File: test.xml

package info (click to toggle)
sphinxsearch 2.2.11-8
  • links: PTS, VCS
  • area: main
  • in suites: bookworm, sid, trixie
  • size: 25,720 kB
  • sloc: cpp: 102,259; xml: 85,608; sh: 9,259; php: 3,790; ansic: 3,158; yacc: 1,969; java: 1,336; ruby: 1,289; python: 1,062; pascal: 912; perl: 381; lex: 275; makefile: 150; sql: 77; cs: 35
file content (196 lines) | stat: -rw-r--r-- 7,037 bytes parent folder | download | duplicates (4)
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
<?xml version="1.0" encoding="utf-8"?>

<test>
<name>snippets vs SPZ</name>

<requires>
</requires>

<config>
searchd
{
	<searchd_settings/>
}

source test
{
	type = mysql
	<sql_settings/>
	sql_query = SELECT 1, 'text';
}

index test
{
	source			= test
	path			= <data_path/>/test

	html_strip		= 1
	index_sp		= 1
	index_zones		= zone*
	min_infix_len	= 1
}

index multiform
{
	source			= test
	path			= <data_path/>/multiform

	wordforms		= <this_test/>/multiwordorms.txt
	min_infix_len	= 1
}

</config>

<db_insert>select 1;</db_insert>

<custom_test><![CDATA[

$data = array();

// pass 0
$data[] = 'ZONE:zoneA these';
$data[] = 'ZONE:zoneB these';
$data[] = 'ZONE:(zoneA, zoneB) th*';
$data[] = 'ZONE:(zoneA, zoneB) are';
$data[] = 'ZONE:zoneZZ a* cool$';
// pass 5
$data[] = 'ZONE:zoneZZ to* a*';


$results = array();
$opts = array ( 'passage_boundary'=>'zone', 'limit'=>0 );
$docs = array('<zoneZZ><zoneA> these words </zoneA><zoneB> and these to </zoneB> are cool </zoneZZ>');
$pass = 0;

$results[] = '[pass] (query/result=q/r) (fast path=1/0) (query_mode=1/0)';

foreach ( array(0, 1) as $qmode )
{
	$opts['query_mode'] = $qmode;
	foreach ( $data as $q )
	{
		$opts['limit_passages'] = 10;
		$results["[$pass]q"] = $q;
		$res = $client->BuildExcerpts($docs, 'test', $q, $opts );
		$results["[$pass]r 0 $qmode"] = ( count($res)>0 ? $res[0] : '');
		$opts['limit_passages'] = 0;
		$res = $client->BuildExcerpts($docs, 'test', $q, $opts );
		$results["[$pass]r 1 $qmode"] = ( count($res)>0 ? $res[0] : '' );
		$pass += 1;
	}
}

$results[] = $client->BuildExcerpts(array('small doc', 'one more'), 'multiform', 'crash on tokenizer from another doc', array ('query_mode'=>0) );

// another regression - zone transformed by stripper in result set
$opts = array ( 'query_mode'=>1, 'limit_words'=>6 );

$opts['html_strip_mode'] = 'index';
$res =  $client->BuildExcerpts($docs, 'test', 'these | are',  $opts);
$res['html_strip_mode'] = $opts['html_strip_mode'];
$results[] = $res;	
	
$opts['html_strip_mode'] = 'strip';
$res= $client->BuildExcerpts($docs, 'test', 'these | are',  $opts);
$res['html_strip_mode'] = $opts['html_strip_mode'];
$results[] = $res;	

$opts['html_strip_mode'] = 'index';
$opts['passage_boundary'] = 'zone';
$res =  $client->BuildExcerpts($docs, 'test', 'these | are',  $opts);
$res['html_strip_mode'] = $opts['html_strip_mode'];
$res['passage_boundary'] = $opts['passage_boundary'];
$results[] = $res;	
	
$opts['html_strip_mode'] = 'strip';
$res= $client->BuildExcerpts($docs, 'test', 'these',  $opts);
$res['html_strip_mode'] = $opts['html_strip_mode'];
$res['passage_boundary'] = $opts['passage_boundary'];
$results[] = $res;	

// regression retain vs SPZ
$docs = array(
'<zoneZZ><zoneA> these words </zoneA><zoneB> and these to </zoneB> are cool </zoneZZ>',
'<zoneZZ><zoneA> these words <TR> and these to </zoneA> are cool </zoneZZ>'
);
$opts = array ( 'limit'=>0, 'html_strip_mode'=>'retain', 'query_mode'=>1 );

$res =  $client->BuildExcerpts($docs, 'test', 'ZONE:zoneZZ these',  $opts);
$res['zone'] = 'zoneZZ';
$results[] = $res;

