You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2015/05/29 16:36:24 UTC
svn commit: r1682489 [10/14] - in /tika/trunk:
tika-parsers/src/main/java/org/apache/tika/parser/html/
tika-parsers/src/main/java/org/apache/tika/parser/image/
tika-parsers/src/main/java/org/apache/tika/parser/image/xmp/
tika-parsers/src/main/java/org/...
Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/txt/CharsetRecognizer.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/txt/CharsetRecognizer.java?rev=1682489&r1=1682488&r2=1682489&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/txt/CharsetRecognizer.java (original)
+++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/txt/CharsetRecognizer.java Fri May 29 14:36:21 2015
@@ -1,25 +1,25 @@
/**
-*******************************************************************************
-* Copyright (C) 2005, International Business Machines Corporation and *
-* others. All Rights Reserved. *
-*******************************************************************************
-*/
+ * ******************************************************************************
+ * Copyright (C) 2005, International Business Machines Corporation and *
+ * others. All Rights Reserved. *
+ * ******************************************************************************
+ */
package org.apache.tika.parser.txt;
/**
* Abstract class for recognizing a single charset.
* Part of the implementation of ICU's CharsetDetector.
- *
+ *
* Each specific charset that can be recognized will have an instance
* of some subclass of this class. All interaction between the overall
* CharsetDetector and the stuff specific to an individual charset happens
* via the interface provided here.
- *
+ *
* Instances of CharsetDetector DO NOT have or maintain
* state pertaining to a specific match or detect operation.
* The WILL be shared by multiple instances of CharsetDetector.
* They encapsulate const charset-specific information.
- *
+ *
* @internal
*/
abstract class CharsetRecognizer {
@@ -27,29 +27,28 @@ abstract class CharsetRecognizer {
* Get the IANA name of this charset.
* @return the charset name.
*/
- abstract String getName();
-
+ abstract String getName();
+
/**
* Get the ISO language code for this charset.
* @return the language code, or <code>null</code> if the language cannot be determined.
*/
- public String getLanguage()
- {
+ public String getLanguage() {
return null;
}
-
+
/**
* Test the match of this charset with the input text data
* which is obtained via the CharsetDetector object.
- *
+ *
* @param det The CharsetDetector, which contains the input text
* to be checked for being in this charset.
- * @return Two values packed into one int (Damn java, anyhow)
+ * @return Two values packed into one int (Damn java, anyhow)
* <br/>
* bits 0-7: the match confidence, ranging from 0-100
* <br/>
* bits 8-15: The match reason, an enum-like value.
*/
- abstract int match(CharsetDetector det);
+ abstract int match(CharsetDetector det);
}
Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/txt/Icu4jEncodingDetector.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/txt/Icu4jEncodingDetector.java?rev=1682489&r1=1682488&r2=1682489&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/txt/Icu4jEncodingDetector.java (original)
+++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/txt/Icu4jEncodingDetector.java Fri May 29 14:36:21 2015
@@ -5,9 +5,9 @@
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
+ * <p/>
+ * http://www.apache.org/licenses/LICENSE-2.0
+ * <p/>
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/txt/TXTParser.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/txt/TXTParser.java?rev=1682489&r1=1682488&r2=1682489&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/txt/TXTParser.java (original)
+++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/txt/TXTParser.java Fri May 29 14:36:21 2015
@@ -40,20 +40,22 @@ import org.xml.sax.SAXException;
* beginning of the stream and the given document metadata, most
* notably the <code>charset</code> parameter of a
* {@link org.apache.tika.metadata.HttpHeaders#CONTENT_TYPE} value.
- * <p>
+ * <p/>
* This parser sets the following output metadata entries:
* <dl>
- * <dt>{@link org.apache.tika.metadata.HttpHeaders#CONTENT_TYPE}</dt>
- * <dd><code>text/plain; charset=...</code></dd>
+ * <dt>{@link org.apache.tika.metadata.HttpHeaders#CONTENT_TYPE}</dt>
+ * <dd><code>text/plain; charset=...</code></dd>
* </dl>
*/
public class TXTParser extends AbstractParser {
- /** Serial version UID */
+ /**
+ * Serial version UID
+ */
private static final long serialVersionUID = -6656102320836888910L;
private static final Set<MediaType> SUPPORTED_TYPES =
- Collections.singleton(MediaType.TEXT_PLAIN);
+ Collections.singleton(MediaType.TEXT_PLAIN);
private static final ServiceLoader LOADER =
new ServiceLoader(TXTParser.class.getClassLoader());
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/RecursiveParserWrapperTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/RecursiveParserWrapperTest.java?rev=1682489&r1=1682488&r2=1682489&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/RecursiveParserWrapperTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/RecursiveParserWrapperTest.java Fri May 29 14:36:21 2015
@@ -76,12 +76,12 @@ public class RecursiveParserWrapperTest
assertNull(content);
}
-
+
@Test
public void testCharLimit() throws Exception {
ParseContext context = new ParseContext();
Metadata metadata = new Metadata();
-
+
Parser wrapped = new AutoDetectParser();
RecursiveParserWrapper wrapper = new RecursiveParserWrapper(wrapped,
new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.TEXT, 60));
@@ -89,19 +89,20 @@ public class RecursiveParserWrapperTest
"/test-documents/test_recursive_embedded.docx");
wrapper.parse(stream, new DefaultHandler(), metadata, context);
List<Metadata> list = wrapper.getMetadata();
-
+
assertEquals(5, list.size());
-
+
int wlr = 0;
for (Metadata m : list) {
String limitReached = m.get(RecursiveParserWrapper.WRITE_LIMIT_REACHED);
- if (limitReached != null && limitReached.equals("true")){
+ if (limitReached != null && limitReached.equals("true")) {
wlr++;
}
}
assertEquals(1, wlr);
}
+
@Test
public void testMaxEmbedded() throws Exception {
int maxEmbedded = 4;
@@ -109,7 +110,7 @@ public class RecursiveParserWrapperTest
ParseContext context = new ParseContext();
Metadata metadata = new Metadata();
String limitReached = null;
-
+
Parser wrapped = new AutoDetectParser();
RecursiveParserWrapper wrapper = new RecursiveParserWrapper(wrapped,
new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.TEXT, -1));
@@ -124,7 +125,7 @@ public class RecursiveParserWrapperTest
