luetzkendorf 2005/04/04 06:51:59
Modified: src/conf/webapp Extractor-Domain.xml
Log:
exctractor configuration updated
Revision Changes Path
1.2 +18 -12 jakarta-slide/src/conf/webapp/Extractor-Domain.xml
Index: Extractor-Domain.xml
===================================================================
RCS file: /home/cvs/jakarta-slide/src/conf/webapp/Extractor-Domain.xml,v
retrieving revision 1.1
retrieving revision 1.2
diff -u -r1.1 -r1.2
--- Extractor-Domain.xml 29 Jun 2004 08:10:58 -0000 1.1
+++ Extractor-Domain.xml 4 Apr 2005 13:51:59 -0000 1.2
@@ -281,27 +281,33 @@
<extractors>
<extractor classname="org.apache.slide.extractor.SimpleXmlExtractor"
uri="/files/articles/test.xml">
<configuration>
- <instruction property="title" xpath="/article/title/text()"
/>
- <instruction property="summary"
xpath="/article/summary/text()" />
+ <instruction property="title"
namespace="http://jakarta.apache.org/slide/"
+ xpath="/article/title/text()" />
+ <instruction property="summary"
namespace="http://jakarta.apache.org/slide/"
+ xpath="/article/summary/text()" />
</configuration>
</extractor>
<extractor classname="org.apache.slide.extractor.OfficeExtractor"
uri="/files/docs/">
<configuration>
- <instruction property="author" id="SummaryInformation-0-4" />
- <instruction property="application"
id="SummaryInformation-0-18" />
+ <instruction property="author"
namespace="http://jakarta.apache.org/slide/"
+ summary-information="4"/>
+ <instruction property="application"
namespace="http://jakarta.apache.org/slide/"
+ summary-information="18"/>
</configuration>
+ </extractor>
+
+ <!-- content extractors -->
+ <extractor
classname="org.apache.slide.extractor.TextContentExtractor" uri="/files/">
+ </extractor>
+ <extractor
classname="org.apache.slide.extractor.XmlContentExtractor" uri="/files/">
</extractor>
- <extractor classname="org.apache.slide.extractor.MSWordExtractor"
uri="/files/"
- content-type="application/ms-word">
+ <extractor classname="org.apache.slide.extractor.MSWordExtractor"
uri="/files/">
</extractor>
- <extractor classname="org.apache.slide.extractor.MSExcelExtractor"
uri="/files/"
- content-type="application/ms-excel">
+ <extractor classname="org.apache.slide.extractor.MSExcelExtractor"
uri="/files/">
</extractor>
- <extractor
classname="org.apache.slide.extractor.MSPowerPointExtractor" uri="/files/"
- content-type="application/vnd.ms-powerpoint">
+ <extractor
classname="org.apache.slide.extractor.MSPowerPointExtractor" uri="/files/">
</extractor>
- <extractor classname="org.apache.slide.extractor.PDFExtractor"
uri="/files/"
- content-type="application/pdf">
+ <extractor classname="org.apache.slide.extractor.PDFExtractor"
uri="/files/">
</extractor>
</extractors>
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]