From b1b5cb5e5e7531524d5a4ebb13d5c0473d6d8926 Mon Sep 17 00:00:00 2001
From: Jean-Francois Dockes <jf@dockes.org>
Date: Thu, 27 Dec 2018 17:55:32 +0100
Subject: [PATCH] added openxml word and xl. Cant do ppt because need page
 looping

---
 src/Makefile.am                   |  3 ++
 src/filters/openxml-meta.xsl      | 49 +++++++++++++++++++++++++++++++
 src/filters/openxml-word-body.xsl | 27 +++++++++++++++++
 src/filters/openxml-xls-body.xsl  | 19 ++++++++++++
 src/sampleconf/mimeconf           |  8 ++---
 5 files changed, 102 insertions(+), 4 deletions(-)
 create mode 100644 src/filters/openxml-meta.xsl
 create mode 100644 src/filters/openxml-word-body.xsl
 create mode 100644 src/filters/openxml-xls-body.xsl

diff --git a/src/Makefile.am b/src/Makefile.am
index bd2e44af..d9566b30 100644
--- a/src/Makefile.am
+++ b/src/Makefile.am
@@ -656,6 +656,9 @@ filters/okular-note.xsl \
 filters/opendoc-body.xsl \
 filters/opendoc-flat.xsl \
 filters/opendoc-meta.xsl \
+filters/openxml-xls-body.xsl \
+filters/openxml-word-body.xsl \
+filters/openxml-meta.xsl \
 filters/ppt-dump.py \
 filters/rcl7z \
 filters/rclabw.py \
diff --git a/src/filters/openxml-meta.xsl b/src/filters/openxml-meta.xsl
new file mode 100644
index 00000000..5a4677a4
--- /dev/null
+++ b/src/filters/openxml-meta.xsl
@@ -0,0 +1,49 @@
+<?xml version="1.0"?>
+<xsl:stylesheet 
+ xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0"
+ xmlns:cp="http://schemas.openxmlformats.org/package/2006/metadata/core-properties"
+ xmlns:dc="http://purl.org/dc/elements/1.1/"
+ xmlns:dcterms="http://purl.org/dc/terms/"
+ xmlns:dcmitype="http://purl.org/dc/dcmitype/"
+ xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
+
+<!--  <xsl:output method="text"/> -->
+  <xsl:output omit-xml-declaration="yes"/>
+
+  <xsl:template match="cp:coreProperties">
+    <xsl:text>&#10;</xsl:text>
+    <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
+    <xsl:text>&#10;</xsl:text>
+    <xsl:apply-templates/>
+  </xsl:template>
+
+  <xsl:template match="dc:creator">
+    <meta>
+    <xsl:attribute name="name">
+      <!-- <xsl:value-of select="name()"/> pour sortir tous les meta avec 
+       le meme nom que dans le xml (si on devenait dc-natif) -->
+      <xsl:text>author</xsl:text> 
+    </xsl:attribute>
+    <xsl:attribute name="content">
+       <xsl:value-of select="."/>
+    </xsl:attribute>
+    </meta>
+    <xsl:text>&#10;</xsl:text>
+  </xsl:template>
+
+  <xsl:template match="dcterms:modified">
+    <meta>
+    <xsl:attribute name="name">
+      <xsl:text>date</xsl:text> 
+    </xsl:attribute>
+    <xsl:attribute name="content">
+       <xsl:value-of select="."/>
+    </xsl:attribute>
+    </meta>
+    <xsl:text>&#10;</xsl:text>
+  </xsl:template>
+
+  <xsl:template match="*">
+  </xsl:template>
+
+</xsl:stylesheet>
diff --git a/src/filters/openxml-word-body.xsl b/src/filters/openxml-word-body.xsl
new file mode 100644
index 00000000..e9962a32
--- /dev/null
+++ b/src/filters/openxml-word-body.xsl
@@ -0,0 +1,27 @@
+<?xml version="1.0"?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0"
+                xmlns:ve="http://schemas.openxmlformats.org/markup-compatibility/2006"
+                xmlns:o="urn:schemas-microsoft-com:office:office"
+                xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
+                xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math"
+                xmlns:v="urn:schemas-microsoft-com:vml"
+                xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing"
+                xmlns:w10="urn:schemas-microsoft-com:office:word"
+                xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+                xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml">
+
+  <xsl:output omit-xml-declaration="yes"/>
+
+  <xsl:template match="/">
+    <div>
+      <xsl:apply-templates/> 
+    </div>
+  </xsl:template>
+
+  <xsl:template match="w:p">
+    <p>
+      <xsl:value-of select="."/>
+    </p>
+  </xsl:template>
+
+</xsl:stylesheet>
diff --git a/src/filters/openxml-xls-body.xsl b/src/filters/openxml-xls-body.xsl
new file mode 100644
index 00000000..5c0d6c71
--- /dev/null
+++ b/src/filters/openxml-xls-body.xsl
@@ -0,0 +1,19 @@
+<?xml version="1.0"?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0"
+                xmlns:x="http://schemas.openxmlformats.org/spreadsheetml/2006/main">
+
+  <xsl:output omit-xml-declaration="yes"/>
+
+  <xsl:template match="/">
+    <div>
+      <xsl:apply-templates/> 
+    </div>
+  </xsl:template>
+
+  <xsl:template match="x:t">
+    <p>
+      <xsl:value-of select="."/>
+    </p>
+  </xsl:template>
+
+</xsl:stylesheet>
diff --git a/src/sampleconf/mimeconf b/src/sampleconf/mimeconf
index 7a0e8850..103daee2 100644
--- a/src/sampleconf/mimeconf
+++ b/src/sampleconf/mimeconf
@@ -88,17 +88,17 @@ application/vnd.oasis.opendocument.presentation-flat-xml = internal xsltproc ope
 application/vnd.oasis.opendocument.text-flat-xml = internal xsltproc opendoc-flat.xsl
 application/vnd.oasis.opendocument.spreadsheet-flat-xml = internal xsltproc opendoc-flat.xsl
 application/vnd.openxmlformats-officedocument.wordprocessingml.document = \
- execm rclopxml.py
+ internal xsltproc docProps/core.xml openxml-meta.xsl word/document.xml openxml-word-body.xsl
 application/vnd.openxmlformats-officedocument.wordprocessingml.template = \
- execm rclopxml.py
+ internal xsltproc docProps/core.xml openxml-meta.xsl word/document.xml openxml-word-body.xsl
 application/vnd.openxmlformats-officedocument.presentationml.template = \
  execm rclopxml.py
 application/vnd.openxmlformats-officedocument.presentationml.presentation = \
  execm rclopxml.py
 application/vnd.openxmlformats-officedocument.spreadsheetml.sheet = \
- execm rclopxml.py
+ internal xsltproc docProps/core.xml openxml-meta.xsl xl/sharedStrings.xml openxml-xls-body.xsl
 application/vnd.openxmlformats-officedocument.spreadsheetml.template =\
- execm rclopxml.py
+ internal xsltproc docProps/core.xml openxml-meta.xsl xl/sharedStrings.xml openxml-xls-body.xsl
 application/vnd.sun.xml.calc = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
 application/vnd.sun.xml.calc.template = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
 application/vnd.sun.xml.draw = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl