Add support for reading w:br

3 files changed, 27 insertions, 0 deletions

diff --git a/mammoth/documents.py b/mammoth/documents.py
index 4f67850..326fbeb 100644
--- a/mammoth/documents.py
+++ b/mammoth/documents.py
@@ -9,6 +9,7 @@ Hyperlink = dodge.data_class("Hyperlink", ["href", "children"])
 Table = dodge.data_class("Table", ["children"])
 TableRow = dodge.data_class("TableRow", ["children"])
 TableCell = dodge.data_class("TableCell", ["children"])
+LineBreak = dodge.data_class("LineBreak", [])
 
 class Tab(object):
     pass
@@ -42,6 +43,7 @@ hyperlink = Hyperlink
 table = Table
 table_row = TableRow
 table_cell = TableCell
+line_break = LineBreak
 
 def numbering_level(level_index, is_ordered):
     return _NumberingLevel(str(level_index), bool(is_ordered))
diff --git a/mammoth/docx/document_xml.py b/mammoth/docx/document_xml.py
index 32d655c..f96098e 100644
--- a/mammoth/docx/document_xml.py
+++ b/mammoth/docx/document_xml.py
@@ -159,6 +159,15 @@ def _create_reader(numbering, content_types, relationships, styles, docx_file):
             href = relationships[relationship_id].target
             return children_result.map(lambda children: documents.hyperlink(href, children))
     
+    @handler("w:br")
+    def br(element):
+        break_type = element.attributes.get("w:type")
+        if break_type:
+            warning = results.warning("Unsupported break type: {0}".format(break_type))
+            return results.Result(None, [warning])
+        else:
+            return results.success(documents.line_break())
+    
     @handler("wp:inline")
     @handler("wp:anchor")
     def inline(element):
diff --git a/tests/docx/document_xml_tests.py b/tests/docx/document_xml_tests.py
index 984609d..963a75f 100644
--- a/tests/docx/document_xml_tests.py
+++ b/tests/docx/document_xml_tests.py
@@ -219,6 +219,22 @@ class ReadXmlElementTests(object):
             [documents.run([])],
             _read_and_get_document_xml_element(element)
         )
+    
+    
+    @istest
+    def br_is_read_as_line_break(self):
+        break_element = xml_element("w:br", {}, [])
+        result = _read_and_get_document_xml_element(break_element)
+        assert_equal(result, documents.line_break())
+    
+    
+    @istest
+    def warning_on_breaks_that_arent_line_breaks(self):
+        break_element = xml_element("w:br", {"w:type": "page"}, [])
+        result = read_document_xml_element(break_element)
+        expected_warning = results.warning("Unsupported break type: page")
+        assert_equal([expected_warning], result.messages)
+        assert_equal(None, result.value)
         
         
     @istest