[ 
https://issues.apache.org/jira/browse/TIKA-1215?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13860246#comment-13860246
 ] 

Hong-Thai Nguyen commented on TIKA-1215:
----------------------------------------

[~davemeikle], here's a sample test failed on this file:
{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);
      parser.parse(input, bodyHandler, new Metadata(), context);
    } finally {
      IOUtils.closeQuietly(input);
    }
    
    String output = outputStream.toString("UTF-8");    
    assertThat(output).isNotEmpty(); // failed
  }
}
{code}

> Regression: Unable 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)

Reply via email to