blob: d93216db6976871c9df956150f2cdb2fca19e4bd (
plain)
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
|
package morfologik.stemming;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.nio.ByteBuffer;
import org.junit.BeforeClass;
import org.junit.Test;
import com.carrotsearch.junitbenchmarks.AbstractBenchmark;
import com.carrotsearch.junitbenchmarks.BenchmarkOptions;
/**
* Simple performance micro-benchmarks.
*/
@BenchmarkOptions(callgc = false, warmupRounds = 5, benchmarkRounds = 10)
public class PerformanceTest extends AbstractBenchmark {
/* Guard against escape analysis and HotSpot opts. */
public volatile int guard;
/* Test data. */
static final int sequences = 100000;
static final String[] testWords = new String[sequences];
static final PolishStemmer stemmer = new PolishStemmer();
/**
* Prepare test data.
*/
@BeforeClass
public static void prepare() throws UnsupportedEncodingException
{
final Dictionary dict = Dictionary.getForLanguage("pl");
int i = 0;
for (ByteBuffer sequence : dict.fsa) {
testWords[i] = new String(sequence.array(), 0,
sequence.remaining(), dict.metadata.getEncoding());
testWords[i] = testWords[i].substring(0, testWords[i]
.indexOf(dict.metadata.getSeparator()));
i++;
if (i == testWords.length)
break;
}
}
@Test
public void traversal_100000() throws IOException {
final Dictionary dict = Dictionary.getForLanguage("pl");
int max = sequences;
int guard = 0;
for (ByteBuffer sequence : dict.fsa) {
guard += sequence.remaining();
if (--max == 0)
break;
}
this.guard = guard;
}
@Test
public void stemming_100000() throws IOException {
int guard = 0;
for (String word : testWords) {
for (WordData dta : stemmer.lookup(word))
{
guard += dta.getStem().length();
guard += dta.getTag().length();
}
}
this.guard = guard;
}
}
|