You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by kk...@apache.org on 2013/12/19 20:46:51 UTC
svn commit: r1552405 [3/4] - in /tika/trunk: ./ tika-app/
tika-app/src/test/java/org/apache/tika/cli/ tika-bundle/
tika-bundle/src/test/java/org/apache/tika/bundle/ tika-core/
tika-core/src/test/java/org/apache/tika/
tika-core/src/test/java/org/apache/...
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/crypto/Pkcs7ParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/crypto/Pkcs7ParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/crypto/Pkcs7ParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/crypto/Pkcs7ParserTest.java Thu Dec 19 19:46:49 2013
@@ -17,6 +17,9 @@
package org.apache.tika.parser.crypto;
+import static org.junit.Assert.assertTrue;
+import static org.junit.Assert.fail;
+
import java.io.InputStream;
import org.apache.tika.TikaTest;
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/dwg/DWGParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/dwg/DWGParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/dwg/DWGParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/dwg/DWGParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,46 +16,56 @@
*/
package org.apache.tika.parser.dwg;
-import java.io.InputStream;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertNull;
+import static org.junit.Assert.assertTrue;
-import junit.framework.TestCase;
+import java.io.InputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
-public class DWGParserTest extends TestCase {
+public class DWGParserTest {
+
+ @Test
public void testDWG2000Parser() throws Exception {
InputStream input = DWGParserTest.class.getResourceAsStream(
"/test-documents/testDWG2000.dwg");
testParserAlt(input);
}
+ @Test
public void testDWG2004Parser() throws Exception {
InputStream input = DWGParserTest.class.getResourceAsStream(
"/test-documents/testDWG2004.dwg");
testParser(input);
}
+ @Test
public void testDWG2004ParserNoHeaderAddress() throws Exception {
InputStream input = DWGParserTest.class.getResourceAsStream(
"/test-documents/testDWG2004_no_header.dwg");
testParserNoHeader(input);
}
+ @Test
public void testDWG2007Parser() throws Exception {
InputStream input = DWGParserTest.class.getResourceAsStream(
"/test-documents/testDWG2007.dwg");
testParser(input);
}
+ @Test
public void testDWG2010Parser() throws Exception {
InputStream input = DWGParserTest.class.getResourceAsStream(
"/test-documents/testDWG2010.dwg");
testParser(input);
}
+ @Test
public void testDWG2010CustomPropertiesParser() throws Exception {
// Check that standard parsing works
InputStream input = DWGParserTest.class.getResourceAsStream(
@@ -79,6 +89,7 @@ public class DWGParserTest extends TestC
}
}
+ @Test
public void testDWGMechParser() throws Exception {
String[] types = new String[] {
"6", "2004", "2004DX", "2005", "2006",
@@ -91,6 +102,7 @@ public class DWGParserTest extends TestC
}
}
+ @SuppressWarnings("deprecation")
private void testParser(InputStream input) throws Exception {
try {
Metadata metadata = new Metadata();
@@ -129,6 +141,7 @@ public class DWGParserTest extends TestC
}
}
+ @SuppressWarnings("deprecation")
private void testParserNoHeader(InputStream input) throws Exception {
try {
Metadata metadata = new Metadata();
@@ -152,6 +165,7 @@ public class DWGParserTest extends TestC
}
}
+ @SuppressWarnings("deprecation")
private void testParserAlt(InputStream input) throws Exception {
try {
Metadata metadata = new Metadata();
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/epub/EpubParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/epub/EpubParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/epub/EpubParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/epub/EpubParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,18 +16,21 @@
*/
package org.apache.tika.parser.epub;
-import java.io.InputStream;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
-import junit.framework.TestCase;
+import java.io.InputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
-public class EpubParserTest extends TestCase {
+public class EpubParserTest {
+ @Test
public void testXMLParser() throws Exception {
InputStream input = EpubParserTest.class.getResourceAsStream(
"/test-documents/testEPUB.epub");
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/executable/ExecutableParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/executable/ExecutableParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/executable/ExecutableParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/executable/ExecutableParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,17 +16,19 @@
*/
package org.apache.tika.parser.executable;
-import java.io.InputStream;
+import static org.junit.Assert.assertEquals;
-import junit.framework.TestCase;
+import java.io.InputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
-public class ExecutableParserTest extends TestCase {
+public class ExecutableParserTest {
+ @Test
public void testWin32Parser() throws Exception {
InputStream input = ExecutableParserTest.class.getResourceAsStream(
"/test-documents/testWindows-x86-32.exe");
@@ -56,6 +58,7 @@ public class ExecutableParserTest extend
}
}
+ @Test
public void testElfParser_x86_32() throws Exception {
InputStream input = ExecutableParserTest.class.getResourceAsStream(
"/test-documents/testLinux-x86-32");
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/feed/FeedParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/feed/FeedParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/feed/FeedParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/feed/FeedParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,18 +16,21 @@
*/
package org.apache.tika.parser.feed;
-import java.io.InputStream;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertFalse;
-import junit.framework.TestCase;
+import java.io.InputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
-public class FeedParserTest extends TestCase {
+public class FeedParserTest {
+ @Test
public void testXMLParser() throws Exception {
InputStream input = FeedParserTest.class
.getResourceAsStream("/test-documents/rsstest.rss");
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/font/AdobeFontMetricParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/font/AdobeFontMetricParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/font/AdobeFontMetricParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/font/AdobeFontMetricParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,7 +16,8 @@
*/
package org.apache.tika.parser.font;
-import junit.framework.TestCase;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
@@ -26,11 +27,14 @@ import org.apache.tika.parser.Parser;
import org.apache.tika.sax.BodyContentHandler;
import org.xml.sax.ContentHandler;
import org.apache.tika.io.TikaInputStream;
+import org.junit.Test;
/**
* Test case for parsing afm files.
*/
-public class AdobeFontMetricParserTest extends TestCase {
+public class AdobeFontMetricParserTest {
+
+ @Test
public void testAdobeFontMetricParsing() throws Exception {
Parser parser = new AutoDetectParser(); // Should auto-detect!