limitReached = list.get(0).get(RecursiveParserWrapper.EMBEDDED_RESOURCE_LIMIT_REACHED);
assertNull(limitReached);
-
+
wrapper.reset();
stream.close();
@@ -137,29 +138,29 @@ public class RecursiveParserWrapperTest
list = wrapper.getMetadata();
//add 1 for outer container file
- assertEquals(maxEmbedded+1, list.size());
-
+ assertEquals(maxEmbedded + 1, list.size());
+
limitReached = list.get(0).get(RecursiveParserWrapper.EMBEDDED_RESOURCE_LIMIT_REACHED);
assertEquals("true", limitReached);
wrapper.reset();
stream.close();
-
+
//test setting value < 0
metadata = new Metadata();
stream = RecursiveParserWrapperTest.class.getResourceAsStream(
"/test-documents/test_recursive_embedded.docx");
-
+
wrapper.setMaxEmbeddedResources(-2);
wrapper.parse(stream, new DefaultHandler(), metadata, context);
assertEquals(totalNoLimit, list.size());
limitReached = list.get(0).get(RecursiveParserWrapper.EMBEDDED_RESOURCE_LIMIT_REACHED);
assertNull(limitReached);
}
-
+
@Test
public void testEmbeddedResourcePath() throws Exception {
-
+
Set<String> targets = new HashSet<String>();
targets.add("test_recursive_embedded.docx/embed1.zip");
targets.add("test_recursive_embedded.docx/embed1.zip/embed2.zip");
@@ -172,15 +173,15 @@ public class RecursiveParserWrapperTest
targets.add("test_recursive_embedded.docx/embed1.zip/embed1b.txt");
targets.add("test_recursive_embedded.docx/embed1.zip/embed1a.txt");
targets.add("test_recursive_embedded.docx/image1.emf");
-
+
Metadata metadata = new Metadata();
metadata.set(Metadata.RESOURCE_NAME_KEY, "test_recursive_embedded.docx");
List<Metadata> list = getMetadata(metadata,
new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.XML, -1));
Metadata container = list.get(0);
String content = container.get(RecursiveParserWrapper.TIKA_CONTENT);
- assertTrue(content.indexOf("<p class=\"header\" />") > -1);
-
+ assertTrue(content.indexOf("<p class=\"header\" />") > -1);
+
Set<String> seen = new HashSet<String>();
for (Metadata m : list) {
String path = m.get(RecursiveParserWrapper.EMBEDDED_RESOURCE_PATH);
@@ -224,7 +225,7 @@ public class RecursiveParserWrapperTest
if (path == null) {
path = "/test-documents/test_recursive_embedded.docx";
} else {
- path = "/test-documents/"+path;
+ path = "/test-documents/" + path;
}
InputStream stream = null;
try {
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=1682489&r1=1682488&r2=1682489&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 Fri May 29 14:36:21 2015
@@ -157,6 +157,7 @@ public class HtmlParserTest {
/**
* Test case for TIKA-210
+ *
* @see <a href="https://issues.apache.org/jira/browse/TIKA-210">TIKA-210</a>
*/
@Test
@@ -169,6 +170,7 @@ public class HtmlParserTest {
/**
* Test case for TIKA-287
+ *
* @see <a href="https://issues.apache.org/jira/browse/TIKA-287">TIKA-287</a>
*/
@Test
@@ -216,8 +218,8 @@ public class HtmlParserTest {
private void assertRelativeLink(String url, String base, String relative)
throws Exception {
String test =
- "<html><head><base href=\"" + base + "\"></head>"
- + "<body><a href=\"" + relative + "\">test</a></body></html>";
+ "<html><head><base href=\"" + base + "\"></head>"
+ + "<body><a href=\"" + relative + "\">test</a></body></html>";
final List<String> links = new ArrayList<String>();
new HtmlParser().parse(
new ByteArrayInputStream(test.getBytes(IOUtils.UTF_8)),
@@ -238,12 +240,13 @@ public class HtmlParserTest {
/**
* 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>";
+ "<html><body><table><tr><td>a</td><td>b</td></table></body></html>";
String content = new Tika().parseToString(
new ByteArrayInputStream(test.getBytes(IOUtils.UTF_8)));
assertContains("a", content);
@@ -253,15 +256,16 @@ public class HtmlParserTest {
/**
* 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\""
- + " content=\"text/html; charset=ISO-8859-1\" />"
- + "<title>the name is \u00e1ndre</title>"
- + "</head><body></body></html>";
+ "<html><head><meta http-equiv=\"content-type\""
+ + " content=\"text/html; charset=ISO-8859-1\" />"
+ + "<title>the name is \u00e1ndre</title>"
+ + "</head><body></body></html>";
Metadata metadata = new Metadata();
new HtmlParser().parse(
new ByteArrayInputStream(test.getBytes("ISO-8859-1")),
@@ -271,14 +275,15 @@ public class HtmlParserTest {
/**
* 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\" />"
- + "<title>the name is \u00e1ndre</title>"
- + "</head><body></body></html>";
+ + "<title>the name is \u00e1ndre</title>"
+ + "</head><body></body></html>";
Metadata metadata = new Metadata();
new HtmlParser().parse(
new ByteArrayInputStream(test.getBytes("ISO-8859-1")),
@@ -288,40 +293,42 @@ public class HtmlParserTest {
/**
* 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>";
+ "<html><head><title>\u017d</title></head><body></body></html>";
Metadata metadata = new Metadata();
- new HtmlParser().parse (
+ new HtmlParser().parse(
new ByteArrayInputStream(test.getBytes(IOUtils.UTF_8)),
- new BodyContentHandler(), metadata, new ParseContext());
+ new BodyContentHandler(), metadata, new ParseContext());
assertEquals("\u017d", metadata.get(TikaCoreProperties.TITLE));
}
/**
* 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>"
- + "<body></body></html>";
+ "<html><head><title>the name is \u00e1ndre</title></head>"
+ + "<body></body></html>";
Metadata metadata = new Metadata();
- new HtmlParser().parse (
+ new HtmlParser().parse(
new ByteArrayInputStream(test.getBytes(IOUtils.UTF_8)),
- new BodyContentHandler(), metadata, new ParseContext());
+ new BodyContentHandler(), metadata, new ParseContext());
assertEquals("UTF-8", metadata.get(Metadata.CONTENT_ENCODING));
metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "text/html; charset=ISO-8859-1");
- new HtmlParser().parse (
+ new HtmlParser().parse(
new ByteArrayInputStream(test.getBytes("ISO-8859-1")),
- new BodyContentHandler(), metadata, new ParseContext());
+ new BodyContentHandler(), metadata, new ParseContext());
assertEquals("ISO-8859-1", metadata.get(Metadata.CONTENT_ENCODING));
}
@@ -347,6 +354,7 @@ public class HtmlParserTest {
/**
* 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
@@ -363,61 +371,64 @@ public class HtmlParserTest {
/**
* 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\""
- + " content=\"text/html; charset=ISO-8859-15; charset=iso-8859-15\" />"
- + "<title>the name is \u00e1ndre</title>"
- + "</head><body></body></html>";
+ "<html><head><meta http-equiv=\"content-type\""
+ + " content=\"text/html; charset=ISO-8859-15; charset=iso-8859-15\" />"
+ + "<title>the name is \u00e1ndre</title>"
+ + "</head><body></body></html>";
Metadata metadata = new Metadata();
- new HtmlParser().parse (
+ new HtmlParser().parse(
