Merge branch 'master' of gitlab.utc.fr:crozatst/hdoc

framapad_to_hdoc/README.md

@@ -54,7 +54,14 @@ Example :
 
 Currently available on: https://framemo.org/framapad_to_opale
 
+See also : https://bimestriel.framapad.org/p/nf29_framapad_to_opale for the full documentation of our working process.
+
 ## TODO
+- Nested Lists
+- Indentation
+- Titles (and therefore Structure of the doc)
+- Coloured text
+- Code
 - Markdown
 
 ## Technical notes

hdoc_to_elasticSearch/build.properties

 libdir=${basedir}/lib
 xsldir=${basedir}/xsl
 inputPath=${basedir}/input
-outputPath=${basedir}/output
\ No newline at end of file
+tmpHdoc=${basedir}/tmp_hdoc
+outputPath=${basedir}/output

hdoc_to_elasticSearch/hdoc_to_elasticsearch.ant

-<project name="hdoc_to_elasticsearch" default="unzipSource">
-
-	<property file="build.properties"/>
-    <target name="unzipSource">
+<project name="hdoc_to_elasticsearch" default="clean"> 
+	
+	<property file="build.properties"/>     
+	
+	<target name="unzipSource">
 		<echo message="Conversion begin" />
 		<path id="hdocDirPath">
 			<fileset dir="${inputPath}" id="hdocFile">
-				<include name="*.hdoc"/>
-			</fileset> 
+			<include name="*.hdoc"/>
+			</fileset>
 		</path>
-		
-		<property name="hdocFile" refId="hdocDirPath"/>
+		<property name="hdocFile" refId="hdocDirPath"/> 		
 		<basename property="hdocFileName" file="${hdocFile}" suffix=".hdoc"/>
-		
-        <echo>Entry file : ${hdocFileName}</echo>
-		
+		<echo>Entry file : ${hdocFileName}</echo>
+
 		<!-- create subdirectory for each file -->
-		<mkdir dir="${outputPath}/${hdocFileName}"/>
-		
-		<!--unzips the hdoc to be converted into the previously created directory-->
-		<unzip dest="${outputPath}/${hdocFileName}">
-			<fileset dir="${inputPath}" id="hdocFile">
-				<include name="${hdocFileName}.hdoc"/>
-			</fileset> 
-		</unzip>
-		<echo message="Conversion end" />
-    </target>
+		<mkdir dir="${tmpHdoc}/${hdocFileName}"/>
+
+		<!--unzips the hdoc to be converted into the previously created directory--> 
+		<unzip dest="${tmpHdoc}/${hdocFileName}">
+			<fileset dir="${inputPath}" id="hdocFile"> 			
+				<include name="${hdocFileName}.hdoc"/> 			
+			</fileset> 		
+		</unzip> 		
+
+	</target> 		
 	
 	<target name="jsonFiles" depends="unzipSource"> 
-		<echo message="JSON File creation" />
-		<!-- TODO : create JSON & extract data -->
-	</target>
-	
+		<echo message="JSON File creation" /> 		
+		<xslt in="${tmpHdoc}/${hdocFileName}/content.xml" out="${outputPath}/${hdocFileName}.json" style="xsl/content_extractor.xsl"/>
+	</target> 			
 	
-	<!-- Clear tmp files -->
-	<target name="clean" depends="jsonFiles">
-     
-    </target>
+	<!-- Clear tmp files --> 	
+	<target name="clean" depends="jsonFiles">         
+		<echo message="Clean files" />
+		<!-- -->
+		<delete includeemptydirs="true" verbose="true">
+			<fileset dir="${tmpHdoc}"> </fileset>
+			<dirset dir="${tmpHdoc}" includes="**/*" />
+		</delete>
+		<echo message="Conversion end" />
+	</target> 	
+
+</project>
 