ContentHandler handler = new BodyContentHandler();
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/fork/ForkParserIntegrationTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/fork/ForkParserIntegrationTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/fork/ForkParserIntegrationTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/fork/ForkParserIntegrationTest.java Thu Dec 19 19:46:49 2013
@@ -16,6 +16,11 @@
*/
package org.apache.tika.parser.fork;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertNotNull;
+import static org.junit.Assert.assertTrue;
+import static org.junit.Assert.fail;
+
import java.io.IOException;
import java.io.InputStream;
import java.io.NotSerializableException;
@@ -23,8 +28,6 @@ import java.util.Arrays;
import java.util.HashSet;
import java.util.Set;
-import junit.framework.TestCase;
-
import org.apache.tika.Tika;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.detect.DefaultDetector;
@@ -36,6 +39,7 @@ import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
@@ -43,13 +47,14 @@ import org.xml.sax.SAXException;
* Test that the ForkParser correctly behaves when
* wired in to the regular Parsers and their test data
*/
-public class ForkParserIntegrationTest extends TestCase {
+public class ForkParserIntegrationTest {
private Tika tika = new Tika(); // TODO Use TikaConfig instead, when it works
/**
* Simple text parsing
*/
+ @Test
public void testForkedTextParsing() throws Exception {
ForkParser parser = new ForkParser(
ForkParserIntegrationTest.class.getClassLoader(),
@@ -144,6 +149,7 @@ public class ForkParserIntegrationTest e
* TIKA-831 Parsers throwing errors should be caught and
* properly reported
*/
+ @Test
public void testParsingErrorInForkedParserShouldBeReported() throws Exception {
BrokenParser brokenParser = new BrokenParser();
Parser parser = new ForkParser(ForkParser.class.getClassLoader(), brokenParser);
@@ -179,6 +185,7 @@ public class ForkParserIntegrationTest e
* If we supply a non serializable object on the ParseContext,
* check we get a helpful exception back
*/
+ @Test
public void testParserHandlingOfNonSerializable() throws Exception {
ForkParser parser = new ForkParser(
ForkParserIntegrationTest.class.getClassLoader(),
@@ -210,6 +217,7 @@ public class ForkParserIntegrationTest e
/**
* TIKA-832
*/
+ @Test
public void testAttachingADebuggerOnTheForkedParserShouldWork()
throws Exception {
ParseContext context = new ParseContext();
@@ -238,6 +246,7 @@ public class ForkParserIntegrationTest e
* TIKA-808 - Ensure that parsing of our test PDFs work under
* the Fork Parser, to ensure that complex parsing behaves
*/
+ @Test
public void testForkedPDFParsing() throws Exception {
ForkParser parser = new ForkParser(
ForkParserIntegrationTest.class.getClassLoader(),
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/hdf/HDFParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/hdf/HDFParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/hdf/HDFParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/hdf/HDFParserTest.java Thu Dec 19 19:46:49 2013
@@ -17,26 +17,31 @@
package org.apache.tika.parser.hdf;
//JDK imports
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertNotNull;
+
import java.io.InputStream;
+
+
+
//TIKA imports
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.hdf.HDFParser;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
-//Junit imports
-import junit.framework.TestCase;
-
/**
*
* Test suite for the {@link HDFParser}.
*
*/
-public class HDFParserTest extends TestCase {
+public class HDFParserTest {
+ @Test
public void testParseGlobalMetadata() throws Exception {
if(System.getProperty("java.version").startsWith("1.5")) {
return;
@@ -64,6 +69,7 @@ public class HDFParserTest extends TestC
assertEquals("5", metadata.get("GranuleMonth"));
}
+ @Test
public void testHDF4() throws Exception {
if(System.getProperty("java.version").startsWith("1.5")) {
return;
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,6 +16,11 @@
*/
package org.apache.tika.parser.html;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertFalse;
+import static org.junit.Assert.assertNotNull;
+import static org.junit.Assert.assertTrue;
+
import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
@@ -30,8 +35,6 @@ import javax.xml.transform.sax.SAXTransf
import javax.xml.transform.sax.TransformerHandler;
import javax.xml.transform.stream.StreamResult;
-import junit.framework.TestCase;
-
import org.apache.tika.Tika;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Geographic;
@@ -40,13 +43,16 @@ import org.apache.tika.metadata.TikaCore
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.TeeContentHandler;
+import org.junit.Ignore;
+import org.junit.Test;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
-public class HtmlParserTest extends TestCase {
+public class HtmlParserTest {
+ @Test
public void testParseAscii() throws Exception {
String path = "/test-documents/testHTML.html";
final StringWriter href = new StringWriter();
@@ -96,6 +102,8 @@ public class HtmlParserTest extends Test
content.contains("Indexation du fichier"));
}
+ @Test
+ @Ignore("The file 'testXHTML_utf8.html' is not available fo testing")
public void XtestParseUTF8() throws IOException, SAXException, TikaException {
String path = "/test-documents/testXHTML_utf8.html";
Metadata metadata = new Metadata();
@@ -114,6 +122,7 @@ public class HtmlParserTest extends Test
.contains("ââ¢â§ââ"));
}
+ @Test
public void testXhtmlParsing() throws Exception {
String path = "/test-documents/testXHTML.html";
Metadata metadata = new Metadata();
@@ -130,6 +139,7 @@ public class HtmlParserTest extends Test
assertTrue(content.contains("an XHTML document"));
}
+ @Test
public void testParseEmpty() throws Exception {
ContentHandler handler = new BodyContentHandler();
new HtmlParser().parse(
@@ -142,6 +152,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-210
* @see <a href="https://issues.apache.org/jira/browse/TIKA-210">TIKA-210</a>
*/
+ @Test
public void testCharactersDirectlyUnderBodyElement() throws Exception {
String test = "<html><body>test</body></html>";
String content = new Tika().parseToString(
@@ -153,6 +164,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-287
* @see <a href="https://issues.apache.org/jira/browse/TIKA-287">TIKA-287</a>
*/
+ @Test
public void testBaseHref() throws Exception {
assertRelativeLink(
"http://lucene.apache.org/tika/",
@@ -221,6 +233,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-268
* @see <a href="https://issues.apache.org/jira/browse/TIKA-268">TIKA-268</a>
*/
+ @Test
public void testWhitespaceBetweenTableCells() throws Exception {
String test =
"<html><body><table><tr><td>a</td><td>b</td></table></body></html>";
@@ -235,6 +248,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-332
* @see <a href="https://issues.apache.org/jira/browse/TIKA-332">TIKA-332</a>
*/
+ @Test
public void testHttpEquivCharset() throws Exception {
String test =
"<html><head><meta http-equiv=\"content-type\""
@@ -252,6 +266,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-892
* @see <a href="https://issues.apache.org/jira/browse/TIKA-892">TIKA-892</a>
*/
+ @Test
public void testHtml5Charset() throws Exception {
String test =
"<html><head><meta charset=\"ISO-8859-15\" />"
@@ -268,6 +283,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-334
* @see <a href="https://issues.apache.org/jira/browse/TIKA-334">TIKA-334</a>
*/
+ @Test
public void testDetectOfCharset() throws Exception {
String test =
"<html><head><title>\u017d</title></head><body></body></html>";
@@ -282,6 +298,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-341
* @see <a href="https://issues.apache.org/jira/browse/TIKA-341">TIKA-341</a>
*/
+ @Test
public void testUsingCharsetInContentTypeHeader() throws Exception {
final String test =
"<html><head><title>the name is \u00e1ndre</title></head>"
@@ -309,6 +326,7 @@ public class HtmlParserTest extends Test
*
* @see <a href="https://issues.apache.org/jira/browse/TIKA-343">TIKA-343</a>
*/
+ @Test
public void testLineBreak() throws Exception {
String test = "<html><body><div>foo<br>bar</div>baz</body></html>";
String text = new Tika().parseToString(
@@ -324,6 +342,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-339: Don't use language returned by CharsetDetector
* @see <a href="https://issues.apache.org/jira/browse/TIKA-339">TIKA-339</a>
*/
+ @Test
public void testIgnoreCharsetDetectorLanguage() throws Exception {
String test = "<html><title>Simple Content</title><body></body></html>";
Metadata metadata = new Metadata();
@@ -339,6 +358,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-349
* @see <a href="https://issues.apache.org/jira/browse/TIKA-349">TIKA-349</a>
*/
+ @Test
public void testHttpEquivCharsetFunkyAttributes() throws Exception {
String test1 =
"<html><head><meta http-equiv=\"content-type\""
@@ -368,6 +388,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-350
* @see <a href="https://issues.apache.org/jira/browse/TIKA-350">TIKA-350</a>
*/
+ @Test
public void testUsingFunkyCharsetInContentTypeHeader() throws Exception {
final String test =
"<html><head><title>the name is \u00e1ndre</title></head>"
@@ -392,6 +413,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-357
* @see <a href="https://issues.apache.org/jira/browse/TIKA-357">TIKA-357</a>
*/
+ @Test
public void testMetaHttpEquivWithLotsOfPreambleText() throws Exception {
String path = "/test-documents/big-preamble.html";
Metadata metadata = new Metadata();
@@ -406,6 +428,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-420
* @see <a href="https://issues.apache.org/jira/browse/TIKA-420">TIKA-420</a>
*/
+ @Test
public void testBoilerplateRemoval() throws Exception {
String path = "/test-documents/boilerplate.html";
@@ -426,6 +449,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-478. Don't emit <head> sub-elements inside of <body>.
