| 1 | /**************************************************************************
|
|---|
| 2 | *
|
|---|
| 3 | * words.h -- Macros for parsing out words from the source text
|
|---|
| 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: words.h 13 1998-11-17 09:36:00Z rjmcnab $
|
|---|
| 21 | *
|
|---|
| 22 | **************************************************************************/
|
|---|
| 23 |
|
|---|
| 24 | #include "sysfuncs.h"
|
|---|
| 25 |
|
|---|
| 26 | /*
|
|---|
| 27 | * This has been cleaned up by Tim Shimmin.
|
|---|
| 28 | */
|
|---|
| 29 |
|
|---|
| 30 | /*
|
|---|
| 31 | * ---NOTE---
|
|---|
| 32 | *
|
|---|
| 33 | * "WORD" refers to a word in the compressed text.
|
|---|
| 34 | * "STEM" or "STEM_WORD" refers to a word for indexing on
|
|---|
| 35 | *
|
|---|
| 36 | */
|
|---|
| 37 |
|
|---|
| 38 | #define MAXWORDLEN 15
|
|---|
| 39 | /* Maximum length in bytes of any word or non-word. Note that
|
|---|
| 40 | variations to MAXWORDLEN may have dramatic effects on the rest
|
|---|
| 41 | of the program, as the length and the prefix match are packed
|
|---|
| 42 | together into a four bit nibble, and there is not check that
|
|---|
| 43 | this is possible, i.e., leave MAXWORDLEN alone... */
|
|---|
| 44 | #define MAXSTEMLEN 255
|
|---|
| 45 | /* Maximum length in bytes of any stem. Note that
|
|---|
| 46 | variations to MAXSTEMLEN may have dramatic effects on the rest
|
|---|
| 47 | of the program, , i.e., leave MAXSTEMLEN alone... */
|
|---|
| 48 | #define MAXNUMERIC 4
|
|---|
| 49 | /* Maximum number of numeric characters permitted in a word.
|
|---|
| 50 | This avoids long sequences of numbers creating just one
|
|---|
| 51 | word occurrence for each number. At most 10,000 all numeric
|
|---|
| 52 | words will be permitted. */
|
|---|
| 53 |
|
|---|
| 54 | /* [RPAP - Jan 97: Stem Index Change] */
|
|---|
| 55 | #define MAXPARAMLEN 20
|
|---|
| 56 | /* Maximum number of bytes to read for a parameter value for a
|
|---|
| 57 | term in a query. */
|
|---|
| 58 | #define WEIGHTPARAM '/'
|
|---|
| 59 | #define STEMPARAM '#'
|
|---|
| 60 |
|
|---|
| 61 | /* [RJM 07/97: Ranked Required Terms] */
|
|---|
| 62 | #define MUSTMATCHPARAM '+'
|
|---|
| 63 |
|
|---|
| 64 | /* [RJM 03/98: Extended ascii] */
|
|---|
| 65 | /* Note that this extension was based on some code by */
|
|---|
| 66 | /* Nelson H.F. Beebe */
|
|---|
| 67 | static u_char c__;
|
|---|
| 68 | #define isextletter(c) (c__ = (c), \
|
|---|
| 69 | ((c__ >= 65 && c__ <= 90) || \
|
|---|
| 70 | (c__ >= 97 && c__ <= 122) || \
|
|---|
| 71 | (c__ >= 192 && c__ <= 214) || \
|
|---|
| 72 | (c__ >= 216 && c__ <= 246) || \
|
|---|
| 73 | (c__ >= 248 && c__ <= 255)))
|
|---|
| 74 |
|
|---|
| 75 | #define INAWORD(c) (isalnum(c) || isextletter(c))
|
|---|
| 76 | /* The definition of what characters are permitted in a word
|
|---|
| 77 | */
|
|---|
| 78 |
|
|---|
| 79 | #define INNUMBER(c) (isdigit(c)?1:0)
|
|---|
| 80 |
|
|---|
| 81 | /* =========================================================================
|
|---|
| 82 | * Macro: PARSE_WORD
|
|---|
| 83 | * Description:
|
|---|
| 84 | * Extract a word out for compressing text
|
|---|
| 85 | * Input:
|
|---|
| 86 | * s_in = string start in buffer
|
|---|
| 87 | * end = string end in buffer
|
|---|
| 88 | * Output:
|
|---|
