You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ni...@apache.org on 2015/08/20 11:42:41 UTC
svn commit: r1696743 - in
/tika/trunk/tika-core/src/test/java/org/apache/tika: detect/ io/ language/
mime/ parser/mock/ sax/
Author: nick
Date: Thu Aug 20 09:42:40 2015
New Revision: 1696743
URL: http://svn.apache.org/r1696743
Log:
TIKA-1710 patch from Yaniv Kunda - Use java.nio.charset.StandardCharsets
Modified:
tika/trunk/tika-core/src/test/java/org/apache/tika/detect/MagicDetectorTest.java
tika/trunk/tika-core/src/test/java/org/apache/tika/detect/TextDetectorTest.java
tika/trunk/tika-core/src/test/java/org/apache/tika/io/TailStreamTest.java
tika/trunk/tika-core/src/test/java/org/apache/tika/io/TikaInputStreamTest.java
tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageIdentifierTest.java
tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageProfilerBuilderTest.java
tika/trunk/tika-core/src/test/java/org/apache/tika/mime/MimeDetectionTest.java
tika/trunk/tika-core/src/test/java/org/apache/tika/mime/MimeTypesReaderTest.java
tika/trunk/tika-core/src/test/java/org/apache/tika/mime/ProbabilisticMimeDetectionTest.java
tika/trunk/tika-core/src/test/java/org/apache/tika/mime/ProbabilisticMimeDetectionTestWithTika.java
tika/trunk/tika-core/src/test/java/org/apache/tika/parser/mock/MockParser.java
tika/trunk/tika-core/src/test/java/org/apache/tika/sax/BasicContentHandlerFactoryTest.java
tika/trunk/tika-core/src/test/java/org/apache/tika/sax/BodyContentHandlerTest.java
Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/detect/MagicDetectorTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/detect/MagicDetectorTest.java?rev=1696743&r1=1696742&r2=1696743&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/detect/MagicDetectorTest.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/detect/MagicDetectorTest.java Thu Aug 20 09:42:40 2015
@@ -24,6 +24,9 @@ import org.apache.tika.metadata.Metadata
import org.apache.tika.mime.MediaType;
import org.junit.Test;
+import static java.nio.charset.StandardCharsets.US_ASCII;
+import static java.nio.charset.StandardCharsets.UTF_16BE;
+import static java.nio.charset.StandardCharsets.UTF_16LE;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.fail;
@@ -35,7 +38,7 @@ public class MagicDetectorTest {
@Test
public void testDetectNull() throws Exception {
MediaType html = new MediaType("text", "html");
- Detector detector = new MagicDetector(html, "<html".getBytes("ASCII"));
+ Detector detector = new MagicDetector(html, "<html".getBytes(US_ASCII));
assertEquals(
MediaType.OCTET_STREAM,
detector.detect(null, new Metadata()));
@@ -44,7 +47,7 @@ public class MagicDetectorTest {
@Test
public void testDetectSimple() throws Exception {
MediaType html = new MediaType("text", "html");
- Detector detector = new MagicDetector(html, "<html".getBytes("ASCII"));
+ Detector detector = new MagicDetector(html, "<html".getBytes(US_ASCII));
assertDetect(detector, html, "<html");
assertDetect(detector, html, "<html><head/><body/></html>");
@@ -58,7 +61,7 @@ public class MagicDetectorTest {
public void testDetectOffsetRange() throws Exception {
MediaType html = new MediaType("text", "html");
Detector detector = new MagicDetector(
- html, "<html".getBytes("ASCII"), null, 0, 64);
+ html, "<html".getBytes(US_ASCII), null, 0, 64);
assertDetect(detector, html, "<html");
assertDetect(detector, html, "<html><head/><body/></html>");
@@ -111,7 +114,7 @@ public class MagicDetectorTest {
public void testDetectRegExPDF() throws Exception {
MediaType pdf = new MediaType("application", "pdf");
Detector detector = new MagicDetector(
- pdf, "(?s)\\A.{0,144}%PDF-".getBytes("ASCII"), null, true, 0, 0);
