |
|
|---|
| 59 | word[0] = (unsigned char)(last+1);
|
|---|
| 60 | } /* end if (len > 4) */
|
|---|
| 61 | }
|
|---|