| 89 | * Word = extracted word with length in 1st byte
|
|---|
| 90 | * s_in = ptr to next character in buffer yet to be processed
|
|---|
| 91 | * ========================================================================= */
|
|---|
| 92 | #define PARSE_WORD(Word, s_in, end) \
|
|---|
| 93 | do { \
|
|---|
| 94 | register u_char *wptr = (Word)+1; \
|
|---|
| 95 | register int length = 0; \
|
|---|
| 96 | register int c = *(s_in); \
|
|---|
| 97 | register int numeric = 0; \
|
|---|
| 98 | \
|
|---|
| 99 | while( length < MAXWORDLEN && INAWORD(c) && (s_in)<=(end)) \
|
|---|
| 100 | { \
|
|---|
| 101 | if ((numeric += INNUMBER(c)) > MAXNUMERIC) \
|
|---|
| 102 | break; \
|
|---|
| 103 | *wptr++ = c; \
|
|---|
| 104 | length++; \
|
|---|
| 105 | c = *++(s_in); \
|
|---|
| 106 | } \
|
|---|
| 107 | *(Word) = length; \
|
|---|
| 108 | }while(0)
|
|---|
| 109 |
|
|---|
| 110 | /* =========================================================================
|
|---|
| 111 | * Macro: PARSE_NON_WORD
|
|---|
| 112 | * Description:
|
|---|
| 113 | * Extract a non-word out for storing compressed text
|
|---|
| 114 | * Input: as above
|
|---|
| 115 | * Output: as above
|
|---|
| 116 | * ========================================================================= */
|
|---|
| 117 | #define PARSE_NON_WORD(Word, s_in, end) \
|
|---|
| 118 | do { \
|
|---|
| 119 | register u_char *wptr = (Word)+1; \
|
|---|
| 120 | register int length = 0; \
|
|---|
| 121 | register int c = *(s_in); \
|
|---|
| 122 | \
|
|---|
| 123 | while( length < MAXWORDLEN && !INAWORD(c) && (s_in)<=(end) ) \
|
|---|
| 124 | { \
|
|---|
| 125 | *wptr++ = c; \
|
|---|
| 126 | length++; \
|
|---|
| 127 | c = *++(s_in); \
|
|---|
| 128 | } \
|
|---|
| 129 | *(Word) = length; \
|
|---|
| 130 | }while(0)
|
|---|
| 131 |
|
|---|
| 132 | /* =========================================================================
|
|---|
| 133 | * Macro: PARSE_STEM_WORD
|
|---|
| 134 | * Description:
|
|---|
| 135 | * Extracts out Word.
|
|---|
| 136 | * Input:
|
|---|
| 137 | * s_in points to 1st letter in buffer to test
|
|---|
| 138 | * end points to last letter in buffer
|
|---|
| 139 | * Output:
|
|---|
| 140 | * s_in is modified to move to next word
|
|---|
| 141 | * Returns Word filled in with length in 1st byte.
|
|---|
| 142 | * ========================================================================= */
|
|---|
| 143 | #define PARSE_STEM_WORD(Word, s_in, end) \
|
|---|
| 144 | do \
|
|---|
| 145 | { \
|
|---|
| 146 | register u_char *wptr = (Word)+1; \
|
|---|
| 147 | register int length = 0; \
|
|---|
| 148 | register int c = *(s_in); \
|
|---|
| 149 | register int numeric = 0; \
|
|---|
| 150 | \
|
|---|
| 151 | while ( length < MAXSTEMLEN && INAWORD(c) && (s_in)<=(end)) \
|
|---|
| 152 | { \
|
|---|
| 153 | if ((numeric += INNUMBER(c)) > MAXNUMERIC) \
|
|---|
| 154 | break; \
|
|---|
| 155 | *wptr++ = c; \
|
|---|
| 156 | length++; \
|
|---|
| 157 | c = *++(s_in); \
|
|---|
| 158 | } \
|
|---|
| 159 | *(Word) = length; \
|
|---|
| 160 | }while(0)
|
|---|
| 161 |
|
|---|
| 162 | /* =========================================================================
|
|---|
| 163 | * Macro: PARSE_NON_STEM_WORD
|
|---|
| 164 | * Description:
|
|---|
| 165 | * Eat up non-word. Do not store non-word.
|
|---|
| 166 | * It is not needed in index only in text !