* @see <a href="https://issues.apache.org/jira/browse/TIKA-478">TIKA-478</a>
*/
+ @Test
public void testElementOrdering() throws Exception {
final String test = "<html><head><title>Title</title>" +
"<meta http-equiv=\"content-type\" content=\"text/html\">" +
@@ -463,6 +487,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-463. Don't skip elements that have URLs.
* @see <a href="https://issues.apache.org/jira/browse/TIKA-463">TIKA-463</a>
*/
+ @Test
public void testImgUrlExtraction() throws Exception {
final String test = "<html><head><title>Title</title>" +
"<base href=\"http://domain.com\" />" +
@@ -483,6 +508,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-463. Don't skip elements that have URLs.
* @see <a href="https://issues.apache.org/jira/browse/TIKA-463">TIKA-463</a>
*/
+ @Test
public void testFrameSrcExtraction() throws Exception {
final String test = "<html><head><title>Title</title>" +
"<base href=\"http://domain.com\" />" +
@@ -503,6 +529,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-463. Don't skip elements that have URLs.
* @see <a href="https://issues.apache.org/jira/browse/TIKA-463">TIKA-463</a>
*/
+ @Test
public void testIFrameSrcExtraction() throws Exception {
final String test = "<html><head><title>Title</title>" +
"<base href=\"http://domain.com\" />" +
@@ -524,6 +551,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-463. Don't skip elements that have URLs.
* @see <a href="https://issues.apache.org/jira/browse/TIKA-463">TIKA-463</a>
*/
+ @Test
public void testAreaExtraction() throws Exception {
final String test = "<html><head><title>Title</title>" +
"<base href=\"http://domain.com\" />" +
@@ -546,6 +574,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-463. Don't skip elements that have URLs.
* @see <a href="https://issues.apache.org/jira/browse/TIKA-463">TIKA-463</a>
*/
+ @Test
public void testObjectExtraction() throws Exception {
final String test = "<html><head><title>Title</title>" +
"<base href=\"http://domain.com\" />" +
@@ -571,6 +600,7 @@ public class HtmlParserTest extends Test
* Test case for change related to TIKA-463. Verify proper handling of <meta> tags.
* @see <a href="https://issues.apache.org/jira/browse/TIKA-463">TIKA-463</a>
*/
+ @Test
public void testMetaTagHandling() throws Exception {
final String test = "<html><body><h1>header</h1><p>some text</p></body></html>";
@@ -594,6 +624,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-457. Better handling for broken HTML that has <frameset> inside of <body>.
* @see <a href="https://issues.apache.org/jira/browse/TIKA-457">TIKA-457</a>
*/
+ @Test
public void testBrokenFrameset() throws Exception {
final String test1 = "<html><head><title>Title</title>" +
"<base href=\"http://domain.com\" />" +
@@ -642,6 +673,7 @@ public class HtmlParserTest extends Test
* as delegate for BoilerpipeContentHandler
* @see <a href="https://issues.apache.org/jira/browse/TIKA-480">TIKA-480</a>
*/
+ @Test
public void testBoilerplateDelegation() throws Exception {
String path = "/test-documents/boilerplate.html";
@@ -664,6 +696,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-481. Verify href in <link> is resolved.
* @see <a href="https://issues.apache.org/jira/browse/TIKA-481">TIKA-481</a>
*/
+ @Test
public void testLinkHrefResolution() throws Exception {
final String test = "<html><head><title>Title</title>" +
"<base href=\"http://domain.com\" />" +
@@ -704,6 +737,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-564. Support returning markup from BoilerpipeContentHandler.
* @see <a href="https://issues.apache.org/jira/browse/TIKA-564">TIKA-564</a>
*/
+ @Test
public void testBoilerplateWithMarkup() throws Exception {
String path = "/test-documents/boilerplate.html";
@@ -729,11 +763,10 @@ public class HtmlParserTest extends Test
/**
* Test case for TIKA-434 - Pushback buffer overflow in TagSoup
*/
+ @Test
public void testPushback() throws IOException, TikaException {
String content = new Tika().parseToString(
HtmlParserTest.class.getResourceAsStream("/test-documents/tika434.html"), new Metadata());
-
-
assertNotNull(content);
}
@@ -743,6 +776,7 @@ public class HtmlParserTest extends Test
*
* @see <a href="https://issues.apache.org/jira/browse/TIKA-869">TIKA-869</a>
*/
+ @Test
public void testIdentityMapper() throws Exception {
final String html = "<html><head><title>Title</title></head>" +
"<body></body></html>";
@@ -767,6 +801,7 @@ public class HtmlParserTest extends Test
*
* @see <a href="https://issues.apache.org/jira/browse/TIKA-889">TIKA-889</a>
*/
+ @Test
public void testNewlineAndIndent() throws Exception {
final String html = "<html><head><title>Title</title></head>" +
"<body><ul><li>one</li></ul></body></html>";
@@ -786,6 +821,7 @@ public class HtmlParserTest extends Test
* Test case for TIKA-961
* @see <a href="https://issues.apache.org/jira/browse/TIKA-961">TIKA-961</a>
*/
+ @Test
public void testBoilerplateWhitespace() throws Exception {
String path = "/test-documents/boilerplate-whitespace.html";
@@ -816,6 +852,7 @@ public class HtmlParserTest extends Test
*
* @see <a href="https://issues.apache.org/jira/browse/TIKA-983">TIKA-983</a>
*/
+ @Test
public void testOpenGraphMetadata() throws Exception {
String test1 =
"<html><head><meta property=\"og:description\""
@@ -833,6 +870,7 @@ public class HtmlParserTest extends Test
}
// TIKA-1011
+ @Test
public void testUserDefinedCharset() throws Exception {
String content = new Tika().parseToString(
HtmlParserTest.class.getResourceAsStream("/test-documents/testUserDefinedCharset.mhtml"), new Metadata());
@@ -840,6 +878,7 @@ public class HtmlParserTest extends Test
}
//TIKA-1001
+ @Test
public void testNoisyMetaCharsetHeaders() throws Exception {
Tika tika = new Tika();
String hit = "\u0623\u0639\u0631\u0628";
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/ibooks/iBooksParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/ibooks/iBooksParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/ibooks/iBooksParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/ibooks/iBooksParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,19 +16,21 @@
*/
package org.apache.tika.parser.ibooks;
-import java.io.InputStream;
+import static org.junit.Assert.assertEquals;
-import junit.framework.TestCase;
+import java.io.InputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.epub.EpubParser;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
-public class iBooksParserTest extends TestCase {
+public class iBooksParserTest {
+ @Test
public void testiBooksParser() throws Exception {
InputStream input = iBooksParserTest.class.getResourceAsStream(
"/test-documents/testiBooks.ibooks");
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/ImageMetadataExtractorTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/ImageMetadataExtractorTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/ImageMetadataExtractorTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/ImageMetadataExtractorTest.java Thu Dec 19 19:46:49 2013
@@ -23,6 +23,7 @@ import java.util.List;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
+import org.junit.Test;
import com.drew.metadata.Directory;
import com.drew.metadata.MetadataException;
@@ -31,13 +32,16 @@ import com.drew.metadata.exif.ExifIFD0Di
import com.drew.metadata.exif.ExifSubIFDDirectory;
import com.drew.metadata.jpeg.JpegCommentDirectory;
-import junit.framework.TestCase;
-
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertFalse;
+import static org.junit.Assert.assertNull;
+import static org.junit.Assert.assertTrue;
import static org.mockito.Mockito.*;
-public class ImageMetadataExtractorTest extends TestCase {
+public class ImageMetadataExtractorTest {
@SuppressWarnings({ "rawtypes", "unchecked" })
+ @Test
public void testHandleDirectories() throws MetadataException {
Metadata metadata = mock(Metadata.class);
ImageMetadataExtractor.DirectoryHandler handler1 = mock(ImageMetadataExtractor.DirectoryHandler.class);
@@ -54,6 +58,7 @@ public class ImageMetadataExtractorTest
verify(handler1).handle(directory, metadata);
}
+ @Test
public void testExifHandlerSupports() {
assertTrue(new ImageMetadataExtractor.ExifHandler().supports(ExifIFD0Directory.class));
assertTrue(new ImageMetadataExtractor.ExifHandler().supports(ExifSubIFDDirectory.class));
@@ -61,6 +66,7 @@ public class ImageMetadataExtractorTest
assertFalse(new ImageMetadataExtractor.ExifHandler().supports(JpegCommentDirectory.class));
}
+ @Test
public void testExifHandlerParseDate() throws MetadataException {
ExifSubIFDDirectory exif = mock(ExifSubIFDDirectory.class);
when(exif.containsTag(ExifSubIFDDirectory.TAG_DATETIME_ORIGINAL)).thenReturn(true);
