Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

LUCENE-4199: more test fixes 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/branches/lucene4199@1358561 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2012-07-07 13:10:20 +00:00
parent 1590b5f7b8
commit 5a6a9e7f80
5 changed files with 17 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
lucene/analysis/common/src/test/org/apache/lucene/analysis/sinks/TestTeeSinkTokenFilter.java
View File

@ -18,6 +18,7 @@ package org.apache.lucene.analysis.sinks;
import java.io.IOException;
import java.io.StringReader;
import java.util.Locale;
import org.apache.lucene.analysis.*;
import org.apache.lucene.analysis.core.LowerCaseFilter;
@ -164,7 +165,7 @@ public class TestTeeSinkTokenFilter extends BaseTokenStreamTestCase {
TokenStream lowerCasing = new LowerCaseFilter(TEST_VERSION_CURRENT, source1);
String[] lowerCaseTokens = new String[tokens1.length];
for (int i = 0; i < tokens1.length; i++)
lowerCaseTokens[i] = tokens1[i].toLowerCase();
lowerCaseTokens[i] = tokens1[i].toLowerCase(Locale.ROOT);
assertTokenStreamContents(lowerCasing, lowerCaseTokens);
}
@ -180,7 +181,7 @@ public class TestTeeSinkTokenFilter extends BaseTokenStreamTestCase {
StringBuilder buffer = new StringBuilder();
System.out.println("-----Tokens: " + tokCount[k] + "-----");
for (int i = 0; i < tokCount[k]; i++) {
buffer.append(English.intToEnglish(i).toUpperCase()).append(' ');
buffer.append(English.intToEnglish(i).toUpperCase(Locale.ROOT)).append(' ');
}
//make sure we produce the same tokens
TeeSinkTokenFilter teeStream = new TeeSinkTokenFilter(new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.toString()))));

6
lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestCharArraySet.java
View File

@ -258,7 +258,7 @@ public class TestCharArraySet extends LuceneTestCase {
List<String> stopwords = Arrays.asList(TEST_STOP_WORDS);
List<String> stopwordsUpper = new ArrayList<String>();
for (String string : stopwords) {
stopwordsUpper.add(string.toUpperCase());
stopwordsUpper.add(string.toUpperCase(Locale.ROOT));
}
setIngoreCase.addAll(Arrays.asList(TEST_STOP_WORDS));
setIngoreCase.add(Integer.valueOf(1));
@ -305,7 +305,7 @@ public class TestCharArraySet extends LuceneTestCase {
List<String> stopwords = Arrays.asList(TEST_STOP_WORDS);
List<String> stopwordsUpper = new ArrayList<String>();
for (String string : stopwords) {
stopwordsUpper.add(string.toUpperCase());
stopwordsUpper.add(string.toUpperCase(Locale.ROOT));
}
setIngoreCase.addAll(Arrays.asList(TEST_STOP_WORDS));
setIngoreCase.add(Integer.valueOf(1));
@ -351,7 +351,7 @@ public class TestCharArraySet extends LuceneTestCase {
List<String> stopwords = Arrays.asList(TEST_STOP_WORDS);
List<String> stopwordsUpper = new ArrayList<String>();
for (String string : stopwords) {
stopwordsUpper.add(string.toUpperCase());
stopwordsUpper.add(string.toUpperCase(Locale.ROOT));
}
set.addAll(Arrays.asList(TEST_STOP_WORDS));

9
lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestCharTokenizers.java
View File

