[3365] | 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 |
|
---|
| 22 | #include "sysfuncs.h"
|
---|
| 23 |
|
---|
| 24 | #include "unitool.h"
|
---|
| 25 | #include "UCArray.h"
|
---|
| 26 |
|
---|
| 27 |
|
---|
| 28 | /*
|
---|
| 29 | * This has been cleaned up by Tim Shimmin.
|
---|
| 30 | */
|
---|
| 31 |
|
---|
| 32 | /*
|
---|
| 33 | * ---NOTE---
|
---|
| 34 | *
|
---|
| 35 | * "WORD" refers to a word in the compressed text.
|
---|
| 36 | * "STEM" or "STEM_WORD" refers to a word for indexing on
|
---|
| 37 | *
|
---|
| 38 | */
|
---|
| 39 |
|
---|
| 40 | #define MAXWORDLEN 15
|
---|
| 41 | /* Maximum length in bytes of any word or non-word. Note that
|
---|
| 42 | variations to MAXWORDLEN may have dramatic effects on the rest
|
---|
| 43 | of the program, as the length and the prefix match are packed
|
---|
| 44 | together into a four bit nibble, and there is not check that
|
---|
| 45 | this is possible, i.e., leave MAXWORDLEN alone... */
|
---|
| 46 |
|
---|
| 47 | #define MAXSTEMLEN 255
|
---|
| 48 | /* Maximum length in bytes of any stem. Note that
|
---|
| 49 | variations to MAXSTEMLEN may have dramatic effects on the rest
|
---|
| 50 | of the program, , i.e., leave MAXSTEMLEN alone... */
|
---|
| 51 |
|
---|
| 52 | #define MAXNUMERIC 4
|
---|
| 53 | /* Maximum number of numeric characters permitted in a word.
|
---|
| 54 | This avoids long sequences of numbers creating just one
|
---|
| 55 | word occurrence for each number. At most 10,000 all numeric
|
---|
| 56 | words will be permitted. */
|
---|
| 57 |
|
---|
| 58 | /* [RPAP - Jan 97: Stem Index Change] */
|
---|
| 59 | #define MAXPARAMLEN 20
|
---|
| 60 | /* Maximum number of bytes to read for a parameter value for a
|
---|
| 61 | term in a query. */
|
---|
| 62 | #define WEIGHTPARAM '/'
|
---|
| 63 | #define STEMPARAM '#'
|
---|
| 64 |
|
---|
| 65 | /* [RJM 07/97: Ranked Required Terms] */
|
---|
| 66 | #define MUSTMATCHPARAM '+'
|
---|
| 67 |
|
---|
| 68 |
|
---|
| 69 | #define PESINAWORD(c) (isalnum(c) || ((c) >= 0x80 && (c) <= 0xff))
|
---|
| 70 | /* The definition of what characters are permitted in a word.
|
---|
| 71 | This macro is pessimistic, you cannot tell from a particular
|
---|
| 72 | byte above 0x80 whether it is a character or not. This function
|
---|
| 73 | is needed by various functions relating to huffman coding
|
---|
| 74 | where frequency counts need to be primed, it should not be
|
---|
| 75 | used in parsing the UTF-8 encoded input. */
|
---|
| 76 |
|
---|
| 77 | #ifdef __cplusplus
|
---|
[8692] | 78 | extern "C" {
|
---|
[3365] | 79 | #endif
|
---|
| 80 | int inaword (const u_char *here, const u_char *end);
|
---|
| 81 | /* Takes the place of the old INAWORD macro. It determines
|
---|
| 82 | whether a given place in a UTF-8 encoded Unicode string
|
---|
| 83 | is part of a word. */
|
---|
| 84 |
|
---|
[8692] | 85 | int isaspace (const u_char *here, const u_char *end);
|
---|
| 86 | /* It determines whether a given place in a UTF-8 encoded Unicode string is a unicode space. */
|
---|
[3365] | 87 |
|
---|
[8692] | 88 | u_char *skipspace(u_char *here, u_char *end);
|
---|
| 89 | /* Return a the UTF-8 encoded Unicode string with begining unicode spaces skippend. */