-	<echo message="Conversion end" />
-</project>
\ No newline at end of file

hdoc_to_elasticSearch/xsl/content_extractor.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"    
+				xpath-default-namespace="http://www.utc.fr/ics/hdoc/xhtml"     
+				exclude-result-prefixes="xs"   
+				version="2.0">
+	
+	<xsl:output omit-xml-declaration="yes"
+				encoding="UTF-8">
+		<!-- Encodage UTF-8 pour caractères spéciaux (accents...) -->
+	</xsl:output> 
+	
+
+	
+	<!-- -->
+	<xsl:template match="/" >
+	{
+			<xsl:apply-templates select="html"/>
+
+	}	
+	</xsl:template>
+	
+	<!-- Extraction des informations du head -->
+	<xsl:template match="head">
+		"title" : "<xsl:value-of select="title/text()"/>",
+		
+		"keywords" : [
+				<xsl:for-each select="meta[@name='keywords']">
+					"<xsl:value-of select="@content"/>"<xsl:if test="position() != last()">,</xsl:if>			
+				</xsl:for-each>
+		],
+		<xsl:apply-templates select="meta"/>
+	</xsl:template>
+	
+	<!-- Extraction des informations du body -->
+	<xsl:template match="body" />
+	
+	<xsl:template match="meta[@name='author']">
+		"author" : "<xsl:value-of select="@content"/>"		
+	</xsl:template>
+	
+	<xsl:template match="meta[@name='date']">
+		"date" : "<xsl:value-of select="@content"/>",		
+	</xsl:template>
+	
+	<xsl:template match="meta[@name='rights']">
+		"rights" : "<xsl:value-of select="@content"/>",	
+	</xsl:template>
+	
+
+				
+</xsl:stylesheet>
\ No newline at end of file

hdoc_to_epub/README.md

@@ -35,15 +35,23 @@ La personne possède un hdoc et voudrait le convertir en epub. Il se dirige vers
 Unsupported
 -----------
 
-
-
 Known bugs
 ----------
 
+Problème dans le hdoc : contient des images mais ne sont pas référencées.
+
+Problème avec les keywords : le hdoc contient des keywords mais nous ne savons pas où les utiliser.
 
 Todo list
 ---------
 
+Validation de l'epub actuel
+
+Mise en place de la première page
+
+Validation
+
+Étude compatibilité entre EPUB2 et EPUB3
 
 Technical Notes
 ---------------

hdoc_to_epub/file/container.xml

 <?xml version="1.0"?>
 <container xmlns="urn:oasis:names:tc:opendocument:xmlns:container" version="1.0">
   <rootfiles>
-    <rootfile full-path="OEBPS/content.opf" media-type="application/oebps-package+xml"/>
+    <rootfile full-path="oebps/content.opf" media-type="application/oebps-package+xml"/>
   </rootfiles>
 </container>

hdoc_to_epub/hdoc_to_epub.ant

@@ -7,9 +7,12 @@
   <property name="in" location="${basedir}/input"/>
   <property name="out" location="${basedir}/output"/>
   <property name="tmp" location="${basedir}/tmp"/>
+  <property name="xsl" location="${basedir}/xsl"/>
   <property name="file" location="${basedir}/file"/>
   <property name="schema" location="${basedir}/schema"/>
-
+  <property name="lib" location="${basedir}/lib"/>
+  <property name="tmpRetour" location="${basedir}/tmp/retour"/>
+  
   <target name="convert">
     <delete dir="${tmp}" failonerror="false"/>
     <sleep seconds="1"/>
@@ -18,6 +21,8 @@
     <delete dir="${out}" failonerror="false"/>
     <sleep seconds="1"/>
     <mkdir dir="${out}"/>
+  
+    <mkdir dir="${tmpRetour}"/>
 
     <for param="inputFile">
       <path>
@@ -27,7 +32,7 @@
       <sequential>
         <local name="filename"/>
         <basename property="filename" file="@{inputFile}"/>
-
+        
         <antcall target="UnzipHdocFile">
           <param name="filename" value="${filename}"/>
         </antcall>
@@ -36,12 +41,27 @@
           <param name="filename" value="${filename}"/>
         </antcall>
 
-        <antcall target="MakeOCF"/>
+        <antcall target="MakeOCF">
+          <param name="filename" value="${filename}"/>
+        </antcall>
 
-        <!--<antcall target="MakeOPF"/> -->
+        <antcall target="MakeOPF">
+          <param name="filename" value="${filename}"/>
+        </antcall>
+
+        <antcall target="MakeOPS">
+          <param name="filename" value="${filename}"/>
+        </antcall>
 
-        <antcall target="MakeOPS"/>
+        <antcall target="ZipEpubFile">
+          <param name="filename" value="${filename}"/>
+        </antcall>
 
+        <antcall target="ValidateOutput">
+          <param name="filename" value="${filename}"/>
+        </antcall>
+        
+        <antcall target="CleanTmp"/>
       </sequential>
     </for>
   </target>
@@ -66,20 +86,49 @@
 	</target>
 
