[
https://issues.apache.org/jira/browse/TIKA-1215?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13860246#comment-13860246
]
Hong-Thai Nguyen edited comment on TIKA-1215 at 1/2/14 5:20 PM:
----------------------------------------------------------------
[~davemeikle], here's a sample test failed on this file with 1.5-SNAPSHOT, but
passed on 1.4:
{code}
package com.polyspot.document.converter;
import static org.fest.assertions.Assertions.assertThat;
import java.io.ByteArrayOutputStream;
import java.io.InputStream;
import org.apache.commons.io.IOUtils;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.CompositeParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.ToHTMLContentHandler;
import org.apache.tika.sax.WriteOutContentHandler;
import org.junit.Before;
import org.junit.Test;
import org.xml.sax.ContentHandler;
public class Mp3ParserTest {
private CompositeParser parser;
@Before
public void before() throws Exception {
TikaConfig tikaConf = new TikaConfig();
parser = (CompositeParser) tikaConf.getParser();
}
@Test
public void can_parse_mp3_files() throws Exception {
ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
ToHTMLContentHandler toHtmlContentHandler = new
ToHTMLContentHandler(outputStream, "UTF-8"); // Extract
// always
// HTML
// by
// default
WriteOutContentHandler handler = new
WriteOutContentHandler(toHtmlContentHandler, (int) 4000000);
ContentHandler bodyHandler = new BodyContentHandler(handler);
InputStream input = getClass().getResourceAsStream("/mp3/test.mp3");
try {
ParseContext context = new ParseContext(); // parsing
context.set(Parser.class, parser);
Metadata metadata = new Metadata();
metadata.add(Metadata.RESOURCE_NAME_KEY, "12345");
metadata.add(Metadata.CONTENT_TYPE, "audio/mpeg");
parser.parse(input, bodyHandler, metadata, context);
} finally {
IOUtils.closeQuietly(input);
}
String output = outputStream.toString("UTF-8");
assertThat(output).isNotEmpty(); // failed
System.out.println(output);
}
}
{code}
Here's stack error
{noformat}
org.xml.sax.SAXException: Namespace http://www.w3.org/1999/xhtml not declared
at
org.apache.tika.sax.ToXMLContentHandler$ElementInfo.getPrefix(ToXMLContentHandler.java:62)
at
org.apache.tika.sax.ToXMLContentHandler$ElementInfo.getQName(ToXMLContentHandler.java:68)
at
org.apache.tika.sax.ToXMLContentHandler.startElement(ToXMLContentHandler.java:148)
at
org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
at
org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
at
org.apache.tika.sax.xpath.MatchingContentHandler.startElement(MatchingContentHandler.java:60)
at
org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
at
org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
at
org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
at
org.apache.tika.sax.SafeContentHandler.startElement(SafeContentHandler.java:264)
at
org.apache.tika.sax.XHTMLContentHandler.startElement(XHTMLContentHandler.java:254)
at
org.apache.tika.sax.XHTMLContentHandler.startElement(XHTMLContentHandler.java:284)
at
org.apache.tika.sax.XHTMLContentHandler.element(XHTMLContentHandler.java:323)
at org.apache.tika.parser.mp3.Mp3Parser.parse(Mp3Parser.java:107)
at org.apache.tika.parser.ParserDecorator.parse(ParserDecorator.java:91)
at
org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:242)
at
com.polyspot.document.converter.Mp3ParserTest.can_parse_mp3_files(Mp3ParserTest.java:49)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
at java.lang.reflect.Method.invoke(Method.java:597)
at
org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:47)
at
org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
at
org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:44)
at
org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
at
org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26)
at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:271)
at
org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:70)
at
org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:50)
at org.junit.runners.ParentRunner$3.run(ParentRunner.java:238)
at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:63)
at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:236)
at org.junit.runners.ParentRunner.access$000(ParentRunner.java:53)
at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:229)
at org.junit.runners.ParentRunner.run(ParentRunner.java:309)
at
org.eclipse.jdt.internal.junit4.runner.JUnit4TestReference.run(JUnit4TestReference.java:50)
at
org.eclipse.jdt.internal.junit.runner.TestExecution.run(TestExecution.java:38)
at
org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:467)
at
org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:683)
at
org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.run(RemoteTestRunner.java:390)
at
org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.main(RemoteTestRunner.java:197)
{noformat}
was (Author: thaichat04):
[~davemeikle], here's a sample test failed on this file with 1.5-SNAPSHOT, but
passed on 1.4:
{code}
package com.polyspot.document.converter;
import static org.fest.assertions.Assertions.assertThat;
import java.io.ByteArrayOutputStream;
import java.io.InputStream;
import org.apache.commons.io.IOUtils;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.CompositeParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.ToHTMLContentHandler;
import org.apache.tika.sax.WriteOutContentHandler;
import org.junit.Before;
import org.junit.Test;
import org.xml.sax.ContentHandler;
public class Mp3ParserTest {
private ConverterConfiguration config;
private CompositeParser parser;
@Before
public void before() throws Exception {
config = new ConverterConfiguration();
config.setMimeToConverter("src/test/resources/mimeToConverter.xml");
config.setSizeLimit(400000);
TikaConfig tikaConf = new TikaConfig(config.getMimeToConverter().trim());
parser = (CompositeParser) tikaConf.getParser();
}
@Test
public void can_parse_mp3_files() throws Exception {
ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
ToHTMLContentHandler toHtmlContentHandler = new
ToHTMLContentHandler(outputStream, "UTF-8"); // Extract
// always
// HTML
// by
// default
WriteOutContentHandler handler = new
WriteOutContentHandler(toHtmlContentHandler, (int) 4000000);
ContentHandler bodyHandler = new BodyContentHandler(handler);
InputStream input = getClass().getResourceAsStream("/mp3/test.mp3");
try {
ParseContext context = new ParseContext(); // parsing
context.set(Parser.class, parser);
Metadata metadata = new Metadata();
metadata.add(Metadata.RESOURCE_NAME_KEY, "12345");
metadata.add(Metadata.CONTENT_TYPE, "audio/mpeg");
parser.parse(input, bodyHandler, metadata, context);
} finally {
IOUtils.closeQuietly(input);
}
String output = outputStream.toString("UTF-8");
assertThat(output).isNotEmpty(); // failed
}
}
{code}
Here's stack error
{noformat}
org.xml.sax.SAXException: Namespace http://www.w3.org/1999/xhtml not declared
at
org.apache.tika.sax.ToXMLContentHandler$ElementInfo.getPrefix(ToXMLContentHandler.java:62)
at
org.apache.tika.sax.ToXMLContentHandler$ElementInfo.getQName(ToXMLContentHandler.java:68)
at
org.apache.tika.sax.ToXMLContentHandler.startElement(ToXMLContentHandler.java:148)
at
org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
at
org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
at
org.apache.tika.sax.xpath.MatchingContentHandler.startElement(MatchingContentHandler.java:60)
at
org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
at
org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
at
org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
at
org.apache.tika.sax.SafeContentHandler.startElement(SafeContentHandler.java:264)
at
org.apache.tika.sax.XHTMLContentHandler.startElement(XHTMLContentHandler.java:254)
at
org.apache.tika.sax.XHTMLContentHandler.startElement(XHTMLContentHandler.java:284)
at
org.apache.tika.sax.XHTMLContentHandler.element(XHTMLContentHandler.java:323)
at org.apache.tika.parser.mp3.Mp3Parser.parse(Mp3Parser.java:107)
at org.apache.tika.parser.ParserDecorator.parse(ParserDecorator.java:91)
at
org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:242)
at
com.polyspot.document.converter.Mp3ParserTest.can_parse_mp3_files(Mp3ParserTest.java:49)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
at java.lang.reflect.Method.invoke(Method.java:597)
at
org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:47)
at
org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
at
org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:44)
at
org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
at
org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26)
at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:271)
at
org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:70)
at
org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:50)
at org.junit.runners.ParentRunner$3.run(ParentRunner.java:238)
at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:63)
at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:236)
at org.junit.runners.ParentRunner.access$000(ParentRunner.java:53)
at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:229)
at org.junit.runners.ParentRunner.run(ParentRunner.java:309)
at
org.eclipse.jdt.internal.junit4.runner.JUnit4TestReference.run(JUnit4TestReference.java:50)
at
org.eclipse.jdt.internal.junit.runner.TestExecution.run(TestExecution.java:38)
at
org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:467)
at
org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:683)
at
org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.run(RemoteTestRunner.java:390)
at
org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.main(RemoteTestRunner.java:197)
{noformat}
> Regression: Unable to parse a mp3 file on 1.5 which parsed successfully on 1.4
> ------------------------------------------------------------------------------
>
> Key: TIKA-1215
> URL: https://issues.apache.org/jira/browse/TIKA-1215
> Project: Tika
> Issue Type: Bug
> Components: parser
> Affects Versions: 1.5
> Reporter: Hong-Thai Nguyen
> Priority: Critical
> Attachments: Centres 080805@0650 RTBF Matin Première - A propos des
> rues de Dublin et Dubreucq.mp3
>
>
> With attached file, 1.5 raises this exception on parsing. This file has no
> problem on 1.4
> {code}
> ...
> Caused by: org.xml.sax.SAXException: Namespace http://www.w3.org/1999/xhtml
> not declared
> at
> org.apache.tika.sax.ToXMLContentHandler$ElementInfo.getPrefix(ToXMLContentHandler.java:62)
> at
> org.apache.tika.sax.ToXMLContentHandler$ElementInfo.getQName(ToXMLContentHandler.java:68)
> at
> org.apache.tika.sax.ToXMLContentHandler.startElement(ToXMLContentHandler.java:148)
> at
> org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
> at
> org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
> at
> org.apache.tika.sax.xpath.MatchingContentHandler.startElement(MatchingContentHandler.java:60)
> at
> org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
> at
> org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
> at
> org.apache.tika.sax.ContentHandlerDecorator.startElement(ContentHandlerDecorator.java:126)
> at
> org.apache.tika.sax.SafeContentHandler.startElement(SafeContentHandler.java:264)
> at
> org.apache.tika.sax.XHTMLContentHandler.startElement(XHTMLContentHandler.java:254)
> at
> org.apache.tika.sax.XHTMLContentHandler.startElement(XHTMLContentHandler.java:284)
> at
> org.apache.tika.sax.XHTMLContentHandler.element(XHTMLContentHandler.java:323)
> at org.apache.tika.parser.mp3.Mp3Parser.parse(Mp3Parser.java:107)
> at org.apache.tika.parser.ParserDecorator.parse(ParserDecorator.java:91)
> at
> org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:242)
> at
> com.polyspot.document.converter.DocumentConverter.realizeTikaConversion(DocumentConverter.java:221)
> ... 15 more
> {code}
--
This message was sent by Atlassian JIRA
(v6.1.5#6160)