|
---|
| 90 |
|
---|
| 91 | #ifdef __cplusplus
|
---|
| 92 | }
|
---|
| 93 | #endif
|
---|
| 94 |
|
---|
[3365] | 95 | const unsigned char *ParseIndexWord (const unsigned char *textHere,
|
---|
| 96 | const unsigned char *textEnd,
|
---|
| 97 | UCArray &word);
|
---|
| 98 | const unsigned char *ParseIndexMGWord (const unsigned char *textHere,
|
---|
| 99 | const unsigned char *textEnd,
|
---|
| 100 | unsigned char *mgWord);
|
---|
| 101 | const unsigned char *ParseNonindexWord (const unsigned char *textHere,
|
---|
| 102 | const unsigned char *textEnd);
|
---|
| 103 |
|
---|
| 104 |
|
---|
| 105 |
|
---|
| 106 | /* =========================================================================
|
---|
| 107 | * Macro: PARSE_WORD
|
---|
| 108 | * Description:
|
---|
| 109 | * Extract a word out for compressing text
|
---|
| 110 | * Input:
|
---|
| 111 | * s_in = string start in buffer
|
---|
| 112 | * end = string end in buffer
|
---|
| 113 | * Output:
|
---|
| 114 | * Word = extracted word with length in 1st byte
|
---|
| 115 | * s_in = ptr to next character in buffer yet to be processed
|
---|
| 116 | * ========================================================================= */
|
---|
| 117 | #define PARSE_WORD(Word, s_in, end) \
|
---|
| 118 | do { \
|
---|
| 119 | register int charlength = 0; \
|
---|
| 120 | register u_char *wptr = (Word)+1; \
|
---|
| 121 | register int length = 0; \
|
---|
| 122 | register int numeric = 0; \
|
---|
| 123 | unsigned short c; \
|
---|
| 124 | \
|
---|
| 125 | charlength = parse_utf8_char((s_in),(end),&c); \
|
---|
| 126 | \
|
---|
| 127 | while (length+charlength <= MAXWORDLEN && charlength > 0 && \
|
---|
| 128 | (is_unicode_letter(c) || (is_unicode_digit(c) && \
|
---|
| 129 | ++numeric <= MAXNUMERIC))) { \
|
---|
| 130 | while (charlength-- > 0) { \
|
---|
[9613] | 131 | *wptr++ = *(s_in)++; ++length; \
|
---|
[3365] | 132 | } \
|
---|
| 133 | charlength = parse_utf8_char((s_in),(end),&c); \
|
---|
| 134 | } \
|
---|
| 135 | *(Word) = length; \
|
---|
| 136 | }while(0)
|
---|
| 137 |
|
---|
| 138 |
|
---|
| 139 |
|
---|
| 140 | /* =========================================================================
|
---|
| 141 | * Macro: PARSE_NON_WORD
|
---|
| 142 | * Description:
|
---|
| 143 | * Extract a non-word out for storing compressed text
|
---|
| 144 | * Input: as above
|
---|
| 145 | * Output: as above
|
---|
| 146 | * ========================================================================= */
|
---|
| 147 | #define PARSE_NON_WORD(Word, s_in, end) \
|
---|
| 148 | do { \
|
---|
| 149 | register int charlength = 0; \
|
---|
| 150 | register u_char *wptr = (Word)+1; \
|
---|
| 151 | register int length = 0; \
|
---|
| 152 | unsigned short c; \
|
---|
| 153 | \
|
---|
| 154 | charlength = parse_utf8_char((s_in),(end),&c); \
|
---|
| 155 | \
|
---|
| 156 | while (length+charlength <= MAXWORDLEN && charlength > 0 && \
|
---|
| 157 | !is_unicode_letdig(c)) { \
|
---|
| 158 | while (charlength-- > 0) { \
|
---|
[9613] | 159 | *wptr++ = *(s_in)++; ++length; \
|
---|
[3365] | 160 | } \
|
---|
| 161 | charlength = parse_utf8_char((s_in),(end),&c); \
|
---|
| 162 | } \
|
---|
| 163 | *(Word) = length; \
|
---|
| 164 | }while(0)
|
---|