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
|
<?xml version="1.0" encoding="utf-8"?>
<test>
<name>specials vs charset_table vs match_mode</name>
<config>
indexer
{
mem_limit = 16M
}
searchd
{
<searchd_settings/>
workers = threads
}
source src
{
type = mysql
<sql_settings/>
sql_query = SELECT * FROM test_table WHERE document_id IN (1,2,3,4)
}
index main
{
source = src
path = <data_path/>/main
charset_table = 0..9, A..Z->a..z, _, a..z, (, ), $
}
source src_wf
{
type = mysql
<sql_settings/>
sql_query = SELECT * FROM test_table WHERE document_id>4
}
index wf1
{
source = src_wf
path = <data_path/>/wf1
morphology = stem_en
charset_table = 0..9, A..Z->a..z, a..z,
wordforms = <this_test/>/wordforms.txt
}
index wf2
{
source = src_wf
path = <data_path/>/wf2
morphology = stem_en
charset_table = 0..9, A..Z->a..z, a..z, -
wordforms = <this_test/>/wordforms.txt
}
source src_wf3
{
type = mysql
<sql_settings/>
sql_query = SELECT * FROM test_wf3
}
index wf3
{
source = src_wf3
path = <data_path/>/wf3
morphology = stem_en
charset_table = -, 0..9, A..Z->a..z, _, a..z
wordforms = <this_test/>/wf3.txt
}
index rt
{
type = rt
path = <data_path/>/rt0
rt_mem_limit = 32M
rt_field = title
rt_attr_uint=gid
dict = keywords
min_prefix_len = 1
morphology = stem_en
index_exact_words = 1
}
index exact_wf
{
source = src_wf3
path = <data_path/>/exact_wf
dict = crc
min_prefix_len = 1
morphology = stem_en
index_exact_words = 1
}
source src_cht
{
type = mysql
<sql_settings/>
sql_query = SELECT 1, 'Й Ц У К Е Н Г Ш Щ З Х139Ъ' UNION SELECT 2, 'Ф Ы В А П Р О Л Д Ж Э' UNION SELECT 3, 'Я Ч С М И Т Ь Б Ю Ё' UNION SELECT 11, 'й ц у к е н г ш щ з х ъ' UNION SELECT 12, 'ф ы в а п р о л д ж э' UNION SELECT 13, 'я086ч с м и т ь б ю ё' UNION SELECT 101, 'Q W E R T Y U I O P' UNION SELECT 102, 'A S D F G H J K L' UNION SELECT 103, 'Z X C V B N_M' UNION SELECT 111, 'q w e r t y u i o p' UNION SELECT 112, 'a_s d f g h j k l' UNION SELECT 113, 'z x c v b n m'
}
index cht
{
source = src_cht
path = <data_path/>/cht
charset_table = english, _, 0..9, russian
}
</config>
<queries>
<query index='main'>google$com</query>
<query index='main' mode="any">foo(bar)</query>
<query index='main' mode="any">foo\(bar\)</query>
<query index='main' mode="extended2">google$com</query>
<query index='main' mode="extended2">foo(bar)</query>
<query index='main' mode="extended2">foo\(bar\)</query>
<query index='main' mode="extended2">"foo(bar)"</query>
<query index='main' mode="extended2">(bars all$)</query>
<query index='wf1' mode="extended2">without trouble$</query>
<query index='wf1' mode="extended2">trouble without$</query>
<query index='wf1' mode="extended2">(trouble without$)</query>
<!-- here is going regression (query 8-) when second index shares wordform from 1st index -->
<query index='wf1' mode="extended2">run</query>
<query index='wf2' mode="extended2">run</query>
<query index='wf1' mode="extended2">run\-time</query>
<query index='wf2' mode="extended2">run\-time</query>
<query index='wf1' mode="extended2">run time</query>
<query index='wf2' mode="extended2">run time</query>
<!-- charset alias -->
<query index='cht' mode="extended2">Й Ц У К Е Н Г Ш Щ З Х139Ъ</query>
<query index='cht' mode="extended2">й ц у к е н г ш щ з х ъ</query>
<query index='cht' mode="extended2">Ф Ы В А П Р О Л Д Ж Э</query>
<query index='cht' mode="extended2">Я Ч С М И Т Ь Б Ю Ё</query>
<query index='cht' mode="extended2">я086ч с м и т ь б ю ё</query>
<query index='cht' mode="extended2">Q W E R T Y U I O P</query>
<query index='cht' mode="extended2">A S D F G H J K L</query>
<query index='cht' mode="extended2">a_s d f g h j k l</query>
<query index='cht' mode="extended2">Z X C V B N_M</query>
<query index='cht' mode="extended2">z x c v b n m</query>
</queries>
<sphqueries>
<sphinxql>CALL KEYWORDS ('run-time (run time) issue', 'wf1')</sphinxql>
<sphinxql>CALL KEYWORDS ('run-time (run time) issue', 'wf2')</sphinxql>
<!-- here is going regression crash on indexing wordforms vs multi-wordforms -->
<sphinxql>SELECT * from wf3 where match ('word2word2')</sphinxql>
<!-- here is going regression crash on CALL KEYWORDS to RT index with dict keywords -->
<sphinxql>INSERT INTO rt VALUES ( 1, 'dummy', 100 )</sphinxql>
<sphinxql>CALL KEYWORDS ('runs runs* =runs', 'rt', 1)</sphinxql>
<sphinxql>CALL KEYWORDS ('runs runs* =runs', 'exact_wf', 1)</sphinxql>
</sphqueries>
<db_create>
CREATE TABLE test_table (
document_id INTEGER NOT NULL PRIMARY KEY,
title VARCHAR(255) NOT NULL )
</db_create>
<db_create>
CREATE TABLE test_wf3 (
document_id INTEGER NOT NULL PRIMARY KEY,
title VARCHAR(255) NOT NULL )
</db_create>
<db_drop>
DROP TABLE IF EXISTS test_table
</db_drop>
<db_drop>
DROP TABLE IF EXISTS test_wf3
</db_drop>
<db_insert>
INSERT INTO test_table VALUES
( 1, 'google dot com' ),
( 2, 'foo beyond all bars' ),
( 3, 'mangled google$com link' ),
( 4, 'no idea why search for foo(bar), but they do' ),
( 5, 'run-time error' ),
( 6, 'running without trouble' )
</db_insert>
<db_insert>
INSERT INTO test_wf3 VALUES
( 1, 'word2word2 word4word4' )
</db_insert>
</test>
|