   <target name="MakeOCF">
-    <mkdir dir="${out}/META-INF"/>
-    <mkdir dir="${out}/oebps"/>
-    <copy file="${file}/mimetype" todir="${out}"/>
-    <copy file="${file}/container.xml" todir="${out}/META-INF"/>
+    <mkdir dir="${tmpRetour}/META-INF"/>
+    <mkdir dir="${tmpRetour}/oebps"/>
+    <copy file="${file}/mimetype" todir="${tmpRetour}"/>
+    <copy file="${file}/container.xml" todir="${tmpRetour}/META-INF"/>
   </target>
 
   <target name="MakeOPF">
-
+    <xslt in="${tmp}/${filename}/decompressedHdoc/content.xml" out="${tmpRetour}/oebps/content.opf" classpath="${lib}/saxon9he.jar" style="${xsl}/content.xsl"/>
   </target>
 
   <target name="MakeOPS">
-    <mkdir dir="${out}/oebps/images"/>
-    <mkdir dir="${out}/oebps/styles"/>
-    <mkdir dir="${out}/oebps/text"/>
+    <mkdir dir="${tmpRetour}/oebps/images"/>
+    <copy todir="${tmpRetour}/oebps/images">
+      <fileset dir="${tmp}/${filename}/decompressedHdoc/re" includes="**"/>
+    </copy>
+    <mkdir dir="${tmpRetour}/oebps/styles"/>
+    <mkdir dir="${tmpRetour}/oebps/chapitres"/>
+    <xslt in="${tmp}/${filename}/decompressedHdoc/content.xml" out="${tmpRetour}/oebps/tableDesMatieres.ncx" classpath="${lib}/saxon9he.jar" style="${xsl}/tdmncx.xsl"/>
+    <xslt destdir="${tmpRetour}/oebps/chapitres" basedir="${tmp}/${filename}/decompressedHdoc" includes="content.xml" classpath="${lib}/saxon9he.jar" style="${xsl}/chapitre.xsl"/>
+    <delete file="${tmpRetour}/oebps/chapitres/content.html"/>
   </target>
 
+  <target name="ZipEpubFile">
+    <propertyregex property="properFilename" input="${filename}" regexp=".hdoc" replace="" casesensitive="false" override="true" />
+    <zip destfile="${out}/${properFilename}.epub" update="true" encoding="UTF-8">
+      <zipfileset dir="${tmpRetour}/META-INF"
+        includes="*" prefix="META-INF"/>
+      <zipfileset dir="${tmpRetour}/oebps"
+        includes="**" prefix="oebps"/>
+    </zip>
+    <!-- zip64Mode="never" -->
+    <zip destfile="${out}/${properFilename}.epub" update="true" compress="false" encoding="UTF-8" keepcompression="true" createunicodeextrafields="never">
+      <zipfileset dir="${tmpRetour}"
+        includes="mimetype"/>
+    </zip>
+  </target>
+  
+  <target name="ValidateOutput">
+    
+  </target>
+  
+  <target name="CleanTmp">
+    <delete dir="${tmp}" failonerror="false"/>
+  </target>
+  
 </project>

hdoc_to_epub/xsl/chapitre.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"
+    xpath-default-namespace="http://www.utc.fr/ics/hdoc/xhtml"
+    xmlns="http://www.w3.org/1999/xhtml"
+    version="2.0">
+    
+    <xsl:output method="xml" indent="yes" encoding="UTF-8"/>
+    
+    <xsl:template match="/html" priority="10">
+        <xsl:for-each select="body/section">
+            <xsl:variable name="path">../../../retour/oebps/chapitres/chapitre<xsl:number level="multiple" count="section" format="1"/>.xhtml</xsl:variable>
+            <xsl:result-document method="xml" href="{$path}">
+                <html xml:lang="en" lang="en" xmlns:epub="http://www.idpf.org/2007/ops">
+                    <head>
+                        <title><xsl:value-of select="header/h1"/></title>
+                    </head>
+                    <body>
+                        <h1><xsl:value-of select="header/h1"/></h1>
+                        <xsl:apply-templates select="div|section"/>
+                    </body>
+                </html>
+            </xsl:result-document>
+        </xsl:for-each>
+    </xsl:template>
+    
+    <xsl:template match="section" priority="3">
+        <xsl:element name="h{count(ancestor::section)+1}">
+            <xsl:value-of select="header/h1"/>
+            <xsl:apply-templates select="div|section"/>
+        </xsl:element>
+    </xsl:template>
+    
+    <!-- Identity transformation -->
+    <xsl:template match="node()|@*">
+        <xsl:copy>
+            <xsl:apply-templates select="node()|@*"/>
+        </xsl:copy>        
+    </xsl:template>    
+    
+    <!-- Namespace substitution for hdoc elements -->                        
+    <xsl:template match="*" priority="1">
+        <xsl:element name="{local-name()}">
+            <xsl:apply-templates select="node()|@*"/>
+        </xsl:element>
+    </xsl:template>   
+   
+    
+</xsl:stylesheet>
\ No newline at end of file