new ByteArrayInputStream(test1.getBytes("ISO-8859-1")),
- new BodyContentHandler(), metadata, new ParseContext());
+ new BodyContentHandler(), metadata, new ParseContext());
assertEquals("ISO-8859-15", metadata.get(Metadata.CONTENT_ENCODING));
// Some HTML pages have errors like ';;' versus '; ' as separator
String test2 =
- "<html><head><meta http-equiv=\"content-type\""
- + " content=\"text/html;;charset=ISO-8859-15\" />"
- + "<title>the name is \u00e1ndre</title>"
- + "</head><body></body></html>";
+ "<html><head><meta http-equiv=\"content-type\""
+ + " content=\"text/html;;charset=ISO-8859-15\" />"
+ + "<title>the name is \u00e1ndre</title>"
+ + "</head><body></body></html>";
metadata = new Metadata();
- new HtmlParser().parse (
+ new HtmlParser().parse(
new ByteArrayInputStream(test2.getBytes("ISO-8859-1")),
- new BodyContentHandler(), metadata, new ParseContext());
+ new BodyContentHandler(), metadata, new ParseContext());
assertEquals("ISO-8859-15", metadata.get(Metadata.CONTENT_ENCODING));
}
/**
* 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>"
- + "<body></body></html>";
+ "<html><head><title>the name is \u00e1ndre</title></head>"
+ + "<body></body></html>";
Metadata metadata = new Metadata();
- new HtmlParser().parse (
+ new HtmlParser().parse(
new ByteArrayInputStream(test.getBytes(IOUtils.UTF_8)),
- new BodyContentHandler(), metadata, new ParseContext());
+ new BodyContentHandler(), metadata, new ParseContext());
assertEquals("UTF-8", metadata.get(Metadata.CONTENT_ENCODING));
metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "charset=ISO-8859-1;text/html");
- new HtmlParser().parse (
+ new HtmlParser().parse(
new ByteArrayInputStream(test.getBytes("ISO-8859-1")),
- new BodyContentHandler(), metadata, new ParseContext());
+ new BodyContentHandler(), metadata, new ParseContext());
assertEquals("ISO-8859-1", metadata.get(Metadata.CONTENT_ENCODING));
}
/**
* Test case for TIKA-357
+ *
* @see <a href="https://issues.apache.org/jira/browse/TIKA-357">TIKA-357</a>
*/
@Test
@@ -426,13 +437,14 @@ public class HtmlParserTest {
Metadata metadata = new Metadata();
new HtmlParser().parse(
HtmlParserTest.class.getResourceAsStream(path),
- new BodyContentHandler(), metadata, new ParseContext());
+ new BodyContentHandler(), metadata, new ParseContext());
assertEquals("windows-1251", metadata.get(Metadata.CONTENT_ENCODING));
}
/**
* Test case for TIKA-420
+ *
* @see <a href="https://issues.apache.org/jira/browse/TIKA-420">TIKA-420</a>
*/
@Test
@@ -443,7 +455,7 @@ public class HtmlParserTest {
BodyContentHandler handler = new BodyContentHandler();
new HtmlParser().parse(
HtmlParserTest.class.getResourceAsStream(path),
- new BoilerpipeContentHandler(handler), metadata, new ParseContext());
+ new BoilerpipeContentHandler(handler), metadata, new ParseContext());
String content = handler.toString();
assertTrue(content.startsWith("This is the real meat"));
@@ -454,14 +466,15 @@ public class HtmlParserTest {
/**
* 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\">" +
- "<link rel=\"next\" href=\"next.html\" />" +
- "</head><body><p>Simple Content</p></body></html>";
+ "<meta http-equiv=\"content-type\" content=\"text/html\">" +
+ "<link rel=\"next\" href=\"next.html\" />" +
+ "</head><body><p>Simple Content</p></body></html>";
StringWriter sw = new StringWriter();
new HtmlParser().parse(
@@ -492,13 +505,14 @@ public class HtmlParserTest {
/**
* 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\" />" +
- "</head><body><img src=\"image.jpg\" /></body></html>";
+ "<base href=\"http://domain.com\" />" +
+ "</head><body><img src=\"image.jpg\" /></body></html>";
StringWriter sw = new StringWriter();
new HtmlParser().parse(
@@ -513,13 +527,14 @@ public class HtmlParserTest {
/**
* 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\" />" +
- "</head><frameset><frame src=\"frame.html\" /></frameset></html>";
+ "<base href=\"http://domain.com\" />" +
+ "</head><frameset><frame src=\"frame.html\" /></frameset></html>";
StringWriter sw = new StringWriter();
new HtmlParser().parse(
@@ -534,14 +549,15 @@ public class HtmlParserTest {
/**
* 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\" />" +
- "</head><body><iframe src =\"framed.html\" width=\"100%\" height=\"300\">" +
- "<p>Your browser doesn't support iframes!</p></body></html>";
+ "<base href=\"http://domain.com\" />" +
+ "</head><body><iframe src =\"framed.html\" width=\"100%\" height=\"300\">" +
+ "<p>Your browser doesn't support iframes!</p></body></html>";
StringWriter sw = new StringWriter();
new HtmlParser().parse(
@@ -556,15 +572,16 @@ public class HtmlParserTest {
/**
* 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\" />" +
- "</head><body><p><map name=\"map\" id=\"map\">" +
- "<area shape=\"rect\" href=\"map.html\" alt=\"\" />" +
- "</map></p></body></html>";
+ "<base href=\"http://domain.com\" />" +
+ "</head><body><p><map name=\"map\" id=\"map\">" +
+ "<area shape=\"rect\" href=\"map.html\" alt=\"\" />" +
+ "</map></p></body></html>";
StringWriter sw = new StringWriter();
new HtmlParser().parse(
@@ -579,15 +596,16 @@ public class HtmlParserTest {
/**
* 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\" />" +
- "</head><body><p><object data=\"object.data\" type=\"text/html\">" +
- "<param name=\"name\" value=\"value\" />" +
- "</object></p></body></html>";
+ "<base href=\"http://domain.com\" />" +
+ "</head><body><p><object data=\"object.data\" type=\"text/html\">" +
+ "<param name=\"name\" value=\"value\" />" +
+ "</object></p></body></html>";
StringWriter sw = new StringWriter();
new HtmlParser().parse(
@@ -598,13 +616,14 @@ public class HtmlParserTest {
// <object> tag should exist with fully resolved URLs
assertTrue(
- "<object> tag not correctly found in:\n" + result,
- Pattern.matches("(?s).*<object data=\"http://domain.com/object.data\".*<param .* name=\"name\" value=\"value\"/>.*</object>.*$", result)
+ "<object> tag not correctly found in:\n" + result,
+ Pattern.matches("(?s).*<object data=\"http://domain.com/object.data\".*<param .* name=\"name\" value=\"value\"/>.*</object>.*$", result)
);
}
/**
* 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
@@ -629,13 +648,14 @@ public class HtmlParserTest {
/**
* 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\" />" +
- "</head><body><frameset><frame src=\"frame.html\" /></frameset></body></html>";
+ "<base href=\"http://domain.com\" />" +
+ "</head><body><frameset><frame src=\"frame.html\" /></frameset></body></html>";
StringWriter sw1 = new StringWriter();
new HtmlParser().parse(
@@ -652,11 +672,11 @@ public class HtmlParserTest {
// Test the example from the Nutch project.