+ pdf, "(?s)\\A.{0,144}%PDF-".getBytes(US_ASCII), null, true, 0, 0);
assertDetect(detector, pdf, "%PDF-1.0");
assertDetect(
@@ -136,7 +139,7 @@ public class MagicDetectorTest {
+ "\".*\\x3ctitle\\x3e.*\\x3c/title\\x3e";
MediaType xhtml = new MediaType("application", "xhtml+xml");
Detector detector = new MagicDetector(xhtml,
- pattern.getBytes("ASCII"), null,
+ pattern.getBytes(US_ASCII), null,
true, 0, 8192);
assertDetect(detector, xhtml,
@@ -171,7 +174,7 @@ public class MagicDetectorTest {
MediaType html = new MediaType("text", "html");
Detector detector = new MagicDetector(
- html, pattern.getBytes("ASCII"), null, true, 0, 0);
+ html, pattern.getBytes(US_ASCII), null, true, 0, 0);
assertDetect(detector, html, data);
assertDetect(detector, html, data1);
@@ -180,7 +183,7 @@ public class MagicDetectorTest {
@Test
public void testDetectStreamReadProblems() throws Exception {
- byte[] data = "abcdefghijklmnopqrstuvwxyz0123456789".getBytes("ASCII");
+ byte[] data = "abcdefghijklmnopqrstuvwxyz0123456789".getBytes(US_ASCII);
MediaType testMT = new MediaType("application", "test");
Detector detector = new MagicDetector(testMT, data, null, false, 0, 0);
// Deliberately prevent InputStream.read(...) from reading the entire
@@ -197,28 +200,24 @@ public class MagicDetectorTest {
// Check regular String matching
detector = MagicDetector.parse(testMT, "string", "0:20", "abcd", null);
- assertDetect(detector, testMT, data.getBytes("ASCII"));
+ assertDetect(detector, testMT, data.getBytes(US_ASCII));
detector = MagicDetector.parse(testMT, "string", "0:20", "cdEFGh", null);
- assertDetect(detector, testMT, data.getBytes("ASCII"));
+ assertDetect(detector, testMT, data.getBytes(US_ASCII));
// Check Little Endian and Big Endian utf-16 strings
detector = MagicDetector.parse(testMT, "unicodeLE", "0:20", "cdEFGh", null);
- assertDetect(detector, testMT, data.getBytes("UTF-16LE"));
+ assertDetect(detector, testMT, data.getBytes(UTF_16LE));
detector = MagicDetector.parse(testMT, "unicodeBE", "0:20", "cdEFGh", null);
- assertDetect(detector, testMT, data.getBytes("UTF-16BE"));
+ assertDetect(detector, testMT, data.getBytes(UTF_16BE));
// Check case ignoring String matching
detector = MagicDetector.parse(testMT, "stringignorecase", "0:20", "BcDeFgHiJKlm", null);
- assertDetect(detector, testMT, data.getBytes("ASCII"));
+ assertDetect(detector, testMT, data.getBytes(US_ASCII));
}
private void assertDetect(Detector detector, MediaType type, String data) {
- try {
- byte[] bytes = data.getBytes("ASCII");
- assertDetect(detector, type, bytes);
- } catch (IOException e) {
- fail("Unexpected exception from MagicDetector");
- }
+ byte[] bytes = data.getBytes(US_ASCII);
+ assertDetect(detector, type, bytes);
}
private void assertDetect(Detector detector, MediaType type, byte[] bytes) {
try {
Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/detect/TextDetectorTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/detect/TextDetectorTest.java?rev=1696743&r1=1696742&r2=1696743&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/detect/TextDetectorTest.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/detect/TextDetectorTest.java Thu Aug 20 09:42:40 2015
@@ -21,11 +21,11 @@ import java.io.IOException;
import java.io.InputStream;
import java.util.Arrays;
-import org.apache.tika.io.IOUtils;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
import org.junit.Test;
+import static java.nio.charset.StandardCharsets.UTF_8;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.fail;
@@ -55,8 +55,8 @@ public class TextDetectorTest {
@Test
public void testDetectText() throws Exception {
- assertText("Hello, World!".getBytes(IOUtils.UTF_8));
- assertText(" \t\r\n".getBytes(IOUtils.UTF_8));