@@ -73,6 +79,7 @@ public class ImageMetadataExtractorTest
metadata.get(TikaCoreProperties.CREATED));
}
+ @Test
public void testExifHandlerParseDateFallback() throws MetadataException {
ExifIFD0Directory exif = mock(ExifIFD0Directory.class);
when(exif.containsTag(ExifIFD0Directory.TAG_DATETIME)).thenReturn(true);
@@ -85,6 +92,7 @@ public class ImageMetadataExtractorTest
metadata.get(TikaCoreProperties.CREATED));
}
+ @Test
public void testExifHandlerParseDateError() throws MetadataException {
ExifIFD0Directory exif = mock(ExifIFD0Directory.class);
when(exif.containsTag(ExifSubIFDDirectory.TAG_DATETIME_ORIGINAL)).thenReturn(true);
@@ -96,6 +104,7 @@ public class ImageMetadataExtractorTest
metadata.get(TikaCoreProperties.CREATED));
}
+ @Test
public void testCopyUnknownFieldsHandler() throws MetadataException {
Directory d = mock(Directory.class);
Tag t1 = mock(Tag.class);
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/ImageParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/ImageParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/ImageParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/ImageParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,20 +16,22 @@
*/
package org.apache.tika.parser.image;
+import static org.junit.Assert.assertEquals;
+
import java.io.InputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
+import org.junit.Test;
import org.xml.sax.helpers.DefaultHandler;
-import junit.framework.TestCase;
-
-public class ImageParserTest extends TestCase {
+public class ImageParserTest {
private final Parser parser = new ImageParser();
+ @Test
public void testBMP() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/bmp");
@@ -51,6 +53,7 @@ public class ImageParserTest extends Tes
assertEquals("8 8 8", metadata.get(Metadata.BITS_PER_SAMPLE));
}
+ @Test
public void testGIF() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/gif");
@@ -81,6 +84,7 @@ public class ImageParserTest extends Tes
assertEquals("Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements. See the NOTICE file distributed with this work for additional information regarding copyright ownership.", metadata.get(TikaCoreProperties.COMMENTS));
}
+ @Test
public void testJPEG() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/jpeg");
@@ -116,6 +120,7 @@ public class ImageParserTest extends Tes
assertEquals("Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements. See the NOTICE file distributed with this work for additional information regarding copyright ownership.", metadata.get(TikaCoreProperties.COMMENTS));
}
+ @Test
public void testPNG() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/png");
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/MetadataFieldsTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/MetadataFieldsTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/MetadataFieldsTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/MetadataFieldsTest.java Thu Dec 19 19:46:49 2013
@@ -16,13 +16,16 @@
*/
package org.apache.tika.parser.image;
+import static org.junit.Assert.assertFalse;
+import static org.junit.Assert.assertTrue;
+
import org.apache.tika.metadata.TIFF;
import org.apache.tika.metadata.TikaCoreProperties;
+import org.junit.Test;
-import junit.framework.TestCase;
-
-public class MetadataFieldsTest extends TestCase {
+public class MetadataFieldsTest {
+ @Test
public void testIsMetadataField() {
assertFalse(MetadataFields.isMetadataField("random string that is not a field"));
assertFalse(MetadataFields.isMetadataField("xyz"));
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/PSDParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/PSDParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/PSDParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/PSDParserTest.java Thu Dec 19 19:46:49 2013
@@ -21,19 +21,19 @@ import java.io.InputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
+import org.junit.Test;
import org.xml.sax.helpers.DefaultHandler;
-import junit.framework.TestCase;
-
import static junit.framework.Assert.assertEquals;
-public class PSDParserTest extends TestCase {
+public class PSDParserTest {
private final Parser parser = new PSDParser();
/**
* Tests a very basic file, without much metadata
*/
+ @Test
public void testPSD() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/x-psd");
@@ -50,6 +50,7 @@ public class PSDParserTest extends TestC
* Tests a very basic file, without much metadata,
* where some of the data lengths are padded to be even
*/
+ @Test
public void testOddPSD() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/x-psd");
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/TiffParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/TiffParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/TiffParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/TiffParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,22 +16,25 @@
*/
package org.apache.tika.parser.image;
-import junit.framework.TestCase;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.image.TiffParser;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
+import org.junit.Test;
import org.xml.sax.helpers.DefaultHandler;
import java.io.InputStream;
import java.util.Arrays;
import java.util.List;
-public class TiffParserTest extends TestCase {
+public class TiffParserTest {
private final Parser parser = new TiffParser();
+ @Test
public void testTIFF() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/tiff");
@@ -40,9 +43,9 @@ public class TiffParserTest extends Test
parser.parse(stream, new DefaultHandler(), metadata, new ParseContext());
assertEquals("Licensed to the Apache Software Foundation (ASF) under one or " +
- "more contributor license agreements. See the NOTICE file " +
- "distributed with this work for additional information regarding " +
- "copyright ownership.", metadata.get(TikaCoreProperties.DESCRIPTION));
+ "more contributor license agreements. See the NOTICE file " +
+ "distributed with this work for additional information regarding " +
+ "copyright ownership.", metadata.get(TikaCoreProperties.DESCRIPTION));
// All EXIF/TIFF tags
assertEquals("Inch", metadata.get(Metadata.RESOLUTION_UNIT));
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/xmp/JempboxExtractorTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/xmp/JempboxExtractorTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/xmp/JempboxExtractorTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/xmp/JempboxExtractorTest.java Thu Dec 19 19:46:49 2013
@@ -16,6 +16,9 @@
*/
package org.apache.tika.parser.image.xmp;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
+
import java.io.IOException;
import java.io.InputStream;
import java.util.Arrays;
@@ -25,11 +28,11 @@ import org.apache.tika.exception.TikaExc
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.image.xmp.JempboxExtractor;
+import org.junit.Test;
-import junit.framework.TestCase;
-
-public class JempboxExtractorTest extends TestCase {
+public class JempboxExtractorTest {
+ @Test
public void testParseJpeg() throws IOException, TikaException {
Metadata metadata = new Metadata();
InputStream stream = getClass().getResourceAsStream("/test-documents/testJPEG_commented.jpg");
@@ -61,6 +64,7 @@ public class JempboxExtractorTest extend
assertTrue(subject.contains("coast"));
}
+ @Test
public void testParseJpegPhotoshop() throws IOException, TikaException {
Metadata metadata = new Metadata();
InputStream stream = getClass().getResourceAsStream("/test-documents/testJPEG_commented_pspcs2mac.jpg");
@@ -77,6 +81,7 @@ public class JempboxExtractorTest extend
assertTrue(keywords.contains("coast"));
}
+ @Test
public void testParseJpegXnviewmp() throws IOException, TikaException {
Metadata metadata = new Metadata();
InputStream stream = getClass().getResourceAsStream("/test-documents/testJPEG_commented_xnviewmp026.jpg");
@@ -91,6 +96,7 @@ public class JempboxExtractorTest extend
assertTrue(keywords.contains("nature reserve"));
}
+ @Test
public void testJoinCreators() {
assertEquals("Mr B", new JempboxExtractor(null).joinCreators(
Arrays.asList("Mr B")));
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/iwork/AutoPageNumberUtilsTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/iwork/AutoPageNumberUtilsTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/iwork/AutoPageNumberUtilsTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/iwork/AutoPageNumberUtilsTest.java Thu Dec 19 19:46:49 2013
@@ -16,17 +16,20 @@
*/
package org.apache.tika.parser.iwork;
-import junit.framework.TestCase;
+import static org.junit.Assert.assertEquals;
+
+import org.junit.Test;
/**
* Test class for the <code>AutoPageNumberUtils</code> helper class.
