summaryrefslogtreecommitdiffstats
path: root/storage/innobase/include/fts0tokenize.h
blob: 1cddaf5bf675cff5219e321031136d804c28c6ce (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
/*****************************************************************************

Copyright (c) 2014, 2015, Oracle and/or its affiliates. All Rights Reserved.
Copyright (c) 2020, MariaDB Corporation.

This program is free software; you can redistribute it and/or modify it under
the terms of the GNU General Public License as published by the Free Software
Foundation; version 2 of the License.

This program is distributed in the hope that it will be useful, but WITHOUT
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.

You should have received a copy of the GNU General Public License along with
this program; if not, write to the Free Software Foundation, Inc.,
51 Franklin Street, Fifth Floor, Boston, MA 02110-1335 USA

*****************************************************************************/

/******************************************************************//**
@file fts/fts0tokenize.cc
Full Text Search plugin tokenizer refer to MyISAM

Created 2014/11/17 Shaohua Wang
***********************************************************************/

#include "ft_global.h"
#include "mysql/plugin_ftparser.h"
#include "m_ctype.h"

/* Macros and structs below are from ftdefs.h in MyISAM */
/** Check a char is true word */
#define true_word_char(c, ch) ((c) & (_MY_U | _MY_L | _MY_NMR) || (ch) == '_')

/** Check if a char is misc word */
#define misc_word_char(X)       0

/** Boolean search syntax */
static const char* fts_boolean_syntax = DEFAULT_FTB_SYNTAX;

#define FTB_YES   (fts_boolean_syntax[0])
#define FTB_EGAL  (fts_boolean_syntax[1])
#define FTB_NO    (fts_boolean_syntax[2])
#define FTB_INC   (fts_boolean_syntax[3])
#define FTB_DEC   (fts_boolean_syntax[4])
#define FTB_LBR   (fts_boolean_syntax[5])
#define FTB_RBR   (fts_boolean_syntax[6])
#define FTB_NEG   (fts_boolean_syntax[7])
#define FTB_TRUNC (fts_boolean_syntax[8])
#define FTB_LQUOT (fts_boolean_syntax[10])
#define FTB_RQUOT (fts_boolean_syntax[11])

/** FTS query token */
typedef struct st_ft_word {
        uchar* pos;     /*!< word start pointer */
        uint   len;     /*!< word len */
        double weight;  /*!< word weight, unused in innodb */
} FT_WORD;

/** Tokenizer for ngram referring to ft_get_word(ft_parser.c) in MyISAM.
Differences: a. code format changed; b. stopword processing removed.
@param[in]	cs	charset
@param[in,out]	start	doc start pointer
@param[in,out]	end	doc end pointer
@param[in,out]	word	token
@param[in,out]	info	token info
@retval	0	eof
@retval	1	word found
@retval	2	left bracket
@retval	3	right bracket
@retval	4	stopword found */
inline
uchar
fts_get_word(
	const CHARSET_INFO*	cs,
	uchar**			start,
	uchar*			end,
	FT_WORD*		word,
	MYSQL_FTPARSER_BOOLEAN_INFO*
				info)
{
	uchar*	doc = *start;
	int	ctype;
	uint	mwc;
	uint	length;
	int	mbl;

	info->yesno = (FTB_YES ==' ') ? 1 : (info->quot != 0);
	info->weight_adjust = info->wasign = 0;
	info->type = FT_TOKEN_EOF;

	while (doc < end) {
		for (; doc < end;
		     doc += (mbl > 0 ? mbl : (mbl < 0 ? -mbl : 1))) {
			mbl = cs->ctype(&ctype, doc, end);

			if (true_word_char(ctype, *doc)) {
				break;
			}

			if (*doc == FTB_RQUOT && info->quot) {
				*start = doc + 1;
				info->type = FT_TOKEN_RIGHT_PAREN;

				return(info->type);
			}

			if (!info->quot) {
				if (*doc == FTB_LBR
				    || *doc == FTB_RBR
				    || *doc == FTB_LQUOT) {
					/* param->prev=' '; */
					*start = doc + 1;
					if (*doc == FTB_LQUOT) {
						info->quot = (char*)1;
					}

					info->type = (*doc == FTB_RBR ?
						       FT_TOKEN_RIGHT_PAREN :
						       FT_TOKEN_LEFT_PAREN);

					return(info->type);
				}

				if (info->prev == ' ') {
					if (*doc == FTB_YES) {
						info->yesno = +1;
						continue;
					} else if (*doc == FTB_EGAL) {
						info->yesno = 0;
						continue;
					} else if (*doc == FTB_NO) {
						info->yesno = -1;
						continue;
					} else if (*doc == FTB_INC) {
						info->weight_adjust++;
						continue;
					} else if (*doc == FTB_DEC) {
						info->weight_adjust--;
						continue;
					} else if (*doc == FTB_NEG) {
						info->wasign = !info->wasign;
						continue;
					}
				}
			}

			info->prev = char(*doc);
			info->yesno = (FTB_YES == ' ') ? 1 : (info->quot != 0);
			info->weight_adjust = info->wasign = 0;
		}

		mwc = length = 0;
		for (word->pos = doc;
		     doc < end;
		     length++, doc += (mbl > 0 ? mbl : (mbl < 0 ? -mbl : 1))) {
			mbl = cs->ctype(&ctype, doc, end);

			if (true_word_char(ctype, *doc)) {
				mwc = 0;
			} else if (!misc_word_char(*doc) || mwc) {
				break;
			} else {
				mwc++;
			}
		}

		/* Be sure *prev is true_word_char. */
		info->prev = 'A';
		word->len = (uint)(doc-word->pos) - mwc;

		if ((info->trunc = (doc < end && *doc == FTB_TRUNC))) {
			doc++;
		}

		/* We don't check stopword here. */
		*start = doc;
		info->type = FT_TOKEN_WORD;

		return(info->type);
	}

	if (info->quot) {
		*start = doc;
		info->type = FT_TOKEN_RIGHT_PAREN;
	}

	return(info->type);
}