final String test2 = "<html><head><title> my title </title></head><body>" +
- "<frameset rows=\"20,*\"><frame src=\"top.html\"></frame>" +
- "<frameset cols=\"20,*\"><frame src=\"left.html\"></frame>" +
- "<frame src=\"invalid.html\"/></frame>" +
- "<frame src=\"right.html\"></frame>" +
- "</frameset></frameset></body></html>";
+ "<frameset rows=\"20,*\"><frame src=\"top.html\"></frame>" +
+ "<frameset cols=\"20,*\"><frame src=\"left.html\"></frame>" +
+ "<frame src=\"invalid.html\"/></frame>" +
+ "<frame src=\"right.html\"></frame>" +
+ "</frameset></frameset></body></html>";
StringWriter sw2 = new StringWriter();
new HtmlParser().parse(
@@ -678,6 +698,7 @@ public class HtmlParserTest {
/**
* Test case for TIKA-480: fix NPE when using BodyContentHandler or HtmlTransformer
* as delegate for BoilerpipeContentHandler
+ *
* @see <a href="https://issues.apache.org/jira/browse/TIKA-480">TIKA-480</a>
*/
@Test
@@ -688,7 +709,7 @@ public class HtmlParserTest {
StringWriter sw = new StringWriter();
new HtmlParser().parse(
HtmlParserTest.class.getResourceAsStream(path),
- makeHtmlTransformer(sw), metadata, new ParseContext());
+ makeHtmlTransformer(sw), metadata, new ParseContext());
String content = sw.toString();
@@ -701,14 +722,15 @@ public class HtmlParserTest {
/**
* 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\" />" +
- "<link rel=\"next\" href=\"next.html\" />" +
- "</head><body></body></html>";
+ "<base href=\"http://domain.com\" />" +
+ "<link rel=\"next\" href=\"next.html\" />" +
+ "</head><body></body></html>";
StringWriter sw = new StringWriter();
new HtmlParser().parse(
@@ -731,7 +753,7 @@ public class HtmlParserTest {
* @throws Exception
*/
private ContentHandler makeHtmlTransformer(Writer writer) throws Exception {
- SAXTransformerFactory factory = (SAXTransformerFactory)SAXTransformerFactory.newInstance();
+ SAXTransformerFactory factory = (SAXTransformerFactory) SAXTransformerFactory.newInstance();
TransformerHandler handler = factory.newTransformerHandler();
handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "html");
handler.getTransformer().setOutputProperty(OutputKeys.INDENT, "no");
@@ -742,6 +764,7 @@ public class HtmlParserTest {
/**
* 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
@@ -756,7 +779,7 @@ public class HtmlParserTest {
new HtmlParser().parse(
HtmlParserTest.class.getResourceAsStream(path),
- bpch, metadata, new ParseContext());
+ bpch, metadata, new ParseContext());
String content = sw.toString();
assertTrue("Has empty table elements", content.contains("<body><table><tr><td><table><tr><td>"));
@@ -793,9 +816,9 @@ public class HtmlParserTest {
StringWriter sw = new StringWriter();
- new HtmlParser().parse (
+ new HtmlParser().parse(
new ByteArrayInputStream(html.getBytes(IOUtils.UTF_8)),
- makeHtmlTransformer(sw), metadata, parseContext);
+ makeHtmlTransformer(sw), metadata, parseContext);
String result = sw.toString();
// Make sure we don't get <body><BODY/></body>
@@ -816,7 +839,7 @@ public class HtmlParserTest {
BodyContentHandler handler = new BodyContentHandler();
new HtmlParser().parse(
new ByteArrayInputStream(html.getBytes(IOUtils.UTF_8)),
- handler, new Metadata(), new ParseContext());
+ handler, new Metadata(), new ParseContext());
// Make sure we get <tab>, "one", newline, newline
String result = handler.toString();
@@ -826,22 +849,23 @@ public class HtmlParserTest {
/**
* 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";
-
+
Metadata metadata = new Metadata();
BodyContentHandler handler = new BodyContentHandler();
-
+
BoilerpipeContentHandler bpHandler = new BoilerpipeContentHandler(handler);
bpHandler.setIncludeMarkup(true);
-
+
new HtmlParser().parse(
HtmlParserTest.class.getResourceAsStream(path),
- bpHandler, metadata, new ParseContext());
-
+ bpHandler, metadata, new ParseContext());
+
String content = handler.toString();
// Should not contain item_aitem_b
@@ -862,12 +886,12 @@ public class HtmlParserTest {
@Test
public void testOpenGraphMetadata() throws Exception {
String test1 =
- "<html><head><meta property=\"og:description\""
- + " content=\"some description\" />"
- + "<meta property=\"og:image\" content=\"http://example.com/image1.jpg\" />"
- + "<meta property=\"og:image\" content=\"http://example.com/image2.jpg\" />"
- + "<title>hello</title>"
- + "</head><body></body></html>";
+ "<html><head><meta property=\"og:description\""
+ + " content=\"some description\" />"
+ + "<meta property=\"og:image\" content=\"http://example.com/image1.jpg\" />"
+ + "<meta property=\"og:image\" content=\"http://example.com/image2.jpg\" />"
+ + "<title>hello</title>"
+ + "</head><body></body></html>";
Metadata metadata = new Metadata();
new HtmlParser().parse(
new ByteArrayInputStream(test1.getBytes("ISO-8859-1")),
@@ -883,19 +907,19 @@ public class HtmlParserTest {
HtmlParserTest.class.getResourceAsStream("/test-documents/testUserDefinedCharset.mhtml"), new Metadata());
assertNotNull(content);
}
-
+
//TIKA-1001
@Test
public void testNoisyMetaCharsetHeaders() throws Exception {
- Tika tika = new Tika();
- String hit = "\u0623\u0639\u0631\u0628";
+ Tika tika = new Tika();
+ String hit = "\u0623\u0639\u0631\u0628";
- for (int i = 1; i <=4; i++){
- String fileName = "/test-documents/testHTMLNoisyMetaEncoding_"+i+".html";
- String content = tika.parseToString(
- HtmlParserTest.class.getResourceAsStream(fileName));
- assertTrue("testing: " +fileName, content.contains(hit));
- }
+ for (int i = 1; i <= 4; i++) {
+ String fileName = "/test-documents/testHTMLNoisyMetaEncoding_" + i + ".html";
+ String content = tika.parseToString(
+ HtmlParserTest.class.getResourceAsStream(fileName));
+ assertTrue("testing: " + fileName, content.contains(hit));
+ }
}
// TIKA-1193
@@ -907,7 +931,7 @@ public class HtmlParserTest {
Metadata metadata = new Metadata();
LinkContentHandler linkContentHandler = new LinkContentHandler();
- new HtmlParser().parse (
+ new HtmlParser().parse(
new ByteArrayInputStream(test.getBytes("ISO-8859-1")),
linkContentHandler, metadata, new ParseContext());
@@ -921,7 +945,7 @@ public class HtmlParserTest {
ParseContext parseContext = new ParseContext();
parseContext.set(Schema.class, schema);
linkContentHandler = new LinkContentHandler();
- new HtmlParser().parse (
+ new HtmlParser().parse(
new ByteArrayInputStream(test.getBytes("ISO-8859-1")),
linkContentHandler, metadata, parseContext);
@@ -939,56 +963,57 @@ public class HtmlParserTest {
final int line = 0;
final int col = 1;
final int[] textPosition = new int[2];
-
+
new HtmlParser().parse(HtmlParserTest.class.getResourceAsStream("/test-documents/testHTML.html"),
- new ContentHandler(){
- Locator locator;
+ new ContentHandler() {
+ Locator locator;
+
+ public void setDocumentLocator(Locator locator) {
+ this.locator = locator;
+ }
+
+ public void startDocument() throws SAXException {
+ }
+
+ public void endDocument() throws SAXException {
+ }
+
+ public void startPrefixMapping(String prefix, String uri)
+ throws SAXException {
+ }
- public void setDocumentLocator(Locator locator) {
- this.locator = locator;
- }
-
- public void startDocument() throws SAXException {
- }
-
- public void endDocument() throws SAXException {
- }
-
- public void startPrefixMapping(String prefix, String uri)
- throws SAXException {
- }
-
- public void endPrefixMapping(String prefix)
- throws SAXException {
- }
-
- public void startElement(String uri, String localName,
- String qName, Attributes atts) throws SAXException {
- }
-
- public void endElement(String uri, String localName,
- String qName) throws SAXException {
- }
-
- public void characters(char[] ch, int start, int length)
- throws SAXException {
- String text = new String(ch, start, length);
- if (text.equals("Test Indexation Html") && locator != null) {
- textPosition[line] = locator.getLineNumber();
- textPosition[col] = locator.getColumnNumber();
- }
- }
-
- public void ignorableWhitespace(char[] ch, int start,
- int length) throws SAXException {
- }
-
- public void processingInstruction(String target, String data)
- throws SAXException {
- }
+ public void endPrefixMapping(String prefix)
+ throws SAXException {
+ }
+
+ public void startElement(String uri, String localName,
+ String qName, Attributes atts) throws SAXException {
+ }
+
+ public void endElement(String uri, String localName,
+ String qName) throws SAXException {
+ }
+
+ public void characters(char[] ch, int start, int length)
+ throws SAXException {
+ String text = new String(ch, start, length);
+ if (text.equals("Test Indexation Html") && locator != null) {
+ textPosition[line] = locator.getLineNumber();
+ textPosition[col] = locator.getColumnNumber();
+ }
+ }
+
+ public void ignorableWhitespace(char[] ch, int start,
+ int length) throws SAXException {
+ }
- public void skippedEntity(String name) throws SAXException {
- }},
+ public void processingInstruction(String target, String data)
+ throws SAXException {
+ }
+
+ public void skippedEntity(String name) throws SAXException {
+ }
+ },
new Metadata(),
new ParseContext());
@@ -997,20 +1022,20 @@ public class HtmlParserTest {
// The column reported seems fuzzy, just test it is close enough.