$res =  $client->BuildExcerpts($docs, 'test', 'ZONE:zoneB these',  $opts);
$res['zone'] = 'ZoneB';
$results[] = $res;

$res =  $client->BuildExcerpts($docs, 'test', 'and PARAGRAPH words',  $opts);
$res['boundary'] = 'paragraph';
$results[] = $res;

$results[] = $client->BuildExcerpts(array('tokenizer filter crash at lc'), 'multiform', 'crash at lc',
	array ('query_mode'=>1, 'html_strip_mode'=>'retain', 'limit'=>0) );

$results[] = $client->BuildExcerpts(array('dog dummy! as the house nearby the dog'), 'test', 'the. dog!? as',
	array ('query_mode'=>1, 'html_strip_mode'=>'retain', 'limit'=>0) );
	
// regression SPZ vs passage_boundary

$opts = array ( 'query_mode'=>1, 'allow_empty'=>1 );

$opts['limit'] = 0;
$res =  $client->BuildExcerpts($docs, 'test', 'ZONE:zoneB these',  $opts);
$res['ZoneB'] = 'fast-path';
$results[] = $res;

$opts['limit'] = 30;
$res =  $client->BuildExcerpts($docs, 'test', 'ZONE:zoneB these',  $opts);
$res['ZoneB'] = 'old-path';
$results[] = $res;

$opts['limit'] = 0;
$res =  $client->BuildExcerpts($docs, 'test', 'and PARAGRAPH words',  $opts);
$res['PARAGRAPH'] = 'fast-path';
$results[] = $res;

$opts['limit'] = 30;
$res =  $client->BuildExcerpts($docs, 'test', 'and PARAGRAPH words',  $opts);
$res['PARAGRAPH'] = 'old-path';
$results[] = $res;

// regression fast-path vs passage_boundary
$opts['limit'] = 0;
$opts['passage_boundary'] = 'paragraph';
$res =  $client->BuildExcerpts($docs, 'test', 'and words',  $opts);
$res['passage_boundary'] = 'paragraph';
$results[] = $res;

$opts['passage_boundary'] = 'zone';
$res =  $client->BuildExcerpts($docs, 'test', 'and words',  $opts);
$res['passage_boundary'] = 'zone';
$results[] = $res;

	
// regression head SPZ overgrow + non fast path SPZ

$docs = array ( 'Ultra long stuff is going here then store sales, which were going before of store closes. Same store sales for the quarter increased as ultra long dust was here since univerce was born. ' );
$results[] = $client->BuildExcerpts ( $docs, 'test', '(store SENTENCE closes)', array ( 'query_mode'=>1, 'passage_boundary'=>'sentence', 'limit'=>90 ) );
$results[] = $client->BuildExcerpts ( $docs, 'test', '(store SENTENCE closes)', array ( 'query_mode'=>1, 'passage_boundary'=>'sentence', 'limit'=>0 ) );

$docs = array ( 'Ultra long stuff is going here then store sales, which were going before of store closes. Same store sales for the quarter increased as ultra long dust was here since univerce was born. And again store closes as usual ' );
$results[] = $client->BuildExcerpts ( $docs, 'test', '(store SENTENCE closes)', array ( 'query_mode'=>1, 'passage_boundary'=>'sentence', 'limit'=>90 ) );
$results[] = $client->BuildExcerpts ( $docs, 'test', '(store SENTENCE closes)', array ( 'query_mode'=>1, 'passage_boundary'=>'sentence', 'limit'=>0 ) );

// regression fast path SPZ vs html_strip_mode = retain
$docs = array ( 'Ultra long stuff is going here then store sales, which were going before of store closes. Same store sales for the quarter increased as ultra long dust was here since univerce was born. And again store closes as usual ' );
$results[] = $client->BuildExcerpts ( $docs, 'test', '(store SENTENCE closes)', array ( 'query_mode'=>1, 'html_strip_mode'=>'retain', 'limit'=>0 ) );
$results[] = $client->BuildExcerpts ( $docs, 'test', '(store PARAGRAPH closes)', array ( 'query_mode'=>1, 'html_strip_mode'=>'retain', 'limit'=>0 ) );

$docs = array ( 'Ultra long stuff is going here then store sales, which were going before of store closes. <p> Same store sales for the quarter increased as ultra long dust was here since univerce was born. <p> And again store closes as usual ' );
$results[] = $client->BuildExcerpts ( $docs, 'test', '(store SENTENCE closes)', array ( 'query_mode'=>1, 'html_strip_mode'=>'retain', 'limit'=>0 ) );
$results[] = $client->BuildExcerpts ( $docs, 'test', '(store PARAGRAPH closes)', array ( 'query_mode'=>1, 'html_strip_mode'=>'retain', 'limit'=>0 ) );


]]></custom_test>


</test>