Feature: Paragraph.text includes hyperlink text

desecho · desecho · commit b78354570a43 · 2017-03-17T10:23:01.000-04:00
Fixes issue #85
diff --git a/docx/oxml/__init__.py b/docx/oxml/__init__.py
@@ -7,6 +7,8 @@
 
 from __future__ import absolute_import
 
+import re
+import six
 from lxml import etree
 
 from .ns import NamespacePrefixedTag, nsmap
@@ -18,14 +20,25 @@
 oxml_parser.set_element_class_lookup(element_class_lookup)
 
 
+def remove_hyperlink_tags(xml):
+    is_bytestring = isinstance(xml, six.binary_type)
+    if is_bytestring:
+        xml = xml.decode('utf-8')
+    xml = xml.replace('</w:hyperlink>', '')
+    xml = re.sub('<w:hyperlink[^>]*>', '', xml)
+    if is_bytestring:
+        xml = xml.encode('utf-8')
+    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
 
 
diff --git a/setup.py b/setup.py
@@ -36,7 +36,7 @@ def text_of(relpath):
 PACKAGES = find_packages(exclude=['tests', 'tests.*'])
 PACKAGE_DATA = {'docx': ['templates/*']}
 
-INSTALL_REQUIRES = ['lxml>=2.3.2']
+INSTALL_REQUIRES = ['lxml>=2.3.2', 'six>=1.10.0']
 TEST_SUITE = 'tests'
 TESTS_REQUIRE = ['behave', 'mock', 'pyparsing', 'pytest']
 