assertTrue(Math.abs(textPosition[col] - 47) < 10);
}
-
-
- /**
- * Test case for TIKA-1303: HTML parse should use the first title tag to set value in meta data
+
+
+ /**
+ * Test case for TIKA-1303: HTML parse should use the first title tag to set value in meta data
* and ignore any subsequent title tags found in HTML.
- *
+ *
* @see <a href="https://issues.apache.org/jira/browse/TIKA-1303">TIKA-1303</a>
*/
@Test
- public void testFirstTitleValueisSetToMetadata() throws Exception{
+ public void testFirstTitleValueisSetToMetadata() throws Exception {
String test = "<html><title>Simple Content</title><body><h1></h1>"
- + "<title>TitleToIgnore</title></body></html>";
+ + "<title>TitleToIgnore</title></body></html>";
Metadata metadata = new Metadata();
-
+
new HtmlParser().parse(
new ByteArrayInputStream(test.getBytes(IOUtils.UTF_8)),
new BodyContentHandler(), metadata, new ParseContext());
@@ -1023,7 +1048,7 @@ public class HtmlParserTest {
public void testMisleadingMetaContentTypeTags() throws Exception {
//TIKA-1519
- String test = "<html><head><meta http-equiv=\"content-type\" content=\"text/html; charset=UTF-ELEVEN\">"+
+ String test = "<html><head><meta http-equiv=\"content-type\" content=\"text/html; charset=UTF-ELEVEN\">" +
"</head><title>title</title><body>body</body></html>";
Metadata metadata = new Metadata();
@@ -1033,7 +1058,7 @@ public class HtmlParserTest {
assertEquals("text/html; charset=UTF-ELEVEN", metadata.get(TikaCoreProperties.CONTENT_TYPE_HINT));
assertEquals("text/html; charset=ISO-8859-1", metadata.get(Metadata.CONTENT_TYPE));
- test = "<html><head><meta http-equiv=\"content-type\" content=\"application/pdf\">"+
+ test = "<html><head><meta http-equiv=\"content-type\" content=\"application/pdf\">" +
"</head><title>title</title><body>body</body></html>";
metadata = new Metadata();
@@ -1044,7 +1069,7 @@ public class HtmlParserTest {
assertEquals("text/html; charset=ISO-8859-1", metadata.get(Metadata.CONTENT_TYPE));
//test two content values
- test = "<html><head><meta http-equiv=\"content-type\" content=\"application/pdf\" content=\"application/ms-word\">"+
+ test = "<html><head><meta http-equiv=\"content-type\" content=\"application/pdf\" content=\"application/ms-word\">" +
"</head><title>title</title><body>body</body></html>";
metadata = new Metadata();
@@ -1058,7 +1083,7 @@ public class HtmlParserTest {
@Test
public void testXHTMLWithMisleading() throws Exception {
//first test an acceptable XHTML header with http-equiv tags
- String test = "<?xml version=\"1.0\" ?>"+
+ String test = "<?xml version=\"1.0\" ?>" +
"<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n" +
"<html xmlns=\"http://www.w3.org/1999/xhtml\">\n" +
"<head>\n" +
@@ -1072,7 +1097,7 @@ public class HtmlParserTest {
assertEquals("text/html; charset=iso-8859-1", metadata.get(TikaCoreProperties.CONTENT_TYPE_HINT));
assertEquals("application/xhtml+xml; charset=ISO-8859-1", metadata.get(Metadata.CONTENT_TYPE));
- test = "<?xml version=\"1.0\" ?>"+
+ test = "<?xml version=\"1.0\" ?>" +
"<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n" +
"<html xmlns=\"http://www.w3.org/1999/xhtml\">\n" +
"<head>\n" +
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/BPGParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/BPGParserTest.java?rev=1682489&r1=1682488&r2=1682489&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/BPGParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/BPGParserTest.java Fri May 29 14:36:21 2015
@@ -16,6 +16,9 @@
*/
package org.apache.tika.parser.image;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
+
import java.io.InputStream;
import java.util.Arrays;
import java.util.List;
@@ -28,10 +31,6 @@ import org.apache.tika.parser.Parser;
import org.junit.Test;
import org.xml.sax.helpers.DefaultHandler;
-import static org.junit.Assert.assertEquals;
-import static org.junit.Assert.assertEquals;
-import static org.junit.Assert.assertTrue;
-
public class BPGParserTest {
private final Parser parser = new BPGParser();
@@ -43,7 +42,7 @@ public class BPGParserTest {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/x-bpg");
InputStream stream =
- getClass().getResourceAsStream("/test-documents/testBPG.bpg");
+ getClass().getResourceAsStream("/test-documents/testBPG.bpg");
parser.parse(stream, new DefaultHandler(), metadata, new ParseContext());
assertEquals("100", metadata.get(Metadata.IMAGE_WIDTH));
@@ -60,14 +59,14 @@ public class BPGParserTest {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/x-bpg");
InputStream stream =
- getClass().getResourceAsStream("/test-documents/testBPG_commented.bpg");
+ getClass().getResourceAsStream("/test-documents/testBPG_commented.bpg");
parser.parse(stream, new DefaultHandler(), metadata, new ParseContext());
assertEquals("103", metadata.get(Metadata.IMAGE_WIDTH));
assertEquals("77", metadata.get(Metadata.IMAGE_LENGTH));
assertEquals("10", metadata.get(Metadata.BITS_PER_SAMPLE));
assertEquals("YCbCr Colour", metadata.get(Photoshop.COLOR_MODE));
-
+
// TODO Get the exif comment data to be properly extracted, see TIKA-1495
if (false) {
assertEquals("Tosteberga \u00C4ngar", metadata.get(TikaCoreProperties.TITLE));
@@ -77,7 +76,7 @@ public class BPGParserTest {
assertTrue(keywords.contains("bird watching"));
assertEquals(keywords, Arrays.asList(metadata.getValues(TikaCoreProperties.KEYWORDS)));
}
-
+
// TODO Get the exif data to be properly extracted, see TIKA-1495
if (false) {
assertEquals("1.0E-6", metadata.get(Metadata.EXPOSURE_TIME)); // 1/1000000
@@ -90,7 +89,7 @@ public class BPGParserTest {
assertEquals("1", metadata.get(Metadata.ORIENTATION));
assertEquals("300.0", metadata.get(Metadata.RESOLUTION_HORIZONTAL));
assertEquals("300.0", metadata.get(Metadata.RESOLUTION_VERTICAL));
- assertEquals("Inch", metadata.get(Metadata.RESOLUTION_UNIT));
+ assertEquals("Inch", metadata.get(Metadata.RESOLUTION_UNIT));
}
}
@@ -102,20 +101,20 @@ public class BPGParserTest {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/x-bpg");
InputStream stream =
- getClass().getResourceAsStream("/test-documents/testBPG_GEO.bpg");
+ getClass().getResourceAsStream("/test-documents/testBPG_GEO.bpg");
parser.parse(stream, new DefaultHandler(), metadata, new ParseContext());
assertEquals("100", metadata.get(Metadata.IMAGE_WIDTH));
assertEquals("68", metadata.get(Metadata.IMAGE_LENGTH));
assertEquals("10", metadata.get(Metadata.BITS_PER_SAMPLE));
assertEquals("YCbCr Colour", metadata.get(Photoshop.COLOR_MODE));
-
+
// TODO Get the geographic data to be properly extracted, see TIKA-1495
if (false) {
assertEquals("12.54321", metadata.get(Metadata.LATITUDE));
assertEquals("-54.1234", metadata.get(Metadata.LONGITUDE));
}
-
+
// TODO Get the exif data to be properly extracted, see TIKA-1495
if (false) {
assertEquals("6.25E-4", metadata.get(Metadata.EXPOSURE_TIME)); // 1/1600
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=1682489&r1=1682488&r2=1682489&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 Fri May 29 14:36:21 2015
@@ -17,16 +17,13 @@
package org.apache.tika.parser.image;
-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;
-import com.drew.metadata.Tag;
-import com.drew.metadata.exif.ExifIFD0Directory;
-import com.drew.metadata.exif.ExifSubIFDDirectory;
-import com.drew.metadata.jpeg.JpegCommentDirectory;
+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.mock;
+import static org.mockito.Mockito.verify;
+import static org.mockito.Mockito.when;
import java.util.Arrays;
import java.util.GregorianCalendar;
@@ -35,29 +32,31 @@ import java.util.List;
import java.util.Locale;
import java.util.TimeZone;
-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.mock;
-import static org.mockito.Mockito.verify;
-import static org.mockito.Mockito.when;
+import com.drew.metadata.Directory;
+import com.drew.metadata.MetadataException;
+import com.drew.metadata.Tag;
+import com.drew.metadata.exif.ExifIFD0Directory;
+import com.drew.metadata.exif.ExifSubIFDDirectory;
+import com.drew.metadata.jpeg.JpegCommentDirectory;
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
+import org.junit.Test;
public class ImageMetadataExtractorTest {
-
- @SuppressWarnings({ "rawtypes", "unchecked" })
+
+ @SuppressWarnings({"rawtypes", "unchecked"})
@Test
public void testHandleDirectories() throws MetadataException {
Metadata metadata = mock(Metadata.class);
ImageMetadataExtractor.DirectoryHandler handler1 = mock(ImageMetadataExtractor.DirectoryHandler.class);
ImageMetadataExtractor e = new ImageMetadataExtractor(metadata, handler1);
-
+
Directory directory = new JpegCommentDirectory();
Iterator directories = mock(Iterator.class);
when(directories.hasNext()).thenReturn(true, false);
when(directories.next()).thenReturn(directory);
when(handler1.supports(JpegCommentDirectory.class)).thenReturn(true);
-
+
e.handle(directories);
verify(handler1).supports(JpegCommentDirectory.class);
verify(handler1).handle(directory, metadata);
@@ -70,7 +69,7 @@ public class ImageMetadataExtractorTest
assertFalse(new ImageMetadataExtractor.ExifHandler().supports(Directory.class));
assertFalse(new ImageMetadataExtractor.ExifHandler().supports(JpegCommentDirectory.class));
}
-
+
@Test
public void testExifHandlerParseDate() throws MetadataException {
ExifSubIFDDirectory exif = mock(ExifSubIFDDirectory.class);
@@ -81,9 +80,9 @@ public class ImageMetadataExtractorTest
when(exif.getDate(ExifSubIFDDirectory.TAG_DATETIME_ORIGINAL)).thenReturn(
calendar.getTime()); // jvm default timezone as in Metadata Extractor
Metadata metadata = new Metadata();
-
+
new ImageMetadataExtractor.ExifHandler().handle(exif, metadata);
- assertEquals("Should be ISO date without time zone", "2000-01-01T00:00:00",
+ assertEquals("Should be ISO date without time zone", "2000-01-01T00:00:00",
metadata.get(TikaCoreProperties.CREATED));
}
@@ -97,24 +96,24 @@ public class ImageMetadataExtractorTest
when(exif.getDate(ExifIFD0Directory.TAG_DATETIME)).thenReturn(
calendar.getTime()); // jvm default timezone as in Metadata Extractor
Metadata metadata = new Metadata();
-
+
new ImageMetadataExtractor.ExifHandler().handle(exif, metadata);
- assertEquals("Should try EXIF Date/Time if Original is not set", "1999-01-01T00:00:00",
+ assertEquals("Should try EXIF Date/Time if Original is not set", "1999-01-01T00:00:00",
metadata.get(TikaCoreProperties.CREATED));
}
-
+
@Test
public void testExifHandlerParseDateError() throws MetadataException {
ExifIFD0Directory exif = mock(ExifIFD0Directory.class);
when(exif.containsTag(ExifSubIFDDirectory.TAG_DATETIME_ORIGINAL)).thenReturn(true);
when(exif.getDate(ExifSubIFDDirectory.TAG_DATETIME_ORIGINAL)).thenReturn(null);
Metadata metadata = new Metadata();
-
+
new ImageMetadataExtractor.ExifHandler().handle(exif, metadata);
- assertEquals("Parsing should proceed without date", null,
+ assertEquals("Parsing should proceed without date", null,
metadata.get(TikaCoreProperties.CREATED));
}
-
+
@Test
public void testCopyUnknownFieldsHandler() throws MetadataException {
Directory d = mock(Directory.class);
@@ -136,5 +135,5 @@ public class ImageMetadataExtractorTest
metadata.get(Metadata.KEYWORDS));
assertNull(metadata.get(TikaCoreProperties.DESCRIPTION));
}
-
+
}
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=1682489&r1=1682488&r2=1682489&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 Fri May 29 14:36:21 2015
@@ -36,7 +36,7 @@ public class ImageParserTest {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/bmp");
InputStream stream =
- getClass().getResourceAsStream("/test-documents/testBMP.bmp");
+ getClass().getResourceAsStream("/test-documents/testBMP.bmp");
parser.parse(stream, new DefaultHandler(), metadata, new ParseContext());
assertEquals("75", metadata.get("height"));
@@ -47,7 +47,7 @@ public class ImageParserTest {
assertEquals("0", metadata.get("Dimension HorizontalPhysicalPixelSpacing"));
assertEquals("BI_RGB", metadata.get("Compression CompressionTypeName"));
assertEquals("image/bmp", metadata.get("Content-Type"));
-
+
assertEquals("100", metadata.get(Metadata.IMAGE_WIDTH));
assertEquals("75", metadata.get(Metadata.IMAGE_LENGTH));
assertEquals("8 8 8", metadata.get(Metadata.BITS_PER_SAMPLE));
@@ -58,7 +58,7 @@ public class ImageParserTest {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/gif");
InputStream stream =
- getClass().getResourceAsStream("/test-documents/testGIF.gif");
+ getClass().getResourceAsStream("/test-documents/testGIF.gif");
parser.parse(stream, new DefaultHandler(), metadata, new ParseContext());
assertEquals("75", metadata.get("height"));
@@ -78,7 +78,7 @@ public class ImageParserTest {
assertEquals("disposalMethod=none, userInputFlag=false, transparentColorFlag=false, delayTime=0, transparentColorIndex=0", metadata.get("GraphicControlExtension"));
assertEquals("0", metadata.get("Dimension VerticalPixelOffset"));
assertEquals("image/gif", metadata.get("Content-Type"));
-
+
assertEquals("100", metadata.get(Metadata.IMAGE_WIDTH));
assertEquals("75", metadata.get(Metadata.IMAGE_LENGTH));
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));
@@ -89,7 +89,7 @@ public class ImageParserTest {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/jpeg");
InputStream stream =
- getClass().getResourceAsStream("/test-documents/testJPEG.jpg");
+ getClass().getResourceAsStream("/test-documents/testJPEG.jpg");
parser.parse(stream, new DefaultHandler(), metadata, new ParseContext());
assertEquals("75", metadata.get("height"));
@@ -114,7 +114,7 @@ public class ImageParserTest {
assertEquals("keyword=comment, value=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("Text TextEntry"));
assertEquals("image/jpeg", metadata.get("Content-Type"));
assertEquals("process=0, samplePrecision=8, numLines=75, samplesPerLine=100, numFrameComponents=3", metadata.get("markerSequence sof"));
-
+
assertEquals("100", metadata.get(Metadata.IMAGE_WIDTH));
assertEquals("75", metadata.get(Metadata.IMAGE_LENGTH));
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));
@@ -125,7 +125,7 @@ public class ImageParserTest {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/png");
InputStream stream =
- getClass().getResourceAsStream("/test-documents/testPNG.png");
+ getClass().getResourceAsStream("/test-documents/testPNG.png");
parser.parse(stream, new DefaultHandler(), metadata, new ParseContext());
assertEquals("75", metadata.get("height"));
@@ -152,7 +152,7 @@ public class ImageParserTest {
assertEquals("true", metadata.get("Chroma BlackIsZero"));
assertEquals("year=2008, month=5, day=6, hour=6, minute=18, second=47", metadata.get("Document ImageModificationTime"));
assertEquals("image/png", metadata.get("Content-Type"));
-
+
assertEquals("100", metadata.get(Metadata.IMAGE_WIDTH));
assertEquals("75", metadata.get(Metadata.IMAGE_LENGTH));
assertEquals("8 8 8", metadata.get(Metadata.BITS_PER_SAMPLE));
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=1682489&r1=1682488&r2=1682489&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 Fri May 29 14:36:21 2015
@@ -16,6 +16,8 @@
*/
package org.apache.tika.parser.image;
+import static junit.framework.Assert.assertEquals;
+
import java.io.InputStream;
import org.apache.tika.metadata.Metadata;
@@ -24,8 +26,6 @@ import org.apache.tika.parser.Parser;
import org.junit.Test;
import org.xml.sax.helpers.DefaultHandler;
-import static junit.framework.Assert.assertEquals;
-
public class PSDParserTest {
private final Parser parser = new PSDParser();
@@ -38,24 +38,24 @@ public class PSDParserTest {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/x-psd");
InputStream stream =
- getClass().getResourceAsStream("/test-documents/testPSD.psd");
+ getClass().getResourceAsStream("/test-documents/testPSD.psd");
parser.parse(stream, new DefaultHandler(), metadata, new ParseContext());
assertEquals("537", metadata.get(Metadata.IMAGE_WIDTH));
assertEquals("51", metadata.get(Metadata.IMAGE_LENGTH));
assertEquals("8", metadata.get(Metadata.BITS_PER_SAMPLE));
}
-
+
/**
* Tests a very basic file, without much metadata,
- * where some of the data lengths are padded to be even
+ * 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");
InputStream stream =
- getClass().getResourceAsStream("/test-documents/testPSD2.psd");
+ getClass().getResourceAsStream("/test-documents/testPSD2.psd");
parser.parse(stream, new DefaultHandler(), metadata, new ParseContext());
assertEquals("69", metadata.get(Metadata.IMAGE_WIDTH));
assertEquals("70", metadata.get(Metadata.IMAGE_LENGTH));
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=1682489&r1=1682488&r2=1682489&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 Fri May 29 14:36:21 2015
@@ -19,18 +19,17 @@ package org.apache.tika.parser.image;
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 java.io.InputStream;
+import java.util.Arrays;
+import java.util.List;
+
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 java.io.InputStream;
-import java.util.Arrays;
-import java.util.List;
-
public class TiffParserTest {
private final Parser parser = new TiffParser();
@@ -39,23 +38,23 @@ public class TiffParserTest {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, "image/tiff");
InputStream stream =
- getClass().getResourceAsStream("/test-documents/testTIFF.tif");
+ getClass().getResourceAsStream("/test-documents/testTIFF.tif");
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));
-
+
// Core EXIF/TIFF tags
assertEquals("100", metadata.get(Metadata.IMAGE_WIDTH));
assertEquals("75", metadata.get(Metadata.IMAGE_LENGTH));
assertEquals("8", metadata.get(Metadata.BITS_PER_SAMPLE));
assertEquals("3", metadata.get(Metadata.SAMPLES_PER_PIXEL));
-
+
// Embedded XMP
List<String> keywords = Arrays.asList(metadata.getValues(TikaCoreProperties.KEYWORDS));
assertTrue("got " + keywords, keywords.contains("cat"));
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/WebPParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/WebPParserTest.java?rev=1682489&r1=1682488&r2=1682489&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/WebPParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/image/WebPParserTest.java Fri May 29 14:36:21 2015
@@ -33,16 +33,17 @@ import org.xml.sax.helpers.DefaultHandle
public class WebPParserTest {
Parser parser = new AutoDetectParser();
-/*
- Two photos in test-documents (testWebp_Alpha_Lossy.webp and testWebp_Alpha_Lossless.webp)
- are in the public domain. These files were retrieved from:
- https://github.com/drewnoakes/metadata-extractor-images/tree/master/webp
- These photos are also available here:
- https://developers.google.com/speed/webp/gallery2#webp_links
- Credits for the photo:
- "Free Stock Photo in High Resolution - Yellow Rose 3 - Flowers"
