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 | **************************************************************************/
|
---|
21 |
|
---|
22 | #include "sysfuncs.h"
|
---|
23 | #include "stemmer.h"
|
---|
24 |
|
---|
25 | #include "lovinstem.h"
|
---|
26 | #include "simplefrenchstem.h"
|
---|
27 | #include "unitool.h"
|
---|
28 |
|
---|
29 | #define LOVINSTEMMER 0
|
---|
30 | #define SIMPLEFRENCHSTEMMER 1
|
---|
31 |
|
---|
32 |
|
---|
33 | /* decode the utf-8 encoded unicode, casefold and then recode
|
---|
34 | * making sure the final length doesn't exceed the original
|
---|
35 | * length */
|
---|
36 | static void unicode_casefold (u_char *word) {
|
---|
37 | unsigned short out[256]; /* temp space */
|
---|
38 | int i;
|
---|
39 | int len;
|
---|
40 |
|
---|
41 | /* decode */
|
---|
42 | utf8_word_to_unicode (word, out, 255);
|
---|
43 | len = out[0];
|
---|
44 |
|
---|
45 | /* casefold and simplify-fold */
|
---|
46 | for (i=0; i<len; ++i) {
|
---|
47 | out[i+1] = unicode_tosimplified(unicode_tolower(out[i+1]));
|
---|
48 | }
|
---|
49 |
|
---|
50 | /* re-code */
|
---|
51 | unicode_to_utf8_word (out, word, word[0]+1);
|
---|
52 | }
|
---|
53 |
|
---|
54 |
|
---|
55 | int stemmernumber (u_char *stemmerdescription) {
|
---|
56 | u_char descript[MAX_STEM_DESCRIPTION_LEN];
|
---|
57 | int i;
|
---|
58 |
|
---|
59 | /* copy and case-fold the description */
|
---|
60 | for (i=0; (stemmerdescription[i] != '\0') &&
|
---|
61 | (i < MAX_STEM_DESCRIPTION_LEN-1); ++i)
|
---|
62 | descript[i] = tolower (stemmerdescription[i]);
|
---|
63 | descript[i] = '\0';
|
---|
64 |
|
---|
65 | /* map the description to its number */
|
---|
66 |
|
---|
67 | if ((strcmp ((char *) descript, "0") == 0) ||
|
---|
68 | (strcmp ((char *) descript, "english") == 0) ||
|
---|
69 | (strcmp ((char *) descript, "lovin") == 0))
|
---|
70 | return LOVINSTEMMER;
|
---|
71 |
|
---|
72 | if ((strcmp ((char *) descript, "1") == 1) ||
|
---|
73 | (strcmp ((char *) descript, "french") == 0) ||
|
---|
74 | (strcmp ((char *) descript, "simplefrench") == 0))
|
---|
75 | return SIMPLEFRENCHSTEMMER;
|
---|
76 |
|
---|
77 | return -1;
|
---|
78 | }
|
---|
79 |
|
---|
80 |
|
---|
81 |
|
---|
82 | /*
|
---|
83 | * Method 0 - Do not stem or case fold.
|
---|
84 | * Method 1 - Case fold.
|
---|
85 | * Method 2 - Stem.
|
---|
86 | * Method 3 - Case fold and stem.
|
---|
87 | *
|
---|
88 | * The stemmer number should be obtained using
|
---|
89 | * the stemmernumber function above.
|
---|
90 | */
|
---|
91 | void
|
---|
92 | stemmer (int method, int stemmer, u_char *word) {
|
---|
93 | if (method & 1) {
|
---|
94 | unicode_casefold (word);
|
---|
95 | }
|
---|
96 |
|
---|
97 | if (method & 2) {
|
---|
98 | switch (stemmer) {
|
---|
99 | case LOVINSTEMMER: lovinstem (word);
|
---|
100 | break;
|
---|
101 | case SIMPLEFRENCHSTEMMER: simplefrenchstem (word);
|
---|
102 | break;
|
---|
103 | }
|
---|
104 | }
|
---|
105 | }
|
---|