+ assertText("Hello, World!".getBytes(UTF_8));
+ assertText(" \t\r\n".getBytes(UTF_8));
assertNotText(new byte[] { -1, -2, -3, 0x09, 0x0A, 0x0C, 0x0D, 0x1B });
assertNotText(new byte[] { 0 });
assertNotText(new byte[] { 'H', 'e', 'l', 'l', 'o', 0 });
Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/io/TailStreamTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/io/TailStreamTest.java?rev=1696743&r1=1696742&r2=1696743&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/io/TailStreamTest.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/io/TailStreamTest.java Thu Aug 20 09:42:40 2015
@@ -16,6 +16,7 @@
*/
package org.apache.tika.io;
+import static java.nio.charset.StandardCharsets.UTF_8;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertTrue;
@@ -68,7 +69,7 @@ public class TailStreamTest
*/
private static InputStream generateStream(int from, int length)
{
- return new ByteArrayInputStream(generateText(from, length).getBytes(IOUtils.UTF_8));
+ return new ByteArrayInputStream(generateText(from, length).getBytes(UTF_8));
}
/**
@@ -123,7 +124,7 @@ public class TailStreamTest
TailStream stream = new TailStream(generateStream(0, 2 * count), count);
readStream(stream);
assertEquals("Wrong buffer", generateText(count, count), new String(
- stream.getTail(), IOUtils.UTF_8));
+ stream.getTail(), UTF_8));
}
/**
@@ -144,7 +145,7 @@ public class TailStreamTest
read = stream.read(buf);
}
assertEquals("Wrong buffer", generateText(count - tailSize, tailSize),
- new String(stream.getTail(), IOUtils.UTF_8));
+ new String(stream.getTail(), UTF_8));
stream.close();
}
@@ -164,7 +165,7 @@ public class TailStreamTest
stream.reset();
readStream(stream);
assertEquals("Wrong buffer", generateText(tailSize, tailSize),
- new String(stream.getTail(), IOUtils.UTF_8));
+ new String(stream.getTail(), UTF_8));
}
/**
@@ -180,7 +181,7 @@ public class TailStreamTest
byte[] buf = new byte[count];
stream.read(buf);
assertEquals("Wrong buffer", generateText(count - tailSize, tailSize),
- new String(stream.getTail(), IOUtils.UTF_8));
+ new String(stream.getTail(), UTF_8));
stream.close();
}
@@ -197,7 +198,7 @@ public class TailStreamTest
assertEquals("Wrong skip result", skipCount, stream.skip(skipCount));
assertEquals("Wrong buffer",
generateText(skipCount - tailSize, tailSize),
- new String(stream.getTail(), IOUtils.UTF_8));
+ new String(stream.getTail(), UTF_8));
stream.close();
}
@@ -211,7 +212,7 @@ public class TailStreamTest
TailStream stream = new TailStream(generateStream(0, count), 2 * count);
assertEquals("Wrong skip result", count, stream.skip(2 * count));
assertEquals("Wrong buffer", generateText(0, count),
- new String(stream.getTail(), IOUtils.UTF_8));
+ new String(stream.getTail(), UTF_8));
stream.close();
}
Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/io/TikaInputStreamTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/io/TikaInputStreamTest.java?rev=1696743&r1=1696742&r2=1696743&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/io/TikaInputStreamTest.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/io/TikaInputStreamTest.java Thu Aug 20 09:42:40 2015
@@ -16,6 +16,7 @@
*/
package org.apache.tika.io;
+import static java.nio.charset.StandardCharsets.UTF_8;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertFalse;
import static org.junit.Assert.assertTrue;
@@ -62,7 +63,7 @@ public class TikaInputStreamTest {
@Test
public void testStreamBased() throws IOException {
InputStream input =
- new ByteArrayInputStream("Hello, World!".getBytes(IOUtils.UTF_8));
+ new ByteArrayInputStream("Hello, World!".getBytes(UTF_8));
InputStream stream = TikaInputStream.get(input);
File file = TikaInputStream.get(stream).getFile();
