| 1 | /**************************************************************************
|
|---|
| 2 | *
|
|---|
| 3 | * stemmer.cpp -- The stemmer/case folder
|
|---|
| 4 | * Copyright (C) 1994 Neil Sharman
|
|---|
| 5 | *
|
|---|
| 6 | * This program is free software; you can redistribute it and/or modify
|
|---|
| 7 | * it under the terms of the GNU General Public License as published by
|
|---|
| 8 | * the Free Software Foundation; either version 2 of the License, or
|
|---|
| 9 | * (at your option) any later version.
|
|---|
| 10 | *
|
|---|
| 11 | * This program is distributed in the hope that it will be useful,
|
|---|
| 12 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|---|
| 13 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|---|
| 14 | * GNU General Public License for more details.
|
|---|
| 15 | *
|
|---|
| 16 | * You should have received a copy of the GNU General Public License
|
|---|
| 17 | * along with this program; if not, write to the Free Software
|
|---|
| 18 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|---|
| 19 | *
|
|---|
| 20 | * $Id: stemmer.cpp 856 2000-01-14 02:26:25Z sjboddie $
|
|---|
| 21 | *
|
|---|
| 22 | **************************************************************************/
|
|---|
| 23 |
|
|---|
| 24 | #include "sysfuncs.h"
|
|---|
| 25 | #include "stemmer.h"
|
|---|
| 26 |
|
|---|
| 27 | #include "lovinstem.h"
|
|---|
| 28 | #include "simplefrenchstem.h"
|
|---|
| 29 | #include "unitool.h"
|
|---|
| 30 |
|
|---|
| 31 | /*
|
|---|
| 32 | $Log$
|
|---|
| 33 | Revision 1.1 2000/01/14 02:26:22 sjboddie
|
|---|
| 34 | Rodgers new C++ mg
|
|---|
| 35 |
|
|---|
| 36 | Revision 1.1 1999/10/11 02:58:34 cs025
|
|---|
| 37 | Base install of MG-PP
|
|---|
| 38 |
|
|---|
| 39 | Revision 1.1 1999/08/10 21:18:23 sjboddie
|
|---|
| 40 | renamed mg-1.3d directory mg
|
|---|
| 41 |
|
|---|
| 42 | Revision 1.3 1998/12/17 09:12:54 rjmcnab
|
|---|
| 43 |
|
|---|
| 44 | Altered mg to process utf-8 encoded Unicode. The main changes
|
|---|
| 45 | are in the parsing of the input, the casefolding, and the stemming.
|
|---|
| 46 |
|
|---|
| 47 | Revision 1.2 1998/11/25 07:55:51 rjmcnab
|
|---|
| 48 |
|
|---|
| 49 | Modified mg to that you can specify the stemmer you want
|
|---|
| 50 | to use via a command line option. You specify it to
|
|---|
| 51 | mg_passes during the build process. The number of the
|
|---|
| 52 | stemmer that you used is stored within the inverted
|
|---|
| 53 | dictionary header and the stemmed dictionary header so
|
|---|
| 54 | the correct stemmer is used in later stages of building
|
|---|
| 55 | and querying.
|
|---|
| 56 |
|
|---|
| 57 | Revision 1.1 1998/11/17 09:35:42 rjmcnab
|
|---|
| 58 | *** empty log message ***
|
|---|
| 59 |
|
|---|
| 60 | * Revision 1.3 1994/10/20 03:57:05 tes
|
|---|
| 61 | * I have rewritten the boolean query optimiser and abstracted out the
|
|---|
| 62 | * components of the boolean query.
|
|---|
| 63 | *
|
|---|
| 64 | * Revision 1.2 1994/09/20 04:42:10 tes
|
|---|
| 65 | * For version 1.1
|
|---|
| 66 | *
|
|---|
| 67 | */
|
|---|
| 68 |
|
|---|
| 69 |
|
|---|
| 70 | #define LOVINSTEMMER 0
|
|---|
| 71 | #define SIMPLEFRENCHSTEMMER 1
|
|---|
| 72 |
|
|---|
| 73 |
|
|---|
| 74 | /* decode the utf-8 encoded unicode, casefold and then recode
|
|---|
| 75 | * making sure the final length doesn't exceed the original
|
|---|
| 76 | * length */
|
|---|
| 77 | static void unicode_casefold (u_char *word) {
|
|---|
| 78 | unsigned short out[256]; /* temp space */
|
|---|
| 79 | int i;
|
|---|
| 80 | int len;
|
|---|
| 81 |
|
|---|
| 82 | /* decode */
|
|---|
| 83 | utf8_word_to_unicode (word, out, 255);
|
|---|
| 84 | len = out[0];
|
|---|
| 85 |
|
|---|
| 86 | /* casefold and simplify-fold */
|
|---|
| 87 | for (i=0; i<len; i++) {
|
|---|
| 88 | out[i+1] = unicode_tosimplified(unicode_tolower(out[i+1]));
|
|---|
| 89 | }
|
|---|
| 90 |
|
|---|
| 91 | /* re-code */
|
|---|
| 92 | unicode_to_utf8_word (out, word, word[0]+1);
|
|---|
| 93 | }
|
|---|
| 94 |
|
|---|
| 95 |
|
|---|
| 96 | int stemmernumber (u_char *stemmerdescription) {
|
|---|
| 97 | u_char descript[MAX_STEM_DESCRIPTION_LEN];
|
|---|
| 98 | int i;
|
|---|
| 99 |
|
|---|
| 100 | /* copy and case-fold the description */
|
|---|
| 101 | for (i=0; (stemmerdescription[i] != '\0') &&
|
|---|
| 102 | (i < MAX_STEM_DESCRIPTION_LEN-1); i++)
|
|---|
| 103 | descript[i] = tolower (stemmerdescription[i]);
|
|---|
| 104 | descript[i] = '\0';
|
|---|
| 105 |
|
|---|
| 106 | /* map the description to its number */
|
|---|
| 107 |
|
|---|
| 108 | if ((strcmp ((char *) descript, "0") == 0) ||
|
|---|
| 109 | (strcmp ((char *) descript, "english") == 0) ||
|
|---|
| 110 | (strcmp ((char *) descript, "lovin") == 0))
|
|---|
| 111 | return LOVINSTEMMER;
|
|---|
| 112 |
|
|---|
| 113 | if ((strcmp ((char *) descript, "1") == 1) ||
|
|---|
| 114 | (strcmp ((char *) descript, "french") == 0) ||
|
|---|
| 115 | (strcmp ((char *) descript, "simplefrench") == 0))
|
|---|
| 116 | return SIMPLEFRENCHSTEMMER;
|
|---|
| 117 |
|
|---|
| 118 | return -1;
|
|---|
| 119 | }
|
|---|
| 120 |
|
|---|
| 121 |
|
|---|
| 122 |
|
|---|
| 123 | /*
|
|---|
| 124 | * Method 0 - Do not stem or case fold.
|
|---|
| 125 | * Method 1 - Case fold.
|
|---|
| 126 | * Method 2 - Stem.
|
|---|
| 127 | * Method 3 - Case fold and stem.
|
|---|
| 128 | *
|
|---|
| 129 | * The stemmer number should be obtained using
|
|---|
| 130 | * the stemmernumber function above.
|
|---|
| 131 | */
|
|---|
| 132 | void
|
|---|
| 133 | stemmer (int method, int stemmer, u_char *word) {
|
|---|
| 134 | if (method & 1) {
|
|---|
| 135 | unicode_casefold (word);
|
|---|
| 136 | }
|
|---|
| 137 |
|
|---|
| 138 | if (method & 2) {
|
|---|
| 139 | switch (stemmer) {
|
|---|
| 140 | case LOVINSTEMMER: lovinstem (word);
|
|---|
| 141 | break;
|
|---|
| 142 | case SIMPLEFRENCHSTEMMER: simplefrenchstem (word);
|
|---|
| 143 | break;
|
|---|
| 144 | }
|
|---|
| 145 | }
|
|---|
| 146 | }
|
|---|