- Image Author: Jon Sullivan
- */
+
+ /*
+ Two photos in test-documents (testWebp_Alpha_Lossy.webp and testWebp_Alpha_Lossless.webp)
+ are in the public domain. These files were retrieved from:
+ https://github.com/drewnoakes/metadata-extractor-images/tree/master/webp
+ These photos are also available here:
+ https://developers.google.com/speed/webp/gallery2#webp_links
+ Credits for the photo:
+ "Free Stock Photo in High Resolution - Yellow Rose 3 - Flowers"
+ Image Author: Jon Sullivan
+ */
@Test
public void testSimple() throws Exception {
Metadata metadata = new Metadata();
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=1682489&r1=1682488&r2=1682489&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 Fri May 29 14:36:21 2015
@@ -27,11 +27,10 @@ import java.util.Collection;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
-import org.apache.tika.parser.image.xmp.JempboxExtractor;
import org.junit.Test;
public class JempboxExtractorTest {
-
+
@Test
public void testParseJpeg() throws IOException, TikaException {
Metadata metadata = new Metadata();
@@ -42,21 +41,21 @@ public class JempboxExtractorTest {
metadata.set(TikaCoreProperties.CREATOR, "previous author");
// ... or kept in case the field is multi-value
metadata.add(TikaCoreProperties.KEYWORDS, "oldkeyword");
-
+
JempboxExtractor extractor = new JempboxExtractor(metadata);
extractor.parse(stream);
-
+
// DublinCore fields
assertEquals("Tosteberga \u00C4ngar", metadata.get(TikaCoreProperties.TITLE));
assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(TikaCoreProperties.DESCRIPTION));
assertEquals("Some Tourist", metadata.get(TikaCoreProperties.CREATOR));
- Collection<String> keywords = Arrays.asList(metadata.getValues(TikaCoreProperties.KEYWORDS));
+ Collection<String> keywords = Arrays.asList(metadata.getValues(TikaCoreProperties.KEYWORDS));
assertTrue(keywords.contains("oldkeyword"));
assertTrue(keywords.contains("grazelands"));
assertTrue(keywords.contains("nature reserve"));
assertTrue(keywords.contains("bird watching"));
assertTrue(keywords.contains("coast"));
- Collection<String> subject = Arrays.asList(metadata.getValues(Metadata.SUBJECT));
+ Collection<String> subject = Arrays.asList(metadata.getValues(Metadata.SUBJECT));
assertTrue(subject.contains("oldkeyword"));
assertTrue(subject.contains("grazelands"));
assertTrue(subject.contains("nature reserve"));
@@ -68,34 +67,34 @@ public class JempboxExtractorTest {
public void testParseJpegPhotoshop() throws IOException, TikaException {
Metadata metadata = new Metadata();
InputStream stream = getClass().getResourceAsStream("/test-documents/testJPEG_commented_pspcs2mac.jpg");
-
+
JempboxExtractor extractor = new JempboxExtractor(metadata);
extractor.parse(stream);
-
+
// DublinCore fields
assertEquals("Tosteberga \u00C4ngar", metadata.get(TikaCoreProperties.TITLE));
assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(TikaCoreProperties.DESCRIPTION));
assertEquals("Some Tourist", metadata.get(TikaCoreProperties.CREATOR));
- Collection<String> keywords = Arrays.asList(metadata.getValues(TikaCoreProperties.KEYWORDS));
+ Collection<String> keywords = Arrays.asList(metadata.getValues(TikaCoreProperties.KEYWORDS));
assertTrue(keywords.contains("bird watching"));
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");
-
+
JempboxExtractor extractor = new JempboxExtractor(metadata);
extractor.parse(stream);
-
+
// XnViewMp fields not understood by Jempbox
assertEquals("Bird site in north eastern Sk\u00E5ne, Sweden.\n(new line)", metadata.get(TikaCoreProperties.DESCRIPTION));
Collection<String> keywords = Arrays.asList(metadata.getValues(TikaCoreProperties.KEYWORDS));
assertTrue(keywords.contains("coast"));
assertTrue(keywords.contains("nature reserve"));
}
-
+
@Test
public void testJoinCreators() {
assertEquals("Mr B", new JempboxExtractor(null).joinCreators(
Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/jdbc/SQLite3ParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/jdbc/SQLite3ParserTest.java?rev=1682489&r1=1682488&r2=1682489&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/jdbc/SQLite3ParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/jdbc/SQLite3ParserTest.java Fri May 29 14:36:21 2015
@@ -46,7 +46,8 @@ import org.xml.sax.ContentHandler;
public class SQLite3ParserTest extends TikaTest {
private final static String TEST_FILE_NAME = "testSqlite3b.db";
- private final static String TEST_FILE1 = "/test-documents/"+TEST_FILE_NAME;;
+ private final static String TEST_FILE1 = "/test-documents/" + TEST_FILE_NAME;
+ ;
@Test
public void testBasic() throws Exception {
@@ -98,7 +99,7 @@ public class SQLite3ParserTest extends T
//make sure that table cells and rows are properly marked to
//yield \t and \n at the appropriate places
@Test
- public void testSpacesInBodyContentHandler() throws Exception {
+ public void testSpacesInBodyContentHandler() throws Exception {
Parser p = new AutoDetectParser();
InputStream stream = null;
Metadata metadata = new Metadata();
@@ -188,20 +189,20 @@ public class SQLite3ParserTest extends T
String[] strings = new String[4];
for (int i = 1; i < byteCopier.bytes.size(); i++) {
byte[] byteArr = byteCopier.bytes.get(i);
- String s = new String(byteArr, 0, Math.min(byteArr.length,1000), "UTF-8");
+ String s = new String(byteArr, 0, Math.min(byteArr.length, 1000), "UTF-8");
strings[i] = s;
}
byte[] oleBytes = new byte[]{
- (byte)-48,
- (byte)-49,
- (byte)17,
- (byte)-32,
- (byte)-95,
- (byte)-79,
- (byte)26,
- (byte)-31,
- (byte)0,
- (byte)0,
+ (byte) -48,
+ (byte) -49,
+ (byte) 17,
+ (byte) -32,
+ (byte) -95,
+ (byte) -79,
+ (byte) 26,
+ (byte) -31,
+ (byte) 0,
+ (byte) 0,
};
//test OLE
for (int i = 0; i < 10; i++) {
@@ -231,7 +232,6 @@ public class SQLite3ParserTest extends T
}
-
public static class InputStreamResettingHandler implements EmbeddedResourceHandler {
public List<byte[]> bytes = new ArrayList<byte[]>();
@@ -240,7 +240,7 @@ public class SQLite3ParserTest extends T
public void handle(String filename, MediaType mediaType,
InputStream stream) {
ByteArrayOutputStream os = new ByteArrayOutputStream();
- if (! stream.markSupported()) {
+ if (!stream.markSupported()) {
stream = TikaInputStream.get(stream);
}
stream.mark(1000000);