@@ -89,7 +90,7 @@ public class TikaInputStreamTest {
File file = File.createTempFile("tika-", ".tmp");
OutputStream stream = new FileOutputStream(file);
try {
- stream.write(data.getBytes(IOUtils.UTF_8));
+ stream.write(data.getBytes(UTF_8));
} finally {
stream.close();
}
@@ -108,7 +109,7 @@ public class TikaInputStreamTest {
private String readStream(InputStream stream) throws IOException {
ByteArrayOutputStream buffer = new ByteArrayOutputStream();
IOUtils.copy(stream, buffer);
- return buffer.toString(IOUtils.UTF_8.name());
+ return buffer.toString(UTF_8.name());
}
@Test
Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageIdentifierTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageIdentifierTest.java?rev=1696743&r1=1696742&r2=1696743&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageIdentifierTest.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageIdentifierTest.java Thu Aug 20 09:42:40 2015
@@ -16,6 +16,7 @@
*/
package org.apache.tika.language;
+import static java.nio.charset.StandardCharsets.UTF_8;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertFalse;
import static org.junit.Assert.assertTrue;
@@ -175,7 +176,7 @@ public class LanguageIdentifierTest {
InputStream stream =
LanguageIdentifierTest.class.getResourceAsStream(language + ".test");
try {
- IOUtils.copy(new InputStreamReader(stream, IOUtils.UTF_8), writer);
+ IOUtils.copy(new InputStreamReader(stream, UTF_8), writer);
} finally {
stream.close();
}
Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageProfilerBuilderTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageProfilerBuilderTest.java?rev=1696743&r1=1696742&r2=1696743&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageProfilerBuilderTest.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageProfilerBuilderTest.java Thu Aug 20 09:42:40 2015
@@ -17,6 +17,7 @@
package org.apache.tika.language;
+import static java.nio.charset.StandardCharsets.UTF_8;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertTrue;
@@ -30,7 +31,6 @@ import java.io.InputStreamReader;
import java.net.URISyntaxException;
import org.apache.tika.exception.TikaException;
-import org.apache.tika.io.IOUtils;
import org.junit.After;
import org.junit.Test;
@@ -50,7 +50,7 @@ public class LanguageProfilerBuilderTest
InputStream is =
LanguageProfilerBuilderTest.class.getResourceAsStream(corpusName);
try {
- ngramProfile = LanguageProfilerBuilder.create(profileName, is , IOUtils.UTF_8.name());
+ ngramProfile = LanguageProfilerBuilder.create(profileName, is , UTF_8.name());
} finally {
is.close();
}
@@ -82,7 +82,7 @@ public class LanguageProfilerBuilderTest
+ FILE_EXTENSION));
try {
BufferedReader reader = new BufferedReader(new InputStreamReader(
- stream, IOUtils.UTF_8));
+ stream, UTF_8));
String line = reader.readLine();
while (line != null) {
if (line.length() > 0 && !line.startsWith("#")) {// skips the
Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/mime/MimeDetectionTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/mime/MimeDetectionTest.java?rev=1696743&r1=1696742&r2=1696743&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/mime/MimeDetectionTest.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/mime/MimeDetectionTest.java Thu Aug 20 09:42:40 2015
@@ -16,6 +16,9 @@
*/
package org.apache.tika.mime;
+import static java.nio.charset.StandardCharsets.UTF_16BE;
+import static java.nio.charset.StandardCharsets.UTF_16LE;
+import static java.nio.charset.StandardCharsets.UTF_8;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertTrue;
@@ -25,7 +28,6 @@ import java.io.InputStream;
import java.net.URL;
import org.apache.tika.config.TikaConfig;
-import org.apache.tika.io.IOUtils;
import org.apache.tika.metadata.Metadata;
import org.junit.Before;
import org.junit.Test;
@@ -82,13 +84,13 @@ public class MimeDetectionTest {
@Test
public void testByteOrderMark() throws Exception {
assertEquals(MediaType.TEXT_PLAIN, mimeTypes.detect(
- new ByteArrayInputStream("\ufefftest".getBytes("UTF-16LE")),
+ new ByteArrayInputStream("\ufefftest".getBytes(UTF_16LE)),
new Metadata()));
assertEquals(MediaType.TEXT_PLAIN, mimeTypes.detect(
- new ByteArrayInputStream("\ufefftest".getBytes("UTF-16BE")),
+ new ByteArrayInputStream("\ufefftest".getBytes(UTF_16BE)),
new Metadata()));
assertEquals(MediaType.TEXT_PLAIN, mimeTypes.detect(
- new ByteArrayInputStream("\ufefftest".getBytes(IOUtils.UTF_8)),
+ new ByteArrayInputStream("\ufefftest".getBytes(UTF_8)),
new Metadata()));
}
@@ -198,7 +200,7 @@ public class MimeDetectionTest {
@Test
public void testNotXML() throws IOException {
assertEquals(MediaType.TEXT_PLAIN, mimeTypes.detect(
- new ByteArrayInputStream("<!-- test -->".getBytes(IOUtils.UTF_8)),
+ new ByteArrayInputStream("<!-- test -->".getBytes(UTF_8)),
new Metadata()));
}
@@ -222,7 +224,7 @@ public class MimeDetectionTest {
*/
@Test
public void testMimeMagicClashSamePriority() throws IOException {
- byte[] helloWorld = "Hello, World!".getBytes(IOUtils.UTF_8);
+ byte[] helloWorld = "Hello, World!".getBytes(UTF_8);
MediaType helloType = MediaType.parse("hello/world-file");
MediaType helloXType = MediaType.parse("hello/x-world-hello");
Metadata metadata;
Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/mime/MimeTypesReaderTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/mime/MimeTypesReaderTest.java?rev=1696743&r1=1696742&r2=1696743&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/mime/MimeTypesReaderTest.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/mime/MimeTypesReaderTest.java Thu Aug 20 09:42:40 2015
@@ -16,6 +16,7 @@
*/
package org.apache.tika.mime;
+import static java.nio.charset.StandardCharsets.US_ASCII;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertNotNull;
import static org.junit.Assert.assertTrue;
@@ -225,7 +226,7 @@ public class MimeTypesReaderTest {
// By contents - picks the x one as that sorts later
m = new Metadata();
ByteArrayInputStream s = new ByteArrayInputStream(
- "Hello, World!".getBytes("ASCII"));
+ "Hello, World!".getBytes(US_ASCII));
assertEquals(hxw.toString(), this.mimeTypes.detect(s, m).toString());
} catch (Exception e) {
fail(e.getMessage());
Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/mime/ProbabilisticMimeDetectionTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/mime/ProbabilisticMimeDetectionTest.java?rev=1696743&r1=1696742&r2=1696743&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/mime/ProbabilisticMimeDetectionTest.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/mime/ProbabilisticMimeDetectionTest.java Thu Aug 20 09:42:40 2015
@@ -16,6 +16,9 @@
*/
package org.apache.tika.mime;
+import static java.nio.charset.StandardCharsets.UTF_16BE;
+import static java.nio.charset.StandardCharsets.UTF_16LE;
+import static java.nio.charset.StandardCharsets.UTF_8;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertTrue;
@@ -23,14 +26,13 @@ import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
-import java.nio.charset.Charset;
import org.apache.tika.metadata.Metadata;
import org.junit.Before;
import org.junit.Test;
public class ProbabilisticMimeDetectionTest {
- private static final Charset UTF8 = Charset.forName("UTF-8");
+
private ProbabilisticMimeDetectionSelector proDetector;
private MediaTypeRegistry registry;
@@ -76,14 +78,14 @@ public class ProbabilisticMimeDetectionT
@Test
public void testByteOrderMark() throws Exception {
