From b4306b71c08ca011cc72cce340a94aa408c029e6 Mon Sep 17 00:00:00 2001
From: Jean-Francois Dockes <jf@dockes.org>
Date: Wed, 15 Jul 2020 10:49:06 +0200
Subject: [PATCH] openxml word: be more specific for extracting text, avoids
 treating some image parameters as text

---
 src/filters/openxml-word-body.xsl | 55 ++++++++++++++++---------------
 1 file changed, 28 insertions(+), 27 deletions(-)

diff --git a/src/filters/openxml-word-body.xsl b/src/filters/openxml-word-body.xsl
index e9962a32..31ba6b1b 100644
--- a/src/filters/openxml-word-body.xsl
+++ b/src/filters/openxml-word-body.xsl
@@ -1,27 +1,28 @@
-<?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>
+<?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:for-each select="//w:p"> 
+      <p>
+      <xsl:for-each select=".//w:t"> 
+        <xsl:text> </xsl:text>
+        <xsl:value-of select="." />
+      </xsl:for-each>
+      </p>
+    </xsl:for-each>
+    </div>
+  </xsl:template>
+
+</xsl:stylesheet>