Add support for the strict document format

NEWS

@@ -6,6 +6,8 @@
 
 * Drop support for Python 2.7, Python 3.5 and Python 3.6.
 
+* Add support for the strict document format.
+
 # 1.6.0
 
 * Support merged paragraphs when revisions are tracked.

mammoth/docx/office_xml.py

@@ -3,22 +3,32 @@
 
 
 _namespaces = [
+    # Transitional format
     ("w", "http://schemas.openxmlformats.org/wordprocessingml/2006/main"),
+    ("r", "http://schemas.openxmlformats.org/officeDocument/2006/relationships"),
     ("wp", "http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing"),
     ("a", "http://schemas.openxmlformats.org/drawingml/2006/main"),
     ("pic", "http://schemas.openxmlformats.org/drawingml/2006/picture"),
+
+    # Strict format
+    ("w", "http://purl.oclc.org/ooxml/wordprocessingml/main"),
+    ("r", "http://purl.oclc.org/ooxml/officeDocument/relationships"),
+    ("wp", "http://purl.oclc.org/ooxml/drawingml/wordprocessingDrawing"),
+    ("a", "http://purl.oclc.org/ooxml/drawingml/main"),
+    ("pic", "http://purl.oclc.org/ooxml/drawingml/picture"),
+
+    # Common
     ("content-types", "http://schemas.openxmlformats.org/package/2006/content-types"),
-    ("r", "http://schemas.openxmlformats.org/officeDocument/2006/relationships"),
     ("relationships", "http://schemas.openxmlformats.org/package/2006/relationships"),
-    ("v", "urn:schemas-microsoft-com:vml"),
     ("mc", "http://schemas.openxmlformats.org/markup-compatibility/2006"),
+    ("v", "urn:schemas-microsoft-com:vml"),
     ("office-word", "urn:schemas-microsoft-com:office:word"),
 ]
 
 
 def read(fileobj):
     return _collapse_alternate_content(parse_xml(fileobj, _namespaces))[0]
-    
+
 
 def _collapse_alternate_content(node):
     if isinstance(node, XmlElement):

tests/mammoth_tests.py

@@ -299,6 +299,13 @@ def test_can_extract_raw_text():
         assert_equal("Apple\n\nBanana\n\n", result.value)
 
 
+def test_can_read_strict_format():
+    with open(generate_test_path("strict-format.docx"), "rb") as fileobj:
+        result = mammoth.convert_to_html(fileobj=fileobj)
+        assert_equal([], result.messages)
+        assert_equal("<p>Test</p>", result.value)
+
+
 def _copy_of_test_data(path):
     destination = io.BytesIO()
     with open(generate_test_path(path), "rb") as source: