1 /* Copyright (c) 2000, 2021, Oracle and/or its affiliates.
2
3 This program is free software; you can redistribute it and/or modify
4 it under the terms of the GNU General Public License, version 2.0,
5 as published by the Free Software Foundation.
6
7 This program is also distributed with certain software (including
8 but not limited to OpenSSL) that is licensed under separate terms,
9 as designated in a particular file or component or in included license
10 documentation. The authors of MySQL hereby grant you an additional
11 permission to link the program and your derivative works with the
12 separately licensed software that they have included with MySQL.
13
14 This program is distributed in the hope that it will be useful,
15 but WITHOUT ANY WARRANTY; without even the implied warranty of
16 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
17 GNU General Public License, version 2.0, for more details.
18
19 You should have received a copy of the GNU General Public License
20 along with this program; if not, write to the Free Software
21 Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA */
22
23 /* Written by Sergei A. Golubchik, who has a shared copyright to this code */
24
25 #include "ftdefs.h"
26 #include "my_compare.h"
27
28
29 static CHARSET_INFO *ft_stopword_cs= NULL;
30
31
32 typedef struct st_ft_stopwords
33 {
34 const char * pos;
35 uint len;
36 } FT_STOPWORD;
37
38 static TREE *stopwords3=NULL;
39
FT_STOPWORD_cmp(void * cmp_arg MY_ATTRIBUTE ((unused)),FT_STOPWORD * w1,FT_STOPWORD * w2)40 static int FT_STOPWORD_cmp(void* cmp_arg MY_ATTRIBUTE((unused)),
41 FT_STOPWORD *w1, FT_STOPWORD *w2)
42 {
43 return ha_compare_text(ft_stopword_cs,
44 (uchar *)w1->pos,w1->len,
45 (uchar *)w2->pos,w2->len,0,0);
46 }
47
FT_STOPWORD_free(FT_STOPWORD * w,TREE_FREE action,void * arg MY_ATTRIBUTE ((unused)))48 static void FT_STOPWORD_free(FT_STOPWORD *w, TREE_FREE action,
49 void *arg MY_ATTRIBUTE((unused)))
50 {
51 if (action == free_free)
52 my_free((void*)w->pos);
53 }
54
ft_add_stopword(const char * w)55 static int ft_add_stopword(const char *w)
56 {
57 FT_STOPWORD sw;
58 return !w ||
59 (((sw.len= (uint) strlen(sw.pos=w)) >= ft_min_word_len) &&
60 (tree_insert(stopwords3, &sw, 0, stopwords3->custom_arg)==NULL));
61 }
62
ft_init_stopwords()63 int ft_init_stopwords()
64 {
65 if (!stopwords3)
66 {
67 if (!(stopwords3=(TREE *)my_malloc(mi_key_memory_ft_stopwords,
68 sizeof(TREE),MYF(0))))
69 return -1;
70 init_tree(stopwords3,0,0,sizeof(FT_STOPWORD),(qsort_cmp2)&FT_STOPWORD_cmp,
71 0,
72 (ft_stopword_file ? (tree_element_free)&FT_STOPWORD_free : 0),
73 NULL);
74 /*
75 Stopword engine currently does not support tricky
76 character sets UCS2, UTF16, UTF32.
77 Use latin1 to compare stopwords in case of these character sets.
78 It's also fine to use latin1 with the built-in stopwords.
79 */
80 ft_stopword_cs= default_charset_info->mbminlen == 1 ?
81 default_charset_info : &my_charset_latin1;
82 }
83
84 if (ft_stopword_file)
85 {
86 File fd;
87 size_t len;
88 uchar *buffer, *start, *end;
89 FT_WORD w;
90 int error=-1;
91
92 if (!*ft_stopword_file)
93 return 0;
94
95 if ((fd=my_open(ft_stopword_file, O_RDONLY, MYF(MY_WME))) == -1)
96 return -1;
97 len= (size_t)my_seek(fd, 0L, MY_SEEK_END, MYF(0));
98 my_seek(fd, 0L, MY_SEEK_SET, MYF(0));
99 if (!(start=buffer=my_malloc(mi_key_memory_ft_stopwords,
100 len+1, MYF(MY_WME))))
101 goto err0;
102 len=my_read(fd, buffer, len, MYF(MY_WME));
103 end=start+len;
104 while (ft_simple_get_word(ft_stopword_cs, &start, end, &w, TRUE))
105 {
106 if (ft_add_stopword(my_strndup(mi_key_memory_ft_stopwords,
107 (char*) w.pos, w.len, MYF(0))))
108 goto err1;
109 }
110 error=0;
111 err1:
112 my_free(buffer);
113 err0:
114 my_close(fd, MYF(MY_WME));
115 return error;
116 }
117 else
118 {
119 /* compatibility mode: to be removed */
120 char **sws=(char **)ft_precompiled_stopwords;
121
122 for (;*sws;sws++)
123 {
124 if (ft_add_stopword(*sws))
125 return -1;
126 }
127 ft_stopword_file="(built-in)"; /* for SHOW VARIABLES */
128 }
129 return 0;
130 }
131
is_stopword(char * word,uint len)132 int is_stopword(char *word, uint len)
133 {
134 FT_STOPWORD sw;
135 sw.pos=word;
136 sw.len=len;
137 return tree_search(stopwords3,&sw, stopwords3->custom_arg) != NULL;
138 }
139
140
ft_free_stopwords()141 void ft_free_stopwords()
142 {
143 if (stopwords3)
144 {
145 delete_tree(stopwords3); /* purecov: inspected */
146 my_free(stopwords3);
147 stopwords3=0;
148 }
149 ft_stopword_file= 0;
150 }
151