hdoc_to_epub/xsl/content.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"
+    xmlns:dc="http://www.idpf.org/2007/opf"
+    xpath-default-namespace="http://www.utc.fr/ics/hdoc/xhtml"
+    exclude-result-prefixes="xs"
+    version="2.0">
+
+    <xsl:import href="content/metadata.xsl"/>
+    <xsl:import href="content/manifest.xsl"/>
+    <xsl:import href="content/spine.xsl"/>
+
+    <xsl:output method="xml" indent="yes" encoding="UTF-8"/>
+
+    <xsl:template match="html">
+      <package  unique-identifier="BookID" version="3.0">
+          <xsl:call-template name="metadata"/>
+          <xsl:call-template name="manifest"/>
+          <xsl:call-template name="spine"/>
+      </package>
+    </xsl:template>
+
+    <xsl:template match="text()"/>
+
+</xsl:stylesheet>

hdoc_to_epub/xsl/content/manifest.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"
+    xmlns:dc="http://www.idpf.org/2007/opf"
+    xpath-default-namespace="http://www.utc.fr/ics/hdoc/xhtml"
+    exclude-result-prefixes="xs"
+    version="2.0">
+    <xsl:template name="manifest">
+        <manifest>
+            <item id="tDMncx" href="tableDesMatieres.ncx" media-type="application/x-dtbncx+xml" />
+            <xsl:for-each select="body/section">
+                <item>
+                    <xsl:attribute name="href">chapitres/chapitre<xsl:number level="multiple" count="section" format="1"/>.xhtml</xsl:attribute>
+                    <xsl:attribute name="id">ch<xsl:number level="multiple" count="section" format="1"/></xsl:attribute>
+                    <xsl:attribute name="media-type">application/xhtml+xml</xsl:attribute>
+                </item>
+            </xsl:for-each>
+        </manifest>
+    </xsl:template>
+    
+</xsl:stylesheet>
\ No newline at end of file

hdoc_to_epub/xsl/content/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"
+    xmlns:dc="http://www.idpf.org/2007/opf"
+    xpath-default-namespace="http://www.utc.fr/ics/hdoc/xhtml"
+    exclude-result-prefixes="xs"
+    version="2.0">
+    <xsl:template name="metadata">
+        <metadata>
+            <dc:title><xsl:value-of select="head/title"/></dc:title>
+            <dc:creator><xsl:value-of select="head/meta[@name='author']/@content"/></dc:creator>
+            <dc:language>fr</dc:language>
+        </metadata>
+    </xsl:template>
+    
+</xsl:stylesheet>
\ No newline at end of file

hdoc_to_epub/xsl/content/spine.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"
+    xmlns:dc="http://www.idpf.org/2007/opf"
+    xpath-default-namespace="http://www.utc.fr/ics/hdoc/xhtml"
+    exclude-result-prefixes="xs"
+    version="2.0">
+    <xsl:template name="spine">
+        <spine toc="tDMncx">
+            <xsl:for-each select="body/section">
+                <itemref>
+                    <xsl:attribute name="idref">ch<xsl:number level="multiple" count="section" format="1"/></xsl:attribute>
+                </itemref>
+            </xsl:for-each>
+        </spine>
+    </xsl:template>
+</xsl:stylesheet>
\ No newline at end of file