*/
-public class AutoPageNumberUtilsTest extends TestCase {
+public class AutoPageNumberUtilsTest {
/**
* Check upper-case alpha-numeric numbers are generated based on the
* input page number.
*/
+ @Test
public void testAlphaUpper() {
assertEquals("A", AutoPageNumberUtils.asAlphaNumeric(1));
assertEquals("Z", AutoPageNumberUtils.asAlphaNumeric(26));
@@ -40,6 +43,7 @@ public class AutoPageNumberUtilsTest ext
* Check lower-case alpha-numeric numbers are generated based on the
* input page number.
*/
+ @Test
public void testAlphaLower() {
assertEquals("a", AutoPageNumberUtils.asAlphaNumericLower(1));
assertEquals("z", AutoPageNumberUtils.asAlphaNumericLower(26));
@@ -53,6 +57,7 @@ public class AutoPageNumberUtilsTest ext
* Check upper-case Roman numerals numbers are generated based on the
* input page number.
*/
+ @Test
public void testRomanUpper() {
assertEquals("I", AutoPageNumberUtils.asRomanNumerals(1));
assertEquals("XXVI", AutoPageNumberUtils.asRomanNumerals(26));
@@ -63,6 +68,7 @@ public class AutoPageNumberUtilsTest ext
* Check lower-case Roman numerals numbers are generated based on the
* input page number.
*/
+ @Test
public void testRomanLower() {
assertEquals("i", AutoPageNumberUtils.asRomanNumeralsLower(1));
assertEquals("xxvi", AutoPageNumberUtils.asRomanNumeralsLower(26));
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/iwork/IWorkParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/iwork/IWorkParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/iwork/IWorkParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/iwork/IWorkParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,35 +16,39 @@
*/
package org.apache.tika.parser.iwork;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
+
import java.io.InputStream;
import java.util.Arrays;
import java.util.List;
-import junit.framework.TestCase;
-
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Before;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
/**
* Tests if the IWork parser parses the content and metadata properly of the supported formats.
*/
-public class IWorkParserTest extends TestCase {
+public class IWorkParserTest {
private IWorkPackageParser iWorkParser;
private ParseContext parseContext;
- @Override
- protected void setUp() throws Exception {
+ @Before
+ public void setUp() {
iWorkParser = new IWorkPackageParser();
parseContext = new ParseContext();
parseContext.set(Parser.class, new AutoDetectParser());
}
+ @Test
public void testParseKeynote() throws Exception {
InputStream input = IWorkParserTest.class.getResourceAsStream("/test-documents/testKeynote.key");
Metadata metadata = new Metadata();
@@ -90,6 +94,7 @@ public class IWorkParserTest extends Tes
}
// TIKA-910
+ @Test
public void testKeynoteTextBoxes() throws Exception {
InputStream input = IWorkParserTest.class.getResourceAsStream("/test-documents/testTextBoxes.key");
Metadata metadata = new Metadata();
@@ -101,6 +106,7 @@ public class IWorkParserTest extends Tes
}
// TIKA-910
+ @Test
public void testKeynoteBulletPoints() throws Exception {
InputStream input = IWorkParserTest.class.getResourceAsStream("/test-documents/testBulletPoints.key");
Metadata metadata = new Metadata();
@@ -112,6 +118,7 @@ public class IWorkParserTest extends Tes
}
// TIKA-923
+ @Test
public void testKeynoteTables() throws Exception {
InputStream input = IWorkParserTest.class.getResourceAsStream("/test-documents/testTables.key");
Metadata metadata = new Metadata();
@@ -124,6 +131,7 @@ public class IWorkParserTest extends Tes
}
// TIKA-923
+ @Test
public void testKeynoteMasterSlideTable() throws Exception {
InputStream input = IWorkParserTest.class.getResourceAsStream("/test-documents/testMasterSlideTable.key");
Metadata metadata = new Metadata();
@@ -137,6 +145,7 @@ public class IWorkParserTest extends Tes
assertTrue(content.contains("master row 3"));
}
+ @Test
public void testParsePages() throws Exception {
InputStream input = IWorkParserTest.class.getResourceAsStream("/test-documents/testPages.pages");
Metadata metadata = new Metadata();
@@ -185,6 +194,7 @@ public class IWorkParserTest extends Tes
}
// TIKA-904
+ @Test
public void testPagesLayoutMode() throws Exception {
InputStream input = IWorkParserTest.class.getResourceAsStream("/test-documents/testPagesLayout.pages");
Metadata metadata = new Metadata();
@@ -200,6 +210,7 @@ public class IWorkParserTest extends Tes
assertTrue(content.contains("text inside of a green circle"));
}
+ @Test
public void testParseNumbers() throws Exception {
InputStream input = IWorkParserTest.class.getResourceAsStream("/test-documents/testNumbers.numbers");
Metadata metadata = new Metadata();
@@ -239,6 +250,7 @@ public class IWorkParserTest extends Tes
}
// TIKA- 924
+ @Test
public void testParseNumbersTableNames() throws Exception {
InputStream input = IWorkParserTest.class.getResourceAsStream("/test-documents/tableNames.numbers");
Metadata metadata = new Metadata();
@@ -248,6 +260,7 @@ public class IWorkParserTest extends Tes
assertTrue(content.contains("This is the main table"));
}
+ @Test
public void testParseNumbersTableHeaders() throws Exception {
InputStream input = IWorkParserTest.class.getResourceAsStream("/test-documents/tableHeaders.numbers");
Metadata metadata = new Metadata();
@@ -268,6 +281,7 @@ public class IWorkParserTest extends Tes
* we don't know how the encryption works (it's not regular Zip
* Encryption). See TIKA-903 for details
*/
+ @Test
public void testParsePagesPasswordProtected() throws Exception {
// Document password is "tika", but we can't use that yet...
InputStream input = IWorkParserTest.class.getResourceAsStream("/test-documents/testPagesPwdProtected.pages");
@@ -287,6 +301,7 @@ public class IWorkParserTest extends Tes
/**
* Check we get headers, footers and footnotes from Pages
*/
+ @Test
public void testParsePagesHeadersFootersFootnotes() throws Exception {
String footnote = "Footnote: Do a lot of people really use iWork?!?!";
String header = "THIS IS SOME HEADER TEXT";
@@ -315,6 +330,7 @@ public class IWorkParserTest extends Tes
/**
* Check we get upper-case Roman numerals within the footer for AutoPageNumber.
