[3365] | 1 | /**************************************************************************
|
---|
| 2 | *
|
---|
| 3 | * stemmer.h -- 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 | #ifndef STEMMER_H
|
---|
| 23 | #define STEMMER_H
|
---|
| 24 |
|
---|
[13477] | 25 | /* [RPAP - Jan 97: Stem Index Change] */
|
---|
| 26 | /* [JFG - Mar 06: Accent folding patch] */
|
---|
| 27 | enum stemMethods {
|
---|
| 28 | STEM_None = 0,
|
---|
| 29 | STEM_CaseFolding = 0x1,
|
---|
| 30 | STEM_Stemming = 0x2,
|
---|
| 31 | STEM_AccentFolding = 0x4,
|
---|
| 32 | };
|
---|
[3365] | 33 |
|
---|
[13477] | 34 | /* This is for the QueryParser */
|
---|
| 35 | #define CHAR_FLAG_STEM_CaseFold 'i' // ignore case
|
---|
| 36 | #define CHAR_FLAG_STEM_NoCaseFold 'c' // case sensitive
|
---|
| 37 | #define CHAR_FLAG_STEM_Stemming 's' // stem words
|
---|
| 38 | #define CHAR_FLAG_STEM_NoStemming 'u' // do not stem words
|
---|
| 39 | #define CHAR_FLAG_STEM_AccentFold 'f' // accent fold
|
---|
| 40 | #define CHAR_FLAG_STEM_NoAccentFold 'a' // do no accent folding
|
---|
| 41 | #define CHAR_FLAG_STEM_Validator "icsufa" // all of the above
|
---|
| 42 |
|
---|
| 43 |
|
---|
| 44 | #define STEM_MIN 1
|
---|
| 45 | #define STEM_MAX (STEM_CaseFolding | STEM_Stemming | STEM_AccentFolding)
|
---|
| 46 | #define STEM_PARTIAL_MATCH (STEM_MAX+1)
|
---|
| 47 | #define STEM_INVALID (STEM_MAX+2)
|
---|
| 48 |
|
---|
[3365] | 49 | #define STEMMER_MASK 3
|
---|
| 50 | #define MAX_STEM_DESCRIPTION_LEN 16
|
---|
| 51 |
|
---|
| 52 | /* stemmernumber will return the stemmer for
|
---|
| 53 | * a description of the stemmer. Stemmer descriptions
|
---|
| 54 | * are not case sensitive. Valid descriptions are:
|
---|
| 55 | *
|
---|
| 56 | * 'English'
|
---|
| 57 | * 'Lovin'
|
---|
| 58 | * 'French'
|
---|
| 59 | * 'SimpleFrench'
|
---|
| 60 | *
|
---|
| 61 | * More than one description might result in the same
|
---|
| 62 | * stemmer number (for example, for stemming 'English'
|
---|
| 63 | * we currently use the 'Lovin' stemmer).
|
---|
| 64 | *
|
---|
| 65 | * stemmerdescription is a normal C, null-terminated,
|
---|
| 66 | * string.
|
---|
| 67 | *
|
---|
| 68 | * stemmernumber will return -1 if it doesn't know the
|
---|
| 69 | * stemmer description.
|
---|
| 70 | */
|
---|
[13477] | 71 | int mgpp_stemmernumber (unsigned char *stemmerdescription);
|
---|
[3365] | 72 |
|
---|
| 73 | /*
|
---|
| 74 | * Method 0 - Do not stem or case fold.
|
---|
| 75 | * Method 1 - Case fold.
|
---|
| 76 | * Method 2 - Stem.
|
---|
| 77 | * Method 3 - Case fold and stem.
|
---|
[13477] | 78 | * Method 4 - Accent fold
|
---|
| 79 | * Method 5 - Case fold and accent fold
|
---|
| 80 | * Method 6 - Stem and accent fold
|
---|
| 81 | * Method 7 - Case fold, stem and accent fold
|
---|
[3365] | 82 | * The stemmer number should be obtained using function
|
---|
| 83 | * stemmernumber above.
|
---|
| 84 | */
|
---|
| 85 | #ifdef __cplusplus
|
---|
| 86 | extern "C"
|
---|
| 87 | #endif
|
---|
[13477] | 88 | void mgpp_stemmer (int method, int stemmer, unsigned char * word);
|
---|
[3365] | 89 |
|
---|
| 90 | #endif
|
---|