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
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
|
<?xml version="1.0" encoding="utf-8"?>
<test>
<name>keywords dictionary vs expansion limit</name>
<config>
indexer
{
mem_limit = 16M
}
searchd
{
<searchd_settings/>
<dynamic>
<variant>expansion_limit = 0</variant>
<variant>expansion_limit = 3</variant>
<variant>expansion_limit = 2</variant>
</dynamic>
workers = threads
}
source test
{
type = mysql
<sql_settings/>
sql_query = select * from test_table
sql_attr_uint = gid
}
index test
{
source = test
path = <data_path/>/test
dict = keywords
min_prefix_len = 2
}
index rt
{
type = rt
path = <data_path/>/rt
docinfo = extern
rt_field = data
rt_attr_uint = idd
dict = keywords
min_prefix_len = 1
}
source plain_prefix
{
type = mysql
<sql_settings/>
sql_query_pre = SET NAMES utf8
sql_query = select 1000 as id, 1 as gid, 'Москва родимая' as text
sql_attr_uint = gid
}
index plain_prefix
{
source = plain_prefix
path = <data_path/>/plain_prefix
dict = keywords
min_prefix_len = 1
}
index rt_prefix
{
type = rt
path = <data_path/>/rt_prefix
docinfo = extern
rt_field = data
rt_attr_uint = idd
dict = keywords
min_prefix_len = 1
}
source plain_substring
{
type = mysql
<sql_settings/>
sql_query = select 1 id, 1 gid, '12345' as text
sql_attr_uint = gid
}
index plain_sub_prefix
{
source = plain_substring
path = <data_path/>/plain_sub_prefix
min_prefix_len = 2
max_substring_len = 3
dict = crc
}
index plain_sub_infix
{
source = plain_substring
path = <data_path/>/plain_sub_infix
min_infix_len = 2
max_substring_len = 3
dict = crc
}
source kw_infix
{
type = mysql
<sql_settings/>
sql_query = SELECT 1, '1' title, 100 as idd
sql_attr_uint = idd
}
index kw_infix
{
source = kw_infix
path = <data_path/>/kw_infix
docinfo = extern
min_infix_len = 3
dict = keywords
}
source kw_infix_morph
{
type = mysql
<sql_settings/>
sql_query = SELECT 1, 'running star' title, 100 as idd UNION SELECT 2, 'run off', 100 as idd
sql_attr_uint = idd
}
index kw_infix_morph
{
source = kw_infix_morph
path = <data_path/>/kw_infix_morph
docinfo = extern
min_infix_len = 1
dict = keywords
morphology = stem_en
}
source plain_prefix_limit
{
type = mysql
<sql_settings/>
sql_query_pre = SET NAMES utf8
sql_query = select 1000 as id, 1 as gid, 'hello two world' as text
sql_attr_uint = gid
}
index plain_prefix_limit
{
source = plain_prefix_limit
path = <data_path/>/plain_prefix_limit
dict = keywords
min_prefix_len = 4
}
index rt_prefix_limit
{
type = rt
path = <data_path/>/rt_prefix_limit
docinfo = extern
rt_field = data
rt_attr_uint = idd
dict = keywords
min_prefix_len = 4
}
</config>
<db_create>
create table test_table
(
id int not null,
gid int not null,
title varchar(255) not null
);
</db_create>
<db_drop>drop table if exists test_table;</db_drop>
<db_insert>insert into test_table values ( 1, 1, 'funny place.' );</db_insert>
<db_insert>insert into test_table values ( 2, 1, 'is it function?' );</db_insert>
<db_insert>insert into test_table values ( 3, 1, 'functional lang. quite funny.' );</db_insert>
<db_insert>insert into test_table values ( 4, 1, 'functic sequence.' );</db_insert>
<db_insert>insert into test_table values ( 5, 1, 'fun place. funny place.' );</db_insert>
<db_insert>insert into test_table values ( 6, 1, 'its function.' );</db_insert>
<db_insert>insert into test_table values ( 7, 1, 'functional is not place.' );</db_insert>
<db_insert>insert into test_table values ( 8, 1, 'functic is not place.' );</db_insert>
<queries>
<query index="test" mode="extended2">fu*</query>
<query index="test" mode="extended2">func*</query>
</queries>
<sphqueries>
<sphinxql>insert into rt values ( 1, 'the test is going there', 11 )</sphinxql>
<sphinxql>insert into rt values ( 2, 'a sojmething is going here', 12 )</sphinxql>
<sphinxql>insert into rt values ( 3, 'testing is going not here', 13 )</sphinxql>
<sphinxql>select * from rt where match ( 't*' )</sphinxql>
<sphinxql>show meta</sphinxql>
<!-- regression prefix vs utf-8 codepoint -->
<sphinxql>insert into rt_prefix values ( 1001, 'Москва ква', 23 )</sphinxql>
<sphinxql>select * from plain_prefix where match ( 'Мос*' )</sphinxql>
<sphinxql>select * from rt_prefix where match ( 'Мос*' )</sphinxql>
<sphinxql>select * from plain_sub_prefix where match('1*')</sphinxql>
<sphinxql>select * from plain_sub_prefix where match('12*')</sphinxql>
<sphinxql>select * from plain_sub_prefix where match('123*')</sphinxql>
<sphinxql>select * from plain_sub_prefix where match('1234*')</sphinxql>
<sphinxql>select * from plain_sub_infix where match('*5')</sphinxql>
<sphinxql>select * from plain_sub_infix where match('*45')</sphinxql>
<sphinxql>select * from plain_sub_infix where match('*345')</sphinxql>
<sphinxql>select * from plain_sub_infix where match('*2345')</sphinxql>
<!--regression no infix collected at dict=keywords -->
<sphinxql>select * from kw_infix where match('1')</sphinxql>
<!--regression exact form vs infix -->
<sphinxql>select * from kw_infix_morph where match('r*')</sphinxql>
<!--regression min_prefix_len at plain vs rt -->
<sphinxql>insert into rt_prefix_limit values ( 1000, 'hello two world', 23 )</sphinxql>
<sphinxql>select * from plain_prefix_limit where match('hello two* world')</sphinxql>
<sphinxql>show meta</sphinxql>
<sphinxql>select * from rt_prefix_limit where match('hello two* world')</sphinxql>
<sphinxql>show meta</sphinxql>
</sphqueries>
</test>
|
