<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: Metadata extractor in Alfresco Archive</title>
    <link>https://connect.hyland.com/t5/alfresco-archive/metadata-extractor/m-p/56372#M34065</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;SPAN&gt;The package you want to look at is:&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;org.alfresco.repo.content.metadata&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;Found in the Repository project, this contains the various meta-data extractor class implementations and the MetadataExtractorRegistry.&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;The configuration for the meta-data extractors (you can add your own) is found in config/alfresco/content-services-context.xml in this section:&lt;/SPAN&gt;&lt;BR /&gt;&lt;PRE class="language-none line-numbers"&gt;&lt;CODE&gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;!– Content Metadata Extracters –&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;bean class="org.alfresco.repo.content.metadata.PdfBoxMetadataExtracter" parent="baseMetadataExtracter" /&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;bean class="org.alfresco.repo.content.metadata.OfficeMetadataExtracter" parent="baseMetadataExtracter" /&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;bean class="org.alfresco.repo.content.metadata.MailMetadataExtracter" parent="baseMetadataExtracter" /&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;bean class="org.alfresco.repo.content.metadata.HtmlMetadataExtracter" parent="baseMetadataExtracter" /&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;bean class="org.alfresco.repo.content.metadata.MP3MetadataExtracter" parent="baseMetadataExtracter" /&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;bean class="org.alfresco.repo.content.metadata.OpenDocumentMetadataExtracter" parent="baseMetadataExtracter" /&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;bean class="org.alfresco.repo.content.metadata.OpenOfficeMetadataExtracter" parent="baseMetadataExtracter" init-method="init" &amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; &amp;lt;property name="connection"&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; &amp;lt;ref bean="openOfficeConnection" /&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; &amp;lt;/property&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;/bean&amp;gt;&lt;BR /&gt;&lt;SPAN class="line-numbers-rows"&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/CODE&gt;&lt;/PRE&gt;&lt;BR /&gt;&lt;SPAN&gt;Hope this helps,&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;Kevin&lt;/SPAN&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Fri, 16 Mar 2007 16:39:04 GMT</pubDate>
    <dc:creator>kevinr</dc:creator>
    <dc:date>2007-03-16T16:39:04Z</dc:date>
    <item>
      <title>Metadata extractor</title>
      <link>https://connect.hyland.com/t5/alfresco-archive/metadata-extractor/m-p/56370#M34063</link>
      <description>Hi,Does anyone know how to extract custom metadata using the metadata extractor from alfresco, or how to use the metadata extractor at all?I searched the whole forum and the wiki but couldn't find anything on how to use the metadata extractor from alfresco.I hope someone can help me with this proble</description>
      <pubDate>Wed, 14 Mar 2007 10:20:17 GMT</pubDate>
      <guid>https://connect.hyland.com/t5/alfresco-archive/metadata-extractor/m-p/56370#M34063</guid>
      <dc:creator>dleeuwen</dc:creator>
      <dc:date>2007-03-14T10:20:17Z</dc:date>
    </item>
    <item>
      <title>Re: Metadata extractor</title>
      <link>https://connect.hyland.com/t5/alfresco-archive/metadata-extractor/m-p/56371#M34064</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;SPAN&gt;Anyone? Or does anyone know where to find the file wich contains the java class or something, so I can modify it.&lt;/SPAN&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Fri, 16 Mar 2007 10:18:18 GMT</pubDate>
      <guid>https://connect.hyland.com/t5/alfresco-archive/metadata-extractor/m-p/56371#M34064</guid>
      <dc:creator>dleeuwen</dc:creator>
      <dc:date>2007-03-16T10:18:18Z</dc:date>
    </item>
    <item>
      <title>Re: Metadata extractor</title>