assertEquals(MediaType.TEXT_PLAIN, proDetector.detect(
- new ByteArrayInputStream("\ufefftest".getBytes("UTF-16LE")),
+ new ByteArrayInputStream("\ufefftest".getBytes(UTF_16LE)),
new Metadata()));
assertEquals(MediaType.TEXT_PLAIN, proDetector.detect(
- new ByteArrayInputStream("\ufefftest".getBytes("UTF-16BE")),
+ new ByteArrayInputStream("\ufefftest".getBytes(UTF_16BE)),
new Metadata()));
assertEquals(MediaType.TEXT_PLAIN, proDetector.detect(
- new ByteArrayInputStream("\ufefftest".getBytes(UTF8)),
+ new ByteArrayInputStream("\ufefftest".getBytes(UTF_8)),
new Metadata()));
}
@@ -199,7 +201,7 @@ public class ProbabilisticMimeDetectionT
@Test
public void testNotXML() throws IOException {
assertEquals(MediaType.TEXT_PLAIN, proDetector.detect(
- new ByteArrayInputStream("<!-- test -->".getBytes(UTF8)),
+ new ByteArrayInputStream("<!-- test -->".getBytes(UTF_8)),
new Metadata()));
}
@@ -222,7 +224,7 @@ public class ProbabilisticMimeDetectionT
*/
@Test
public void testMimeMagicClashSamePriority() throws IOException {
- byte[] helloWorld = "Hello, World!".getBytes(UTF8);
+ byte[] helloWorld = "Hello, World!".getBytes(UTF_8);
MediaType helloType = MediaType.parse("hello/world-file");
MediaType helloXType = MediaType.parse("hello/x-world-hello");
Metadata metadata;
Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/mime/ProbabilisticMimeDetectionTestWithTika.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/mime/ProbabilisticMimeDetectionTestWithTika.java?rev=1696743&r1=1696742&r2=1696743&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/mime/ProbabilisticMimeDetectionTestWithTika.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/mime/ProbabilisticMimeDetectionTestWithTika.java Thu Aug 20 09:42:40 2015
@@ -1,4 +1,3 @@
-
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
@@ -17,6 +16,9 @@
*/
package org.apache.tika.mime;
+import static java.nio.charset.StandardCharsets.UTF_16BE;
+import static java.nio.charset.StandardCharsets.UTF_16LE;
+import static java.nio.charset.StandardCharsets.UTF_8;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertNotNull;
import static org.junit.Assert.assertTrue;
@@ -25,7 +27,6 @@ import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
-import java.nio.charset.Charset;
import org.apache.tika.Tika;
import org.apache.tika.config.ServiceLoader;
@@ -36,8 +37,7 @@ import org.junit.Before;
import org.junit.Test;
public class ProbabilisticMimeDetectionTestWithTika {
- private static final Charset UTF8 = Charset.forName("UTF-8");
-
+
private ProbabilisticMimeDetectionSelector proSelector;
private MediaTypeRegistry registry;
private Tika tika;
@@ -98,14 +98,14 @@ public class ProbabilisticMimeDetectionT
@Test
public void testByteOrderMark() throws Exception {
assertEquals(MediaType.TEXT_PLAIN.toString(), tika.detect(
- new ByteArrayInputStream("\ufefftest".getBytes("UTF-16LE")),
+ new ByteArrayInputStream("\ufefftest".getBytes(UTF_16LE)),
new Metadata()));
assertEquals(MediaType.TEXT_PLAIN.toString(), tika.detect(
- new ByteArrayInputStream("\ufefftest".getBytes("UTF-16BE")),
+ new ByteArrayInputStream("\ufefftest".getBytes(UTF_16BE)),
new Metadata()));
assertEquals(MediaType.TEXT_PLAIN.toString(), tika.detect(
- new ByteArrayInputStream("\ufefftest".getBytes(UTF8)),
+ new ByteArrayInputStream("\ufefftest".getBytes(UTF_8)),
new Metadata()));
}
@@ -219,7 +219,7 @@ public class ProbabilisticMimeDetectionT
@Test
public void testNotXML() throws IOException {
assertEquals(MediaType.TEXT_PLAIN.toString(), tika.detect(
- new ByteArrayInputStream("<!-- test -->".getBytes(UTF8)),
+ new ByteArrayInputStream("<!-- test -->".getBytes(UTF_8)),
new Metadata()));
}
@@ -242,7 +242,7 @@ public class ProbabilisticMimeDetectionT
