Add support for reading hyperlinks

3 files changed, 37 insertions, 2 deletions

diff --git a/mammoth/documents.py b/mammoth/documents.py
index 851755e..6ce4582 100644
--- a/mammoth/documents.py
+++ b/mammoth/documents.py
@@ -4,7 +4,7 @@ Document = collections.namedtuple("Document", ["children"])
 Paragraph = collections.namedtuple("Paragraph", ["children", "style_name", "numbering"])
 Run = collections.namedtuple("Run", ["children", "style_name", "is_bold", "is_italic"])
 Text = collections.namedtuple("Text", ["value"])
-
+Hyperlink = collections.namedtuple("Hyperlink", ["href", "children"])
 
 class Tab(object):
     pass
@@ -34,3 +34,4 @@ def tab():
 
 
 image = Image
+hyperlink = Hyperlink
diff --git a/mammoth/docx/document_xml.py b/mammoth/docx/document_xml.py
index 9c895d4..fad4f87 100644
--- a/mammoth/docx/document_xml.py
+++ b/mammoth/docx/document_xml.py
@@ -96,12 +96,24 @@ def _create_reader(numbering, content_types, relationships, docx_file):
     @handler("w:tab")
     def tab(element):
         return results.success(documents.tab())
-        
+    
+    
     @handler("w:ins")
     def ins(element):
         return _read_xml_elements(element.children)
     
     
+    @handler("w:hyperlink")
+    def hyperlink(element):
+        relationship_id = element.attributes.get("r:id")
+        children_result = _read_xml_elements(element.children)
+        if relationship_id is None:
+            return children_result
+        else:
+            href = relationships[relationship_id].target
+            return children_result.map(lambda children: documents.hyperlink(href, children))
+    
+    
     @handler("w:drawing")
     def drawing(element):
         return _read_xml_elements(element.children)
diff --git a/tests/docx/document_xml_tests.py b/tests/docx/document_xml_tests.py
index 9badbac..30580d0 100644
--- a/tests/docx/document_xml_tests.py
+++ b/tests/docx/document_xml_tests.py
@@ -130,6 +130,28 @@ class ReadXmlElementTests(object):
         )
         
     @istest
+    def hyperlink_is_read_if_it_has_a_relationship_id(self):
+        relationships = Relationships({
+            "r42": Relationship(target="http://example.com")
+        })
+        run_element = xml_element("w:r")
+        element = xml_element("w:hyperlink", {"r:id": "r42"}, [run_element])
+        assert_equal(
+            documents.hyperlink("http://example.com", [documents.run([])]),
+            _read_and_get_document_xml_element(element, relationships=relationships)
+        )
+        
+    @istest
+    def hyperlink_is_ignored_if_it_does_not_have_a_relationship_id(self):
+        run_element = xml_element("w:r")
+        element = xml_element("w:hyperlink", {}, [run_element])
+        assert_equal(
+            [documents.run([])],
+            _read_and_get_document_xml_element(element)
+        )
+        
+        
+    @istest
     @funk.with_context
     def can_read_inline_pictures(self, context):
         drawing_element = _create_inline_image(