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
|
---|
78 | extern "C"
|
---|
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 |
|
---|
85 |
|
---|
86 | const unsigned char *ParseIndexWord (const unsigned char *textHere,
|
---|
87 | const unsigned char *textEnd,
|
---|
88 | UCArray &word);
|
---|
89 | const unsigned char *ParseIndexMGWord (const unsigned char *textHere,
|
---|
90 | const unsigned char *textEnd,
|
---|
91 | unsigned char *mgWord);
|
---|
92 | const unsigned char *ParseNonindexWord (const unsigned char *textHere,
|
---|
93 | const unsigned char *textEnd);
|
---|
94 |
|
---|
95 |
|
---|
96 |
|
---|
97 | /* =========================================================================
|
---|
98 | * Macro: PARSE_WORD
|
---|
99 | * Description:
|
---|
100 | * Extract a word out for compressing text
|
---|
101 | * Input:
|
---|
102 | * s_in = string start in buffer
|
---|
103 | * end = string end in buffer
|
---|
104 | * Output:
|
---|
105 | * Word = extracted word with length in 1st byte
|
---|
106 | * s_in = ptr to next character in buffer yet to be processed
|
---|
107 | * ========================================================================= */
|
---|
108 | #define PARSE_WORD(Word, s_in, end) \
|
---|
109 | do { \
|
---|
110 | register int charlength = 0; \
|
---|
111 | register u_char *wptr = (Word)+1; \
|
---|
112 | register int length = 0; \
|
---|
113 | register int numeric = 0; \
|
---|
114 | unsigned short c; \
|
---|
115 | \
|
---|
116 | charlength = parse_utf8_char((s_in),(end),&c); \
|
---|
117 | \
|
---|
118 | while (length+charlength <= MAXWORDLEN && charlength > 0 && \
|
---|
119 | (is_unicode_letter(c) || (is_unicode_digit(c) && \
|
---|
120 | ++numeric <= MAXNUMERIC))) { \
|
---|
121 | while (charlength-- > 0) { \
|
---|
122 | *wptr++ = *(s_in)++; length++; \
|
---|
123 | } \
|
---|
124 | charlength = parse_utf8_char((s_in),(end),&c); \
|
---|
125 | } \
|
---|
126 | *(Word) = length; \
|
---|
127 | }while(0)
|
---|
128 |
|
---|
129 |
|
---|
130 |
|
---|
131 | /* =========================================================================
|
---|
132 | * Macro: PARSE_NON_WORD
|
---|
133 | * Description:
|
---|
134 | * Extract a non-word out for storing compressed text
|
---|
135 | * Input: as above
|
---|
136 | * Output: as above
|
---|
137 | * ========================================================================= */
|
---|
138 | #define PARSE_NON_WORD(Word, s_in, end) \
|
---|
139 | do { \
|
---|
140 | register int charlength = 0; \
|
---|
141 | register u_char *wptr = (Word)+1; \
|
---|
142 | register int length = 0; \
|
---|
143 | unsigned short c; \
|
---|
144 | \
|
---|
145 | charlength = parse_utf8_char((s_in),(end),&c); \
|
---|
146 | \
|
---|
147 | while (length+charlength <= MAXWORDLEN && charlength > 0 && \
|
---|
148 | !is_unicode_letdig(c)) { \
|
---|
149 | while (charlength-- > 0) { \
|
---|
150 | *wptr++ = *(s_in)++; length++; \
|
---|
151 | } \
|
---|
152 | charlength = parse_utf8_char((s_in),(end),&c); \
|
---|
153 | } \
|
---|
154 | *(Word) = length; \
|
---|
155 | }while(0)
|
---|