*/
+ @Test
public void testParsePagesHeadersFootersRomanUpper() throws Exception {
String header = "THIS IS SOME HEADER TEXT";
String footer = "THIS IS SOME FOOTER TEXT\tI";
@@ -335,6 +351,7 @@ public class IWorkParserTest extends Tes
/**
* Check we get lower-case Roman numerals within the footer for AutoPageNumber.
*/
+ @Test
public void testParsePagesHeadersFootersRomanLower() throws Exception {
String header = "THIS IS SOME HEADER TEXT";
String footer = "THIS IS SOME FOOTER TEXT\ti";
@@ -355,6 +372,7 @@ public class IWorkParserTest extends Tes
/**
* Check we get upper-case alpha-numeric letters within the footer for AutoPageNumber.
*/
+ @Test
public void testParsePagesHeadersAlphaUpper() throws Exception {
String header = "THIS IS SOME HEADER TEXT\tA";
String footer = "THIS IS SOME FOOTER TEXT\tA";
@@ -375,6 +393,7 @@ public class IWorkParserTest extends Tes
/**
* Check we get lower-case alpha-numeric letters within the footer for AutoPageNumber.
*/
+ @Test
public void testParsePagesHeadersAlphaLower() throws Exception {
String header = "THIS IS SOME HEADER TEXT";
String footer = "THIS IS SOME FOOTER TEXT\ta";
@@ -395,6 +414,7 @@ public class IWorkParserTest extends Tes
/**
* Check we get annotations (eg comments) from Pages
*/
+ @Test
public void testParsePagesAnnotations() throws Exception {
String commentA = "comment about the APXL file";
String commentB = "comment about UIMA";
@@ -417,6 +437,7 @@ public class IWorkParserTest extends Tes
}
// TIKA-918
+ @Test
public void testNumbersExtractChartNames() throws Exception {
InputStream input = IWorkParserTest.class.getResourceAsStream("/test-documents/testNumbersCharts.numbers");
Metadata metadata = new Metadata();
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/jpeg/JpegParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/jpeg/JpegParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/jpeg/JpegParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/jpeg/JpegParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,22 +16,27 @@
*/
package org.apache.tika.parser.jpeg;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertFalse;
+import static org.junit.Assert.assertTrue;
+
import java.io.InputStream;
import java.util.Arrays;
import java.util.List;
-import junit.framework.TestCase;
-
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TIFF;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
+import org.junit.Test;
import org.xml.sax.helpers.DefaultHandler;
-public class JpegParserTest extends TestCase {
+public class JpegParserTest {
+
private final Parser parser = new JpegParser();
+ @Test
public void testJPEG() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/jpeg");
@@ -82,6 +87,7 @@ public class JpegParserTest extends Test
/**
* Test for a file with Geographic information (lat, long etc) in it
*/
+ @Test
public void testJPEGGeo() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/jpeg");
@@ -128,6 +134,7 @@ public class JpegParserTest extends Test
* different way, see TIKA-915 for details
* Disabled for now, pending a fix to the underlying library
*/
+ @Test
public void testJPEGGeo2() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/jpeg");
@@ -140,6 +147,7 @@ public class JpegParserTest extends Test
assertEquals("-1.567886", metadata.get(Metadata.LONGITUDE));
}
+ @Test
public void testJPEGTitleAndDescription() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/jpeg");
@@ -178,6 +186,7 @@ public class JpegParserTest extends Test
assertEquals("Inch", metadata.get(Metadata.RESOLUTION_UNIT));
}
+ @Test
public void testJPEGTitleAndDescriptionPhotoshop() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/jpeg");
@@ -195,6 +204,7 @@ public class JpegParserTest extends Test
assertTrue("got " + subject, subject.contains("bird watching"));
}
+ @Test
public void testJPEGTitleAndDescriptionXnviewmp() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/jpeg");
@@ -213,6 +223,7 @@ public class JpegParserTest extends Test
assertTrue("'nature reserve'" + " not in " + keywords, keywords.contains("nature reserve"));
}
+ @Test
public void testJPEGoddTagComponent() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/jpeg");
@@ -226,6 +237,7 @@ public class JpegParserTest extends Test
assertEquals("384", metadata.get(Metadata.IMAGE_LENGTH));
}
+ @Test
public void testJPEGEmptyEXIFDateTime() throws Exception {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/jpeg");
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,6 +16,10 @@
*/
package org.apache.tika.parser.mail;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertFalse;
+import static org.junit.Assert.assertTrue;
+import static org.junit.Assert.fail;
import static org.mockito.Matchers.any;
import static org.mockito.Matchers.eq;
import static org.mockito.Mockito.mock;
@@ -26,8 +30,6 @@ import static org.mockito.Mockito.verify
import java.io.ByteArrayInputStream;
import java.io.InputStream;
-import junit.framework.TestCase;
-
import org.apache.james.mime4j.stream.MimeConfig;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
@@ -36,12 +38,14 @@ import org.apache.tika.parser.ParseConte
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.XHTMLContentHandler;
+import org.junit.Test;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.helpers.DefaultHandler;
-public class RFC822ParserTest extends TestCase {
+public class RFC822ParserTest {
+ @Test
public void testSimple() {
Parser parser = new RFC822Parser();
Metadata metadata = new Metadata();
@@ -69,6 +73,7 @@ public class RFC822ParserTest extends Te
}
}
+ @Test
public void testMultipart() {
Parser parser = new RFC822Parser();
Metadata metadata = new Metadata();
@@ -106,6 +111,7 @@ public class RFC822ParserTest extends Te
}
}
+ @Test
public void testQuotedPrintable() {
Parser parser = new RFC822Parser();
Metadata metadata = new Metadata();
@@ -125,6 +131,7 @@ public class RFC822ParserTest extends Te
}
}
+ @Test
public void testBase64() {
Parser parser = new RFC822Parser();
Metadata metadata = new Metadata();
@@ -140,6 +147,7 @@ public class RFC822ParserTest extends Te
}
}
+ @Test
public void testI18NHeaders() {
Parser parser = new RFC822Parser();
Metadata metadata = new Metadata();
@@ -165,6 +173,7 @@ public class RFC822ParserTest extends Te
* The from isn't in the usual form.
