feature: Paragraph.text includes hyperlink text

desecho · web-flow · commit be51b95faf81 · 2016-06-13T12:32:41.000-04:00
Fixes issue #85
diff --git a/docx/oxml/__init__.py b/docx/oxml/__init__.py
@@ -7,6 +7,7 @@
 
 from __future__ import absolute_import
 
+import re
 from lxml import etree
 
 from .ns import NamespacePrefixedTag, nsmap
@@ -18,14 +19,20 @@
 oxml_parser.set_element_class_lookup(element_class_lookup)
 
 
+def remove_hyperlink_tags(xml):
+    xml = xml.replace("</w:hyperlink>","")
+    xml = re.sub('<w:hyperlink[^>]*>',"",xml)
+    return xml
+    
+    
 def parse_xml(xml):
     """
     Return root lxml element obtained by parsing XML character string in
     *xml*, which can be either a Python 2.x string or unicode. The custom
     parser is used, so custom element classes are produced for elements in
     *xml* that have them.
     """
-    root_element = etree.fromstring(xml, oxml_parser)
+    root_element = etree.fromstring(remove_hyperlink_tags(xml), oxml_parser)
     return root_element
 
 