|
|---|
| 167 | *
|
|---|
| 168 | * Input: as above but no Word needed
|
|---|
| 169 | * Output: as above
|
|---|
| 170 | * ========================================================================= */
|
|---|
| 171 | #define PARSE_NON_STEM_WORD(s_in, end) \
|
|---|
| 172 | do \
|
|---|
| 173 | { \
|
|---|
| 174 | while (!INAWORD(*(s_in)) && (s_in)<=(end)) \
|
|---|
| 175 | (s_in)++; \
|
|---|
| 176 | }while(0)
|
|---|
| 177 |
|
|---|
| 178 | /* =========================================================================
|
|---|
| 179 | * Macro: PARSE_NON_STEM_WORD_OR_SGML_TAG
|
|---|
| 180 | * Description:
|
|---|
| 181 | * Like PARSE_NON_STEM_WORD but also eats up SGML tags
|
|---|
| 182 | * Input: as above
|
|---|
| 183 | * Output: as above
|
|---|
| 184 | * ========================================================================= */
|
|---|
| 185 | #define PARSE_NON_STEM_WORD_OR_SGML_TAG(s_in, end) \
|
|---|
| 186 | do \
|
|---|
| 187 | { \
|
|---|
| 188 | register int c = *(s_in); \
|
|---|
| 189 | \
|
|---|
| 190 | while (!INAWORD(c) && (s_in)<=(end)) \
|
|---|
| 191 | { \
|
|---|
| 192 | if (c == '<') \
|
|---|
| 193 | { \
|
|---|
| 194 | while (c != '>' && (s_in)<=(end)) \
|
|---|
| 195 | c = *++(s_in); \
|
|---|
| 196 | } \
|
|---|
| 197 | if ((s_in)<=(end)) \
|
|---|
| 198 | c = *++(s_in); \
|
|---|
| 199 | } \
|
|---|
| 200 | }while(0)
|
|---|
| 201 |
|
|---|
| 202 | /* =========================================================================
|
|---|
| 203 | * Macro: PARSE_OPT_TERM_PARAM [RPAP - Jan 97: Stem Index Change]
|
|---|
| 204 | * Description:
|
|---|
| 205 | * Extracts out optional paramater for query term.
|
|---|
| 206 | * Needed only in parsing the query line !
|
|---|
| 207 |
|
|---|
| 208 | *
|
|---|
| 209 | * Input: as above but no Word needed
|
|---|
| 210 | * Output: as above
|
|---|
| 211 | * ========================================================================= */
|
|---|
| 212 | #define PARSE_OPT_TERM_PARAM(Param, type, s_in, end) \
|
|---|
| 213 | do \
|
|---|
| 214 | { \
|
|---|
| 215 | register u_char *wptr = (Param); \
|
|---|
| 216 | register int length = 0; \
|
|---|
| 217 | register int c = *(s_in); \
|
|---|
| 218 | \
|
|---|
| 219 | if (c == WEIGHTPARAM || c == STEMPARAM) \
|
|---|
| 220 | { \
|
|---|
| 221 | type = c; \
|
|---|
| 222 | c = *++(s_in); \
|
|---|
| 223 | while( length < MAXPARAMLEN && INNUMBER(c) && (s_in)<=(end)) \
|
|---|
| 224 | { \
|
|---|
| 225 | *wptr++ = c; \
|
|---|
| 226 | length++; \
|
|---|
| 227 | c = *++(s_in); \
|
|---|
| 228 | } \
|
|---|
| 229 | *wptr = '\0'; \
|
|---|
| 230 | for (; INNUMBER(c) && (s_in)<=(end); c = *++(s_in)) \
|
|---|
| 231 | ; \
|
|---|
| 232 | } \
|
|---|
| 233 | }while(0)
|
|---|
| 234 |
|
|---|
| 235 | /* =========================================================================
|
|---|
| 236 | * Macro: PARSE_RANKED_NON_STEM_WORD [RJM 07/97: Ranked Required Terms]
|
|---|
| 237 | * Description:
|
|---|
| 238 | * Eat up non-word. Do not store non-word.
|
|---|
| 239 | * If come across a match requirement store it in require_match
|
|---|
| 240 | * It is not needed in index only in text !
|
|---|
| 241 | *
|
|---|
| 242 | * Input: as above
|
|---|
| 243 | * Output: the requirement mode for the next term. -1=must not match,
|
|---|
| 244 | * 0=optional match, 1=must match
|
|---|
| 245 | * ========================================================================= */
|
|---|
| 246 | #define PARSE_RANKED_NON_STEM_WORD(require_match, s_in, end) \
|
|---|
| 247 | do { \
|
|---|
| 248 | (require_match) = 0; \
|
|---|
| 249 | while (!INAWORD(*(s_in)) && (s_in)<=(end)) { \
|
|---|
| 250 | if (*(s_in) == MUSTMATCHPARAM) { \
|
|---|
| 251 | (require_match) = 1; \
|
|---|
| 252 | } \
|
|---|
| 253 | (s_in)++; \
|
|---|
| 254 | } \
|
|---|
| 255 | } while (0)
|
|---|