* See TIKA-618
*/
+ @Test
public void testUnusualFromAddress() throws Exception {
Parser parser = new RFC822Parser();
Metadata metadata = new Metadata();
@@ -183,6 +192,7 @@ public class RFC822ParserTest extends Te
/**
* Test for TIKA-640, increase header max beyond 10k bytes
*/
+ @Test
public void testLongHeader() throws Exception {
StringBuilder inputBuilder = new StringBuilder();
for (int i = 0; i < 2000; ++i) {
@@ -216,6 +226,7 @@ public class RFC822ParserTest extends Te
/**
* Test for TIKA-678 - not all headers may be present
*/
+ @Test
public void testSomeMissingHeaders() throws Exception {
Parser parser = new RFC822Parser();
Metadata metadata = new Metadata();
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/mbox/MboxParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/mbox/MboxParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/mbox/MboxParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/mbox/MboxParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,6 +16,8 @@
*/
package org.apache.tika.parser.mbox;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.fail;
import static org.mockito.Matchers.any;
import static org.mockito.Matchers.eq;
import static org.mockito.Mockito.mock;
@@ -24,19 +26,19 @@ import static org.mockito.Mockito.verify
import java.io.InputStream;
-import junit.framework.TestCase;
-
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.XHTMLContentHandler;
+import org.junit.Test;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.helpers.DefaultHandler;
-public class MboxParserTest extends TestCase {
+public class MboxParserTest {
+ @Test
public void testSimple() {
Parser parser = new MboxParser();
Metadata metadata = new Metadata();
@@ -56,6 +58,7 @@ public class MboxParserTest extends Test
}
}
+ @Test
public void testHeaders() {
Parser parser = new MboxParser();
Metadata metadata = new Metadata();
@@ -83,6 +86,7 @@ public class MboxParserTest extends Test
}
}
+ @Test
public void testMultilineHeader() {
Parser parser = new MboxParser();
Metadata metadata = new Metadata();
@@ -103,6 +107,7 @@ public class MboxParserTest extends Test
}
}
+ @Test
public void testQuoted() {
Parser parser = new MboxParser();
Metadata metadata = new Metadata();
@@ -125,6 +130,7 @@ public class MboxParserTest extends Test
}
}
+ @Test
public void testComplex() {
Parser parser = new MboxParser();
Metadata metadata = new Metadata();
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/AbstractPOIContainerExtractionTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/AbstractPOIContainerExtractionTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/AbstractPOIContainerExtractionTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/AbstractPOIContainerExtractionTest.java Thu Dec 19 19:46:49 2013
@@ -16,13 +16,14 @@
*/
package org.apache.tika.parser.microsoft;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertNotNull;
+
import java.io.InputStream;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
-import junit.framework.TestCase;
-
import org.apache.tika.extractor.ContainerExtractor;
import org.apache.tika.extractor.EmbeddedResourceHandler;
import org.apache.tika.io.TikaInputStream;
@@ -32,7 +33,7 @@ import org.apache.tika.mime.MediaType;
* Parent class of tests that the various POI powered parsers are
* able to extract their embedded contents.
*/
-public abstract class AbstractPOIContainerExtractionTest extends TestCase {
+public abstract class AbstractPOIContainerExtractionTest {
public static final MediaType TYPE_DOC = MediaType.application("msword");
public static final MediaType TYPE_PPT = MediaType.application("vnd.ms-powerpoint");
public static final MediaType TYPE_XLS = MediaType.application("vnd.ms-excel");
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,11 +16,13 @@
*/
package org.apache.tika.parser.microsoft;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertFalse;
+import static org.junit.Assert.assertTrue;
+
import java.io.InputStream;
import java.util.Locale;
-import junit.framework.TestCase;
-
import org.apache.tika.detect.DefaultDetector;
import org.apache.tika.detect.Detector;
import org.apache.tika.metadata.Metadata;
@@ -31,9 +33,12 @@ import org.apache.tika.parser.AutoDetect
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.microsoft.ooxml.OOXMLParser;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
-public class ExcelParserTest extends TestCase {
+public class ExcelParserTest {
+
+ @Test
public void testExcelParser() throws Exception {
InputStream input = ExcelParserTest.class.getResourceAsStream(
"/test-documents/testEXCEL.xls");
@@ -72,6 +77,7 @@ public class ExcelParserTest extends Tes
}
}
+ @Test
public void testExcelParserFormatting() throws Exception {
InputStream input = ExcelParserTest.class.getResourceAsStream(
"/test-documents/testEXCEL-formats.xls");
@@ -147,6 +153,7 @@ public class ExcelParserTest extends Tes
/**
* TIKA-214 - Ensure we extract labels etc from Charts
*/
+ @Test
public void testExcelParserCharts() throws Exception {
InputStream input = ExcelParserTest.class.getResourceAsStream(
"/test-documents/testEXCEL-charts.xls");
@@ -184,6 +191,7 @@ public class ExcelParserTest extends Tes
}
}
+ @Test
public void testJXL() throws Exception {
InputStream input = ExcelParserTest.class.getResourceAsStream(
"/test-documents/jxl.xls");
@@ -204,6 +212,7 @@ public class ExcelParserTest extends Tes
}
}
+ @Test
public void testWorksSpreadsheet70() throws Exception {
InputStream input = ExcelParserTest.class.getResourceAsStream(
"/test-documents/testWORKSSpreadsheet7.0.xlr");
@@ -226,6 +235,7 @@ public class ExcelParserTest extends Tes
* (an OOXML container with binary blobs), but we
* shouldn't break on these files either (TIKA-826)
*/
+ @Test
public void testExcelXLSB() throws Exception {
Detector detector = new DefaultDetector();
AutoDetectParser parser = new AutoDetectParser();
@@ -270,6 +280,7 @@ public class ExcelParserTest extends Tes
* We don't currently support the old Excel 95 .xls file format,
* but we shouldn't break on these files either (TIKA-976)
*/
+ @Test
public void testExcel95() throws Exception {
Detector detector = new DefaultDetector();
AutoDetectParser parser = new AutoDetectParser();
@@ -313,6 +324,7 @@ public class ExcelParserTest extends Tes
/**
* Ensures that custom OLE2 (HPSF) properties are extracted
*/
+ @Test
public void testCustomProperties() throws Exception {
InputStream input = ExcelParserTest.class.getResourceAsStream(
"/test-documents/testEXCEL_custom_props.xls");
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,6 +16,10 @@
*/
package org.apache.tika.parser.microsoft;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertFalse;
+import static org.junit.Assert.assertTrue;
+
import java.io.InputStream;
import java.io.StringWriter;
import java.util.regex.Matcher;
@@ -26,21 +30,21 @@ import javax.xml.transform.sax.SAXTransf
import javax.xml.transform.sax.TransformerHandler;
import javax.xml.transform.stream.StreamResult;
-import junit.framework.TestCase;
-
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
/**
* Test case for parsing Outlook files.
*/
-public class OutlookParserTest extends TestCase {
+public class OutlookParserTest {
+ @Test
public void testOutlookParsing() throws Exception {
Parser parser = new AutoDetectParser(); // Should auto-detect!
