gestion des métadonnées

wikipedia_to_hdoc/ant/wiki_to_hdoc_fetcher.ant

 <?xml version="1.0" encoding="UTF-8"?>
+
 <project name="wikiToHdoc" default="main" basedir="..">
     
     <!-- wikipediaUrl and destination are the only required parameters -->
@@ -21,6 +22,7 @@
         <antcall target="clean"/>
         <antcall target="prepare"/>
         <antcall target="prepareHdocStructure"/>
+        <antcall target="getImgMetadata"/>
         <antcall target="transformWikiToHdoc"/>
         <antcall target="zip"/>
     </target>
@@ -75,7 +77,29 @@
         </echoxml>
         <xslt classpath="lib/saxon9he.jar" in="${tmpFolderPath}/containerTmp.xml" out="${tmpHdocResultFolderPath}/META-INF/container.xml" style="${xsltFolderPath}/addNamespaceToContainer.xsl"/>
     </target>
-    
+    <target name="getImgMetadata">
+        <!--  Preparing the links for the metadata extraction      -->
+        <xslt classpath="lib/saxon9he.jar" in="${tmpFolderPath}/${filename}_prepared.xml" out="${hdocResultPath}/img_metadata_link.xml" style="${xsltFolderPath}/prepare_img_link_metadata.xsl">
+            <factory name="net.sf.saxon.TransformerFactoryImpl"/>
+        </xslt>
+        
+        <xmlproperty file="${hdocResultPath}/img_metadata_link.xml" prefix="TEST"/>  
+        <taskdef resource="net/sf/antcontrib/antlib.xml">
+            <classpath>
+                <pathelement location="/usr/share/java/lib/ant-contrib-version.jar"/>
+            </classpath>
+        </taskdef>       
+        <for list="${TEST.images.image.link}" param="file">
+            <sequential>
+                  <!--       <loadresource  encoding="UTF-8" property="myURL">
+                             <url url="@{file}"/>
+                </loadresource>
+                <echo file="${hdocResultPath}/@{file}/test.xml" encoding="UTF-8">${myURL}</echo>   -->             
+                <echo>@{file}</echo>
+            </sequential>
+        </for>
+        
+    </target>
     <target name="transformWikiToHdoc">
         <!-- Applying wikipedia -> hdoc -->
         <xslt classpath="lib/saxon9he.jar" in="${tmpFolderPath}/${filename}_prepared.xml" out="${hdocResultPath}/${filename}.html" style="${xsltFolderPath}/wiki_to_hdoc.xsl">

wikipedia_to_hdoc/xslt/prepare_img_link_metadata.xsl

+<?xml version="1.0" encoding="UTF-8"?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+    xmlns:xs="http://www.w3.org/2001/XMLSchema"
+    exclude-result-prefixes="xs"
+    version="2.0">
+    <xsl:output encoding="UTF-8"/>
+
+    <xsl:template match="html">
+        <images>
+            <xsl:apply-templates select=".//a[img]"/>
+        </images>
+    </xsl:template>
+    <xsl:template match="a[img]">
+        <image>
+            <link>
+                <xsl:text>https://fr.wikipedia.org</xsl:text><xsl:value-of select="@href"/>             
+            </link>
+            <ref>
+                <xsl:value-of select="./img/@src"/>
+            </ref>
+        </image>
+    </xsl:template>
+    
+  
+</xsl:stylesheet>
\ No newline at end of file