@ -20,6 +20,7 @@ package org.apache.lucene.analysis.util;
import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;
import java.util.Locale;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
@ -53,7 +54,7 @@ public class TestCharTokenizers extends BaseTokenStreamTestCase {
// internal buffer size is 1024 make sure we have a surrogate pair right at the border
builder.insert(1023, "\ud801\udc1c");
Tokenizer tokenizer = new LowerCaseTokenizer(TEST_VERSION_CURRENT, new StringReader(builder.toString()));
assertTokenStreamContents(tokenizer, builder.toString().toLowerCase().split(" "));
assertTokenStreamContents(tokenizer, builder.toString().toLowerCase(Locale.ROOT).split(" "));
}
/*
@ -70,7 +71,7 @@ public class TestCharTokenizers extends BaseTokenStreamTestCase {
}
builder.append("\ud801\udc1cabc");
Tokenizer tokenizer = new LowerCaseTokenizer(TEST_VERSION_CURRENT, new StringReader(builder.toString()));
assertTokenStreamContents(tokenizer, new String[] {builder.toString().toLowerCase()});
assertTokenStreamContents(tokenizer, new String[] {builder.toString().toLowerCase(Locale.ROOT)});
}
}
@ -84,7 +85,7 @@ public class TestCharTokenizers extends BaseTokenStreamTestCase {
builder.append("A");
}
Tokenizer tokenizer = new LowerCaseTokenizer(TEST_VERSION_CURRENT, new StringReader(builder.toString() + builder.toString()));
assertTokenStreamContents(tokenizer, new String[] {builder.toString().toLowerCase(), builder.toString().toLowerCase()});
assertTokenStreamContents(tokenizer, new String[] {builder.toString().toLowerCase(Locale.ROOT), builder.toString().toLowerCase(Locale.ROOT)});
}
/*
@ -98,7 +99,7 @@ public class TestCharTokenizers extends BaseTokenStreamTestCase {
}
builder.append("\ud801\udc1c");
Tokenizer tokenizer = new LowerCaseTokenizer(TEST_VERSION_CURRENT, new StringReader(builder.toString() + builder.toString()));
assertTokenStreamContents(tokenizer, new String[] {builder.toString().toLowerCase(), builder.toString().toLowerCase()});
assertTokenStreamContents(tokenizer, new String[] {builder.toString().toLowerCase(Locale.ROOT), builder.toString().toLowerCase(Locale.ROOT)});
}
// LUCENE-3642: normalize SMP->BMP and check that offsets are correct

2
lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapaneseTokenizer.java
View File

@ -607,7 +607,7 @@ public class TestJapaneseTokenizer extends BaseTokenStreamTestCase {
private void doTestBocchan(int numIterations) throws Exception {
LineNumberReader reader = new LineNumberReader(new InputStreamReader(
this.getClass().getResourceAsStream("bocchan.utf-8")));
this.getClass().getResourceAsStream("bocchan.utf-8"), "UTF-8"));
String line = reader.readLine();
reader.close();

11
lucene/core/src/test/org/apache/lucene/index/TestPayloads.java
View File

@ -43,9 +43,8 @@ public class TestPayloads extends LuceneTestCase {
// Simple tests to test the Payload class
public void testPayload() throws Exception {
byte[] testData = "This is a test!".getBytes();
BytesRef payload = new BytesRef(testData);
assertEquals("Wrong payload length.", testData.length, payload.length);
BytesRef payload = new BytesRef("This is a test!");
assertEquals("Wrong payload length.", "This is a test!".length(), payload.length);
BytesRef clone = payload.clone();
assertEquals(payload.length, clone.length);
@ -73,7 +72,7 @@ public class TestPayloads extends LuceneTestCase {
// enabled in only some documents
d.add(newTextField("f3", "This field has payloads in some docs", Field.Store.NO));
// only add payload data for field f2
analyzer.setPayloadData("f2", "somedata".getBytes(), 0, 1);
analyzer.setPayloadData("f2", "somedata".getBytes("UTF-8"), 0, 1);
writer.addDocument(d);
// flush
writer.close();
@ -96,8 +95,8 @@ public class TestPayloads extends LuceneTestCase {
d.add(newTextField("f2", "This field has payloads in all docs", Field.Store.NO));
d.add(newTextField("f3", "This field has payloads in some docs", Field.Store.NO));
// add payload data for field f2 and f3
analyzer.setPayloadData("f2", "somedata".getBytes(), 0, 1);
analyzer.setPayloadData("f3", "somedata".getBytes(), 0, 3);
analyzer.setPayloadData("f2", "somedata".getBytes("UTF-8"), 0, 1);
analyzer.setPayloadData("f3", "somedata".getBytes("UTF-8"), 0, 3);
writer.addDocument(d);
// force merge