*/
@Test
public void testMimeMagicClashSamePriority() throws IOException {
- byte[] helloWorld = "Hello, World!".getBytes(UTF8);
+ byte[] helloWorld = "Hello, World!".getBytes(UTF_8);
MediaType helloType = MediaType.parse("hello/world-file");
MediaType helloXType = MediaType.parse("hello/x-world-hello");
Metadata metadata;
Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/parser/mock/MockParser.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/parser/mock/MockParser.java?rev=1696743&r1=1696742&r2=1696743&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/parser/mock/MockParser.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/parser/mock/MockParser.java Thu Aug 20 09:42:40 2015
@@ -34,7 +34,6 @@ import java.util.Set;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor;
-import org.apache.tika.io.IOUtils;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaMetadataKeys;
import org.apache.tika.mime.MediaType;
@@ -50,6 +49,8 @@ import org.w3c.dom.NodeList;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
+import static java.nio.charset.StandardCharsets.UTF_8;
+
/**
* This class enables mocking of parser behavior for use in testing
* wrappers and drivers of parsers.
@@ -150,7 +151,7 @@ public class MockParser extends Abstract
if (! "".equals(contentType)) {
m.set(Metadata.CONTENT_TYPE, contentType);
}
- InputStream is = new ByteArrayInputStream(embeddedText.getBytes(IOUtils.UTF_8));
+ InputStream is = new ByteArrayInputStream(embeddedText.getBytes(UTF_8));
extractor.parseEmbedded(
is,
Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/sax/BasicContentHandlerFactoryTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/sax/BasicContentHandlerFactoryTest.java?rev=1696743&r1=1696742&r2=1696743&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/sax/BasicContentHandlerFactoryTest.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/sax/BasicContentHandlerFactoryTest.java Thu Aug 20 09:42:40 2015
@@ -16,6 +16,7 @@
*/
package org.apache.tika.sax;
+import static java.nio.charset.StandardCharsets.UTF_8;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertFalse;
import static org.junit.Assert.assertTrue;
@@ -27,7 +28,6 @@ import java.io.UnsupportedEncodingExcept
import java.util.Set;
import org.apache.tika.exception.TikaException;
-import org.apache.tika.io.IOUtils;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.ParseContext;
@@ -44,7 +44,7 @@ import org.xml.sax.helpers.DefaultHandle
*/
public class BasicContentHandlerFactoryTest {
- private static final String ENCODING = IOUtils.UTF_8.name();
+ private static final String ENCODING = UTF_8.name();
//default max char len (at least in WriteOutContentHandler is 100k)
private static final int OVER_DEFAULT = 120000;
Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/sax/BodyContentHandlerTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/sax/BodyContentHandlerTest.java?rev=1696743&r1=1696742&r2=1696743&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/sax/BodyContentHandlerTest.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/sax/BodyContentHandlerTest.java Thu Aug 20 09:42:40 2015
@@ -16,12 +16,12 @@
*/
package org.apache.tika.sax;
+import static java.nio.charset.StandardCharsets.UTF_8;
import static org.junit.Assert.assertEquals;
import java.io.ByteArrayOutputStream;
import java.io.OutputStream;
-import org.apache.tika.io.IOUtils;
import org.apache.tika.metadata.Metadata;
import org.junit.Test;
@@ -46,7 +46,7 @@ public class BodyContentHandlerTest {
xhtml.element("p", "Test text");
xhtml.endDocument();
- assertEquals("Test text\n", buffer.toString(IOUtils.UTF_8.name()));
+ assertEquals("Test text\n", buffer.toString(UTF_8.name()));
}
}