      <link>https://connect.hyland.com/t5/alfresco-archive/metadata-extractor/m-p/56372#M34065</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;SPAN&gt;The package you want to look at is:&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;org.alfresco.repo.content.metadata&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;Found in the Repository project, this contains the various meta-data extractor class implementations and the MetadataExtractorRegistry.&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;The configuration for the meta-data extractors (you can add your own) is found in config/alfresco/content-services-context.xml in this section:&lt;/SPAN&gt;&lt;BR /&gt;&lt;PRE class="language-none line-numbers"&gt;&lt;CODE&gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;!– Content Metadata Extracters –&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;bean class="org.alfresco.repo.content.metadata.PdfBoxMetadataExtracter" parent="baseMetadataExtracter" /&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;bean class="org.alfresco.repo.content.metadata.OfficeMetadataExtracter" parent="baseMetadataExtracter" /&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;bean class="org.alfresco.repo.content.metadata.MailMetadataExtracter" parent="baseMetadataExtracter" /&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;bean class="org.alfresco.repo.content.metadata.HtmlMetadataExtracter" parent="baseMetadataExtracter" /&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;bean class="org.alfresco.repo.content.metadata.MP3MetadataExtracter" parent="baseMetadataExtracter" /&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;bean class="org.alfresco.repo.content.metadata.OpenDocumentMetadataExtracter" parent="baseMetadataExtracter" /&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;bean class="org.alfresco.repo.content.metadata.OpenOfficeMetadataExtracter" parent="baseMetadataExtracter" init-method="init" &amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; &amp;lt;property name="connection"&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; &amp;lt;ref bean="openOfficeConnection" /&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; &amp;lt;/property&amp;gt;&lt;BR /&gt;&amp;nbsp;&amp;nbsp; &amp;lt;/bean&amp;gt;&lt;BR /&gt;&lt;SPAN class="line-numbers-rows"&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;SPAN&gt;‍&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/CODE&gt;&lt;/PRE&gt;&lt;BR /&gt;&lt;SPAN&gt;Hope this helps,&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;Kevin&lt;/SPAN&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Fri, 16 Mar 2007 16:39:04 GMT</pubDate>
      <guid>https://connect.hyland.com/t5/alfresco-archive/metadata-extractor/m-p/56372#M34065</guid>
      <dc:creator>kevinr</dc:creator>
      <dc:date>2007-03-16T16:39:04Z</dc:date>
    </item>
    <item>
      <title>Re: Metadata extractor</title>
      <link>https://connect.hyland.com/t5/alfresco-archive/metadata-extractor/m-p/56373#M34066</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;SPAN&gt;Yes this helps, now I know where too look at. Thanks a lot,&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;Danny&lt;/SPAN&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Mon, 19 Mar 2007 07:34:29 GMT</pubDate>
      <guid>https://connect.hyland.com/t5/alfresco-archive/metadata-extractor/m-p/56373#M34066</guid>
      <dc:creator>dleeuwen</dc:creator>
      <dc:date>2007-03-19T07:34:29Z</dc:date>
    </item>
    <item>
      <title>Re: Metadata extractor</title>
      <link>https://connect.hyland.com/t5/alfresco-archive/metadata-extractor/m-p/56374#M34067</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;SPAN&gt;Maybe a stupid question but I have tried to find the directory but I couldn't find it. Is this because I use the installer from the enterprise edition? Anyway, do you know where I could find the package org.alfresco.repo.content.metadata? Is it in a JAR file or something?&lt;/SPAN&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Mon, 19 Mar 2007 08:43:52 GMT</pubDate>
      <guid>https://connect.hyland.com/t5/alfresco-archive/metadata-extractor/m-p/56374#M34067</guid>
      <dc:creator>dleeuwen</dc:creator>
      <dc:date>2007-03-19T08:43:52Z</dc:date>
    </item>
    <item>
      <title>Re: Metadata extractor</title>
      <link>https://connect.hyland.com/t5/alfresco-archive/metadata-extractor/m-p/56375#M34068</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;SPAN&gt;You need to download the SDK to access the source - the package structure mentioned will be in the 'repository' project source/java dir.&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;Thanks,&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;Kevin&lt;/SPAN&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Tue, 20 Mar 2007 08:55:31 GMT</pubDate>
      <guid>https://connect.hyland.com/t5/alfresco-archive/metadata-extractor/m-p/56375#M34068</guid>
      <dc:creator>kevinr</dc:creator>
      <dc:date>2007-03-20T08:55:31Z</dc:date>
    </item>
  </channel>
</rss>