hdoc_to_epub/xsl/tdmncx.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"
+    xpath-default-namespace="http://www.utc.fr/ics/hdoc/xhtml"
+    xmlns="http://www.daisy.org/z3986/2005/ncx/"
+    version="2.0">
+    
+    <xsl:output method="xml" indent="yes" encoding="UTF-8"/>
+    
+    <xsl:template match="html">
+        <ncx version="2005-1" xml:lang="en-US">
+            <head>
+                <meta content="org-example-5059463624137734586" name="dtb:uid"/>
+            </head>
+            
+            <navMap>
+                <xsl:apply-templates/>
+            </navMap>
+        </ncx>
+    </xsl:template>
+    
+    <xsl:template match="//section">
+        <navPoint>
+            <xsl:attribute name="class">h<xsl:value-of select="count(ancestor::section)+1"/></xsl:attribute>
+            <xsl:attribute name="id">ch_<xsl:number level="multiple" count="section" format="1_1"/></xsl:attribute>
+            <navLabel>
+                <text>
+                    <xsl:value-of select="header/h1"/>
+                </text>
+            </navLabel>
+            <content>
+                <xsl:attribute name="src">content.html#ch_<xsl:number level="multiple" count="section" format="1_1"/></xsl:attribute>
+            </content>
+            <xsl:apply-templates/>
+            
+        </navPoint>
+    </xsl:template>
+    
+    <xsl:template match="text()"/>
+    
+</xsl:stylesheet>
\ No newline at end of file

hdoc_to_mongo/xsl/main.xsl

@@ -8,6 +8,7 @@
     <xsl:import href="subroutines/author.xsl"/>
     <xsl:import href="subroutines/keyword.xsl"/>
     <xsl:import href="subroutines/right.xsl"/>
+	<xsl:import href="subroutines/introduction.xsl"/>
     
     <xsl:output method="text" encoding="UTF-8" omit-xml-declaration="yes"/>
     
@@ -16,7 +17,8 @@
 			"title" : <xsl:call-template name="title-main"/>,
 			"authors" : <xsl:call-template name="author-main"/>,
 			"keywords" : <xsl:call-template name="keyword-main"/>,
-			"rights" : <xsl:call-template name="right-main"/>
+			"rights" : <xsl:call-template name="right-main"/>,
+			"introduction" : <xsl:call-template name="introduction-main"/>
 		}
     </xsl:template>
 	

hdoc_to_mongo/xsl/subroutines/introduction.xsl

+<?xml version="1.0" encoding="UTF-8"?>
+<?target hdoc/content.xml ?>
+<xsl:stylesheet version="2.0" xpath-default-namespace="http://www.utc.fr/ics/hdoc/xhtml"
+	xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+	xmlns:h2m="http://www.utc.fr/hdoc/hdoc_to_mongo">
+	<xsl:import href="../xsl-import/string.xsl"/>
+	<xsl:template name="introduction-main">
+		<xsl:value-of select="h2m:escape-string(string-join(/html/body/section[@data-hdoc-type='introduction']/div/descendant::*/text(), ' '))"/>
+	</xsl:template>
+	
+</xsl:stylesheet> 
\ No newline at end of file

hdoc_to_opale/schema/hdoc1-xhtml.rng

@@ -195,6 +195,11 @@
                         <text/>
                     </element>
                 </optional>
+                <optional>
+                    <element name="div">
+                        <ref name="DivType"/>
+                    </element>
+                </optional>
                 <ref name="Flow"/>
             </element>
         </oneOrMore>

hdoc_to_opale/schema/type.rng

@@ -45,6 +45,8 @@
                     <value>choice-correct</value>
                     <value>choice-incorrect</value>
                     <value>explanation</value>
+                    <value>explanation-choice-correct</value>
+                    <value>explanation-choice-incorrect</value>
                 </choice>
             </attribute>
         </optional>

mindmapping_to_opale/README.md

@@ -62,6 +62,10 @@ You can use special rules in Freemind to personnalize your Scenari Module :
 	* **#wrng** : a warning
 	* **#ex** : an example
 	* **#def** : a definition
+	* **#question** : a MCQ
+	* **#choice-correct** : a correct answer within a MCQ
+	* **#choice-incorrect** : an incorrect answer within a MCQ
+	* **#explanation** : an explanation of the answers within a MCQ
 	* *Then you can add some **#p** inside these node to create the content*
 - You can arrange the order of the node usine the hashtag **#1, #2, #3** etc.
 

wikipedia_to_hdoc/xslt/wiki_to_hdoc.xsl

@@ -309,10 +309,10 @@
             </xsl:if>
         </xsl:if>
     </xsl:template>
-    
+
     
     <!-- Simple Tables -->
-    <xsl:template match="table" mode="textOnly">
+    <xsl:template match="table" mode="#all">
         <xsl:choose>
             <!-- Tables that doesn't contain colspan, rowspan or included tables -->
             <xsl:when test="not(descendant::td/@colspan | descendant::td/@rowspan | descendant::table)">