| 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 | **************************************************************************/
|
|---|
| 21 | #ifndef H_WORDS
|
|---|
| 22 | #define H_WORDS
|
|---|
| 23 |
|
|---|
| 24 |
|
|---|
| 25 | #include "sysfuncs.h"
|
|---|
| 26 |
|
|---|
| 27 | #include "unitool.h"
|
|---|
| 28 | #include "UCArray.h"
|
|---|
| 29 |
|
|---|
| 30 |
|
|---|
| 31 | /*
|
|---|
| 32 | * This has been cleaned up by Tim Shimmin.
|
|---|
| 33 | */
|
|---|
| 34 |
|
|---|
| 35 | /*
|
|---|
| 36 | * ---NOTE---
|
|---|
| 37 | *
|
|---|
| 38 | * "WORD" refers to a word in the compressed text.
|
|---|
| 39 | * "STEM" or "STEM_WORD" refers to a word for indexing on
|
|---|
| 40 | *
|
|---|
| 41 | */
|
|---|
| 42 |
|
|---|
| 43 | #define MAXWORDLEN 15
|
|---|
| 44 | /* Maximum length in bytes of any word or non-word. Note that
|
|---|
| 45 | variations to MAXWORDLEN may have dramatic effects on the rest
|
|---|
| 46 | of the program, as the length and the prefix match are packed
|
|---|
| 47 | together into a four bit nibble, and there is not check that
|
|---|
| 48 | this is possible, i.e., leave MAXWORDLEN alone... */
|
|---|
| 49 |
|
|---|
| 50 | #define MAXSTEMLEN 255
|
|---|
| 51 | /* Maximum length in bytes of any stem. Note that
|
|---|
| 52 | variations to MAXSTEMLEN may have dramatic effects on the rest
|
|---|
| 53 | of the program, , i.e., leave MAXSTEMLEN alone... */
|
|---|
| 54 |
|
|---|
| 55 | //#define MAXNUMERIC 4
|
|---|
| 56 | /* Maximum number of numeric characters permitted in a word.
|
|---|
| 57 | This avoids long sequences of numbers creating just one
|
|---|
| 58 | word occurrence for each number. At most 10,000 all numeric
|
|---|
| 59 | words will be permitted. */
|
|---|
| 60 |
|
|---|
| 61 | extern int MAXNUMERIC;
|
|---|
| 62 |
|
|---|
| 63 | /* [RPAP - Jan 97: Stem Index Change] */
|
|---|
| 64 | #define MAXPARAMLEN 20
|
|---|
| 65 | /* Maximum number of bytes to read for a parameter value for a
|
|---|
| 66 | term in a query. */
|
|---|
| 67 | #define WEIGHTPARAM '/'
|
|---|
| 68 | #define STEMPARAM '#'
|
|---|
| 69 |
|
|---|
| 70 | /* [RJM 07/97: Ranked Required Terms] */
|
|---|
| 71 | #define MUSTMATCHPARAM '+'
|
|---|
| 72 |
|
|---|
| 73 |
|
|---|
| 74 | #define PESINAWORD(c) (isalnum(c) || ((c) >= 0x80 && (c) <= 0xff))
|
|---|
| 75 | /* The definition of what characters are permitted in a word.
