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
|
<?xml version="1.0" encoding="utf-8"?>
<test>
<name>stemming</name>
<config>
indexer
{
mem_limit = 16M
}
searchd
{
<searchd_settings/>
workers = threads
}
source srctest
{
type = mysql
<sql_settings/>
sql_query = SELECT * FROM test_table
}
index test
{
source = srctest
path = <data_path/>/test
charset_table = -, 0..9, A..Z->a..z, a..z, U+410..U+42F->U+430..U+44F, U+430..U+44F
morphology = stem_ru, stem_en
}
index morph0
{
source = srctest
path = <data_path/>/morph0
dict = keywords
min_prefix_len = 1
}
index morph1
{
source = srctest
path = <data_path/>/morph1
dict = keywords
min_prefix_len = 1
morphology = stem_en
}
source src_ru
{
type = mysql
<sql_settings/>
sql_query = SELECT *, 11 as idd FROM test_ru
sql_query_pre = SET NAMES utf8
sql_attr_uint = idd
}
index test_ru
{
source = src_ru
path = <data_path/>/test_ru
dict = keywords
morphology = stem_ru
charset_table = 0..9, A..Z->a..z, _, ., -, a..z, U+410..U+42F->U+430..U+44F, U+430..U+44F, U+0401->U+0435, U+0451->U+0435
}
index rt
{
type = rt
path = <data_path/>/rt
rt_field = title
rt_attr_uint = idd
dict = keywords
morphology = stem_ru
charset_table = 0..9, A..Z->a..z, _, ., -, a..z, U+410..U+42F->U+430..U+44F, U+430..U+44F, U+0401->U+0435, U+0451->U+0435
}
source src_stop
{
type = mysql
<sql_settings/>
sql_query = SELECT 1, 11 as idd, 'running far' as text UNION SELECT 2, 22 as idd, 'runs me' as text UNION SELECT 3, 33 as idd, 'rufus my friend' as text
sql_query_pre = SET NAMES utf8
sql_attr_uint = idd
}
index test_stop
{
source = src_stop
path = <data_path/>/test_stop
dict = keywords
morphology = stem_en
charset_table = 0..9, A..Z->a..z, _, ., -, a..z
stopwords = <this_test/>/stopwords.txt
min_prefix_len = 1
enable_star = 1
index_exact_words = 1
}
index test_stop1
{
source = src_stop
path = <data_path/>/test_stop1
dict = crc
morphology = stem_en
charset_table = 0..9, A..Z->a..z, _, ., -, a..z
stopwords = <this_test/>/stopwords.txt
min_prefix_len = 1
enable_star = 1
index_exact_words = 1
}
source src_metaphone
{
type = mysql
<sql_settings/>
sql_field_string = name
sql_query = SELECT 1 as id, '加藤郁子アーティスト片山耕アーティストピューロキッズアーティスト金子知恵アーティスト井上かなえアーティスト他知恵アーティスト井上かなえアーティスト他' as name
}
index test_metaphone
{
source = src_metaphone
path = <data_path/>/test_metaphone
morphology = metaphone
charset_table = U+21..U+29, U+30..U+999, U+1000..U+FFFF
}
</config>
<queries>
<!-- long query after proximity length was not properly 0-terminated, and caused overlong token to be passed to stemmer, and crash -->
<query mode="extended2" index="test morph0 morph1 test_ru rt test_stop test_stop1">"one two"~3 three</query>
<!--here is going regression dict=keywords got broken by morphology-->
<query mode="extended2" index="morph1">=running</query>
<query mode="extended2" index="morph1">=run</query>
<query mode="extended2" index="morph1">running*</query>
<query mode="extended2" index="morph1">runnin*</query>
<query mode="extended2" index="morph1">run*</query>
<query mode="extended2" index="morph1">ru*</query>
<query mode="extended2" index="morph1">=runnin*</query>
<query mode="extended2" index="morph1">runnings*</query>
<query mode="extended2" index="morph1">runnin</query>
<query mode="extended2" index="morph1">running</query>
<query mode="extended2" index="morph1">run</query>
<query mode="extended2" index="morph0">=running</query>
<query mode="extended2" index="morph0">=run</query>
<query mode="extended2" index="morph0">running*</query>
<query mode="extended2" index="morph0">runnin*</query>
<query mode="extended2" index="morph0">run*</query>
<query mode="extended2" index="morph0">ru*</query>
<query mode="extended2" index="morph0">=runnin*</query>
<query mode="extended2" index="morph0">runnings*</query>
<query mode="extended2" index="morph0">runnin</query>
<query mode="extended2" index="morph0">running</query>
<query mode="extended2" index="morph0">run</query>
<!-- regression stemmed word vs dict=keyword -->
<query mode="extended2" index="test_ru">ордеру АВАВ</query>
<!-- regression stemmed exact form from stoplist vs dict=keyword prefix -->
<query mode="extended2" index="test_stop">run*</query>
<query mode="extended2" index="test_stop">ru*</query>
<query mode="extended2" index="test_stop">=runs</query>
<query mode="extended2" index="test_stop">runs</query>
<query mode="extended2" index="test_stop1">run*</query>
<query mode="extended2" index="test_stop1">ru*</query>
<query mode="extended2" index="test_stop1">=runs</query>
<query mode="extended2" index="test_stop1">runs</query>
</queries>
<sphqueries>
<!-- here is going regression 2byte vs 2byte + sbc -->
<sphinxql>CALL KEYWORDS ('то-тический', 'test')</sphinxql>
<sphinxql>CALL KEYWORDS ('тоЫтический', 'test')</sphinxql>
<!-- regression stemmed word vs dict=keyword -->
<sphinxql>INSERT INTO rt (id, idd, title) VALUES ( 1, 1, 'testing that' ),( 2, 1, 'ордеру АВАВ/А85/007' )</sphinxql>
<sphinxql>SELECT * FROM test_ru WHERE MATCH('ордеру АВАВ')</sphinxql>
<sphinxql>show meta</sphinxql>
<sphinxql>SELECT * FROM rt WHERE MATCH('ордеру АВАВ')</sphinxql>
<sphinxql>show meta</sphinxql>
</sphqueries>
<db_create>
CREATE TABLE `test_table`
(
`document_id` int(11) NOT NULL default '0',
`body` varchar(255) NOT NULL default ''
)
</db_create>
<db_drop>
DROP TABLE IF EXISTS `test_table`
</db_drop>
<db_insert>
INSERT INTO `test_table` VALUES
( 1, 'and nothing else matters' ),
( 2, 'running into trouble' )
</db_insert>
<db_create>
CREATE TABLE `test_ru`
(
`document_id` int(11) NOT NULL default '0',
`body` varchar(255) CHARACTER SET UTF8 NOT NULL default ''
)
</db_create>
<db_drop>DROP TABLE IF EXISTS `test_ru`</db_drop>
<db_insert>SET NAMES utf8</db_insert>
<db_insert>INSERT INTO `test_ru` (document_id, body) VALUES ( 1, 'testing that' ), ( 2, 'ордеру АВАВ/А85/007' )</db_insert>
</test>
|
