1
/* Copyright (c) 2000, 2011, Oracle and/or its affiliates. All rights reserved.
3
This program is free software; you can redistribute it and/or modify
4
it under the terms of the GNU General Public License as published by
5
the Free Software Foundation; version 2 of the License.
7
This program is distributed in the hope that it will be useful,
8
but WITHOUT ANY WARRANTY; without even the implied warranty of
9
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
10
GNU General Public License for more details.
12
You should have received a copy of the GNU General Public License
13
along with this program; if not, write to the Free Software
14
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA */
16
/* Written by Sergei A. Golubchik, who has a shared copyright to this code */
19
#include "my_compare.h"
22
static CHARSET_INFO *ft_stopword_cs= NULL;
25
typedef struct st_ft_stopwords
31
static TREE *stopwords3=NULL;
33
static int FT_STOPWORD_cmp(void* cmp_arg __attribute__((unused)),
34
FT_STOPWORD *w1, FT_STOPWORD *w2)
36
return ha_compare_text(ft_stopword_cs,
37
(uchar *)w1->pos,w1->len,
38
(uchar *)w2->pos,w2->len,0,0);
41
static void FT_STOPWORD_free(FT_STOPWORD *w, TREE_FREE action,
42
void *arg __attribute__((unused)))
44
if (action == free_free)
45
my_free((void*)w->pos);
48
static int ft_add_stopword(const char *w)
52
(((sw.len= (uint) strlen(sw.pos=w)) >= ft_min_word_len) &&
53
(tree_insert(stopwords3, &sw, 0, stopwords3->custom_arg)==NULL));
56
int ft_init_stopwords()
60
if (!(stopwords3=(TREE *)my_malloc(sizeof(TREE),MYF(0))))
62
init_tree(stopwords3,0,0,sizeof(FT_STOPWORD),(qsort_cmp2)&FT_STOPWORD_cmp,
64
(ft_stopword_file ? (tree_element_free)&FT_STOPWORD_free : 0),
67
Stopword engine currently does not support tricky
68
character sets UCS2, UTF16, UTF32.
69
Use latin1 to compare stopwords in case of these character sets.
70
It's also fine to use latin1 with the built-in stopwords.
72
ft_stopword_cs= default_charset_info->mbminlen == 1 ?
73
default_charset_info : &my_charset_latin1;
80
uchar *buffer, *start, *end;
84
if (!*ft_stopword_file)
87
if ((fd=my_open(ft_stopword_file, O_RDONLY, MYF(MY_WME))) == -1)
89
len=(uint)my_seek(fd, 0L, MY_SEEK_END, MYF(0));
90
my_seek(fd, 0L, MY_SEEK_SET, MYF(0));
91
if (!(start=buffer=my_malloc(len+1, MYF(MY_WME))))
93
len=my_read(fd, buffer, len, MYF(MY_WME));
95
while (ft_simple_get_word(ft_stopword_cs, &start, end, &w, TRUE))
97
if (ft_add_stopword(my_strndup((char*) w.pos, w.len, MYF(0))))
104
my_close(fd, MYF(MY_WME));
109
/* compatibility mode: to be removed */
110
char **sws=(char **)ft_precompiled_stopwords;
114
if (ft_add_stopword(*sws))
117
ft_stopword_file="(built-in)"; /* for SHOW VARIABLES */
122
int is_stopword(char *word, uint len)
127
return tree_search(stopwords3,&sw, stopwords3->custom_arg) != NULL;
131
void ft_free_stopwords()
135
delete_tree(stopwords3); /* purecov: inspected */