|
|---|
| 76 | This macro is pessimistic, you cannot tell from a particular
|
|---|
| 77 | byte above 0x80 whether it is a character or not. This function
|
|---|
| 78 | is needed by various functions relating to huffman coding
|
|---|
| 79 | where frequency counts need to be primed, it should not be
|
|---|
| 80 | used in parsing the UTF-8 encoded input. */
|
|---|
| 81 |
|
|---|
| 82 | #ifdef __cplusplus
|
|---|
| 83 | extern "C" {
|
|---|
| 84 | #endif
|
|---|
| 85 | int inaword_mgpp (const u_char *here, const u_char *end);
|
|---|
| 86 | /* Takes the place of the old INAWORD macro. It determines
|
|---|
| 87 | whether a given place in a UTF-8 encoded Unicode string
|
|---|
| 88 | is part of a word. */
|
|---|
| 89 |
|
|---|
| 90 | int isaspace_mgpp (const u_char *here, const u_char *end);
|
|---|
| 91 | /* It determines whether a given place in a UTF-8 encoded Unicode string is a unicode space. */
|
|---|
| 92 |
|
|---|
| 93 | u_char *skipspace_mgpp(u_char *here, u_char *end);
|
|---|
| 94 | /* Return a the UTF-8 encoded Unicode string with begining unicode spaces skippend. */
|
|---|
| 95 |
|
|---|
| 96 | #ifdef __cplusplus
|
|---|
| 97 | }
|
|---|
| 98 | #endif
|
|---|
| 99 |
|
|---|
| 100 | const unsigned char *ParseIndexWord (const unsigned char *textHere,
|
|---|
| 101 | const unsigned char *textEnd,
|
|---|
| 102 | UCArray &word);
|
|---|
| 103 | const unsigned char *ParseIndexMGWord (const unsigned char *textHere,
|
|---|
| 104 | const unsigned char *textEnd,
|
|---|
| 105 | unsigned char *mgWord);
|
|---|
| 106 | const unsigned char *ParseNonindexWord (const unsigned char *textHere,
|
|---|
| 107 | const unsigned char *textEnd);
|
|---|
| 108 |
|
|---|
| 109 |
|
|---|
| 110 |
|
|---|
| 111 | /* =========================================================================
|
|---|
| 112 | * Macro: PARSE_WORD
|
|---|
| 113 | * Description:
|
|---|
| 114 | * Extract a word out for compressing text
|
|---|
| 115 | * Input:
|
|---|
| 116 | * s_in = string start in buffer
|
|---|
| 117 | * end = string end in buffer
|
|---|
| 118 | * Output:
|
|---|
| 119 | * Word = extracted word with length in 1st byte
|
|---|
| 120 | * s_in = ptr to next character in buffer yet to be processed
|
|---|
| 121 | * ========================================================================= */
|
|---|
| 122 | #define PARSE_WORD(Word, s_in, end) \
|
|---|
| 123 | do { \
|
|---|
| 124 | register int charlength = 0; \
|
|---|
| 125 | register u_char *wptr = (Word)+1; \
|
|---|
| 126 | register int length = 0; \
|
|---|
| 127 | register int numeric = 0; \
|
|---|
| 128 | unsigned short c; \
|
|---|
| 129 | \
|
|---|
| 130 | charlength = parse_utf8_char((s_in),(end),&c); \
|
|---|
| 131 | \
|
|---|
| 132 | while (length+charlength <= MAXWORDLEN && charlength > 0 && \
|
|---|
| 133 | (is_unicode_letter(c) || (is_unicode_digit(c) && \
|
|---|
| 134 | ++numeric <= MAXNUMERIC))) { \
|
|---|
| 135 | while (charlength-- > 0) { \
|
|---|
| 136 | *wptr++ = *(s_in)++; ++length; \
|
|---|
| 137 | } \
|
|---|
| 138 | charlength = parse_utf8_char((s_in),(end),&c); \
|
|---|
| 139 | } \
|
|---|
| 140 | *(Word) = length; \
|
|---|
| 141 | }while(0)
|
|---|
| 142 |
|
|---|
| 143 |
|
|---|
| 144 |
|
|---|
| 145 | /* =========================================================================
|
|---|
| 146 | * Macro: PARSE_NON_WORD
|
|---|
| 147 | * Description:
|
|---|
| 148 | * Extract a non-word out for storing compressed text
|
|---|
| 149 | * Input: as above
|
|---|
| 150 | * Output: as above
|
|---|
| 151 | * ========================================================================= */
|
|---|
| 152 | #define PARSE_NON_WORD(Word, s_in, end) \
|
|---|
| 153 | do { \
|
|---|
| 154 | register int charlength = 0; \
|
|---|
| 155 | register u_char *wptr = (Word)+1; \
|
|---|
| 156 | register int length = 0; \
|
|---|
| 157 | unsigned short c; \
|
|---|
| 158 | \
|
|---|
| 159 | charlength = parse_utf8_char((s_in),(end),&c); \
|
|---|
| 160 | \
|
|---|
| 161 | while (length+charlength <= MAXWORDLEN && charlength > 0 && \
|
|---|
| 162 | !is_unicode_letdig(c)) { \
|
|---|
| 163 | while (charlength-- > 0) { \
|
|---|
| 164 | *wptr++ = *(s_in)++; ++length; \
|
|---|
| 165 | } \
|
|---|
| 166 | charlength = parse_utf8_char((s_in),(end),&c); \
|
|---|
| 167 | } \
|
|---|
| 168 | *(Word) = length; \
|
|---|
| 169 | }while(0)
|
|---|
| 170 |
|
|---|
| 171 | #endif
|
|---|