ContentHandler handler = new BodyContentHandler();
@@ -88,6 +92,7 @@ public class OutlookParserTest extends T
*
* @see <a href="https://issues.apache.org/jira/browse/TIKA-197">TIKA-197</a>
*/
+ @Test
public void testMultipleCopies() throws Exception {
Parser parser = new AutoDetectParser();
ContentHandler handler = new BodyContentHandler();
@@ -117,6 +122,7 @@ public class OutlookParserTest extends T
*
* @see <a href="https://issues.apache.org/jira/browse/TIKA-395">TIKA-395</a>
*/
+ @Test
public void testOutlookNew() throws Exception {
Parser parser = new AutoDetectParser();
ContentHandler handler = new BodyContentHandler();
@@ -143,6 +149,7 @@ public class OutlookParserTest extends T
assertTrue(content.contains("Navigation Pane"));
}
+ @Test
public void testOutlookHTMLVersion() throws Exception {
Parser parser = new AutoDetectParser();
Metadata metadata = new Metadata();
@@ -177,6 +184,7 @@ public class OutlookParserTest extends T
assertEquals(2, content.split("<\\/body>").length);
}
+ @Test
public void testOutlookForwarded() throws Exception {
Parser parser = new AutoDetectParser();
Metadata metadata = new Metadata();
@@ -204,6 +212,7 @@ public class OutlookParserTest extends T
assertEquals(2, content.split("<\\/body>").length);
}
+ @Test
public void testOutlookHTMLfromRTF() throws Exception {
Parser parser = new AutoDetectParser();
Metadata metadata = new Metadata();
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java Thu Dec 19 19:46:49 2013
@@ -16,9 +16,14 @@
*/
package org.apache.tika.parser.microsoft;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertNull;
+import static org.junit.Assert.assertTrue;
+
import org.apache.tika.extractor.ContainerExtractor;
import org.apache.tika.extractor.ParserContainerExtractor;
import org.apache.tika.mime.MediaType;
+import org.junit.Test;
/**
* Tests that the various POI powered parsers are
@@ -29,6 +34,7 @@ public class POIContainerExtractionTest
/**
* For office files which don't have anything embedded in them
*/
+ @Test
public void testWithoutEmbedded() throws Exception {
ContainerExtractor extractor = new ParserContainerExtractor();
@@ -55,6 +61,7 @@ public class POIContainerExtractionTest
* Office files with embedded images, but no other
* office files in them
*/
+ @Test
public void testEmbeddedImages() throws Exception {
ContainerExtractor extractor = new ParserContainerExtractor();
TrackingHandler handler;
@@ -107,6 +114,7 @@ public class POIContainerExtractionTest
* -> excel
* -> image
*/
+ @Test
public void testEmbeddedOfficeFiles() throws Exception {
ContainerExtractor extractor = new ParserContainerExtractor();
TrackingHandler handler;
@@ -267,6 +275,7 @@ public class POIContainerExtractionTest
assertEquals(TYPE_PDF, handler.mediaTypes.get(1));
}
+ @Test
public void testEmbeddedOfficeFilesXML() throws Exception {
ContainerExtractor extractor = new ParserContainerExtractor();
TrackingHandler handler;
@@ -276,6 +285,7 @@ public class POIContainerExtractionTest
assertEquals(2, handler.filenames.size());
}
+ @Test
public void testPowerpointImages() throws Exception {
ContainerExtractor extractor = new ParserContainerExtractor();
TrackingHandler handler;
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,6 +16,9 @@
*/
package org.apache.tika.parser.microsoft;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
+
import java.io.InputStream;
import java.util.Locale;
@@ -26,10 +29,12 @@ import org.apache.tika.metadata.OfficeOp
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
public class PowerPointParserTest extends TikaTest {
+ @Test
public void testPowerPointParser() throws Exception {
InputStream input = PowerPointParserTest.class.getResourceAsStream(
"/test-documents/testPPT.ppt");
@@ -52,6 +57,7 @@ public class PowerPointParserTest extend
}
}
+ @Test
public void testVarious() throws Exception {
ContentHandler handler = new BodyContentHandler();
Metadata metadata = new Metadata();
@@ -124,6 +130,7 @@ public class PowerPointParserTest extend
assertContains("\uD800\uDF32\uD800\uDF3f\uD800\uDF44\uD800\uDF39\uD800\uDF43\uD800\uDF3A", content);
}
+ @Test
public void testMasterFooter() throws Exception {
ContentHandler handler = new BodyContentHandler();
Metadata metadata = new Metadata();
@@ -147,6 +154,7 @@ public class PowerPointParserTest extend
}
// TODO: once we fix TIKA-712, re-enable this
+ @Test
public void testMasterText() throws Exception {
ContentHandler handler = new BodyContentHandler();
Metadata metadata = new Metadata();
@@ -170,6 +178,7 @@ public class PowerPointParserTest extend
}
// TODO: once we fix TIKA-712, re-enable this
+ @Test
public void testMasterText2() throws Exception {
ContentHandler handler = new BodyContentHandler();
Metadata metadata = new Metadata();
@@ -194,6 +203,7 @@ public class PowerPointParserTest extend
/**
* Ensures that custom OLE2 (HPSF) properties are extracted
*/
+ @Test
public void testCustomProperties() throws Exception {
InputStream input = PowerPointParserTest.class.getResourceAsStream(
"/test-documents/testPPT_custom_props.ppt");
@@ -227,6 +237,7 @@ public class PowerPointParserTest extend
}
// TIKA-1025
+ @Test
public void testEmbeddedPlacedholder() throws Exception {
XMLResult result = getXML("testPPT_embedded2.ppt");
assertContains("<div class=\"embedded\" id=\"1\" />", result.xml);
@@ -234,6 +245,7 @@ public class PowerPointParserTest extend
}
// TIKA-817
+ @Test
public void testAutoDatePPT() throws Exception {
//decision was made in POI-52367 not to generate
//autodate automatically. For pptx, where value is stored,
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ProjectParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ProjectParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ProjectParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ProjectParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,6 +16,8 @@
*/
package org.apache.tika.parser.microsoft;
+import static org.junit.Assert.assertEquals;
+
import java.io.InputStream;
import org.apache.tika.metadata.Metadata;
@@ -25,17 +27,18 @@ import org.apache.tika.metadata.OfficeOp
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
-import junit.framework.TestCase;
-
/**
* Tests for Microsoft Project (MPP) Files.
*
* Note - we don't currently have a dedicated Project
* Parser, all we have is the common office metadata
*/
-public class ProjectParserTest extends TestCase {
+public class ProjectParserTest {
+
+ @Test
public void testProject2003() throws Exception {
InputStream input = ProjectParserTest.class.getResourceAsStream(
"/test-documents/testPROJECT2003.mpp");
@@ -46,6 +49,7 @@ public class ProjectParserTest extends T
}
}
+ @Test
public void testProject2007() throws Exception {
InputStream input = ProjectParserTest.class.getResourceAsStream(
"/test-documents/testPROJECT2007.mpp");
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PublisherParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PublisherParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PublisherParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PublisherParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,18 +16,21 @@
*/
package org.apache.tika.parser.microsoft;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
+
import java.io.InputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
-import junit.framework.TestCase;
-
-public class PublisherParserTest extends TestCase {
+public class PublisherParserTest {
+ @Test
public void testPublisherParser() throws Exception {
InputStream input = PublisherParserTest.class.getResourceAsStream(
"/test-documents/testPUBLISHER.pub");
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/TNEFParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/TNEFParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/TNEFParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/TNEFParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,6 +16,8 @@
*/
package org.apache.tika.parser.microsoft;
+import static org.junit.Assert.assertEquals;
+
import org.apache.tika.detect.DefaultDetector;
import org.apache.tika.detect.Detector;
import org.apache.tika.extractor.ContainerExtractor;
@@ -26,6 +28,7 @@ import org.apache.tika.metadata.TikaCore
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
/**
@@ -34,6 +37,7 @@ import org.xml.sax.ContentHandler;
public class TNEFParserTest extends AbstractPOIContainerExtractionTest {
private static final String file = "testWINMAIL.dat";
+ @Test
public void testBasics() throws Exception {
TikaInputStream stream = getTestFile(file);
Detector detector = new DefaultDetector();
@@ -46,6 +50,7 @@ public class TNEFParserTest extends Abst
}
}
+ @Test
public void testMetadata() throws Exception {
TikaInputStream stream = getTestFile(file);
@@ -63,6 +68,7 @@ public class TNEFParserTest extends Abst
* Check the Rtf and Attachments are returned
* as expected
*/
+ @Test
public void testBodyAndAttachments() throws Exception {
ContainerExtractor extractor = new ParserContainerExtractor();
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/VisioParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/VisioParserTest.java?rev=1552405&r1=1552404&r2=1552405&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/VisioParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/VisioParserTest.java Thu Dec 19 19:46:49 2013
@@ -16,18 +16,21 @@
*/
package org.apache.tika.parser.microsoft;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
+
import java.io.InputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
import org.xml.sax.ContentHandler;
-import junit.framework.TestCase;
-
-public class VisioParserTest extends TestCase {
+public class VisioParserTest {
+ @Test
public void testVisioParser() throws Exception {
InputStream input = VisioParserTest.class.getResourceAsStream(
"/test-documents/testVISIO.vsd");