fix unicode violations in test, test relies upon how *invalid* utf8 is converted

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1152089 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2011-07-29 03:29:09 +00:00
parent 963bce23d1
commit 15544c3088
1 changed files with 9 additions and 14 deletions

View File

@ -20,6 +20,7 @@ package org.apache.lucene.index;
import java.io.IOException; import java.io.IOException;
import java.io.Reader; import java.io.Reader;
import java.io.UnsupportedEncodingException; import java.io.UnsupportedEncodingException;
import java.nio.charset.Charset;
import java.util.ArrayList; import java.util.ArrayList;
import java.util.HashMap; import java.util.HashMap;
import java.util.List; import java.util.List;
@ -347,8 +348,13 @@ public class TestPayloads extends LuceneTestCase {
} }
static final Charset utf8 = Charset.forName("UTF-8");
private void generateRandomData(byte[] data) { private void generateRandomData(byte[] data) {
random.nextBytes(data); // this test needs the random data to be valid unicode
String s = _TestUtil.randomFixedByteLengthUnicodeString(random, data.length);
byte b[] = s.getBytes(utf8);
assert b.length == data.length;
System.arraycopy(b, 0, data, 0, b.length);
} }
private byte[] generateRandomData(int n) { private byte[] generateRandomData(int n) {
@ -526,7 +532,7 @@ public class TestPayloads extends LuceneTestCase {
for (int i = 0; i < freq; i++) { for (int i = 0; i < freq; i++) {
tp.nextPosition(); tp.nextPosition();
final BytesRef payload = tp.getPayload(); final BytesRef payload = tp.getPayload();
assertEquals(termText, pool.bytesToString(payload.bytes, payload.offset, payload.length)); assertEquals(termText, payload.utf8ToString());
} }
} }
} }
@ -548,7 +554,7 @@ public class TestPayloads extends LuceneTestCase {
this.pool = pool; this.pool = pool;
payload = pool.get(); payload = pool.get();
generateRandomData(payload); generateRandomData(payload);
term = pool.bytesToString(payload, 0, payload.length); term = new String(payload, 0, payload.length, utf8);
first = true; first = true;
payloadAtt = addAttribute(PayloadAttribute.class); payloadAtt = addAttribute(PayloadAttribute.class);
termAtt = addAttribute(CharTermAttribute.class); termAtt = addAttribute(CharTermAttribute.class);
@ -580,17 +586,6 @@ public class TestPayloads extends LuceneTestCase {
pool.add(new byte[size]); pool.add(new byte[size]);
} }
} }
static String bytesToString(byte[] bytes, int start, int length) {
String s = new String(bytes, start, length);
BytesRef utf8Result = new BytesRef(10);
UnicodeUtil.UTF16toUTF8(s, 0, s.length(), utf8Result);
try {
return new String(utf8Result.bytes, 0, utf8Result.length, "UTF-8");
} catch (UnsupportedEncodingException uee) {
return null;
}
}
synchronized byte[] get() { synchronized byte[] get() {
return pool.remove(0); return pool.remove(0);