oxml: extract parser to docx.oxml

Steve Canny · Steve Canny · commit 8af48cf0a06d · 2014-06-15T02:13:03.000-07:00
register_custom_element_class() needs to go with to avoid a circular
import.
diff --git a/docx/oxml/__init__.py b/docx/oxml/__init__.py
@@ -5,7 +5,28 @@
 corresponding to Open XML elements.
 """
 
-from docx.oxml.shared import register_custom_element_class
+from __future__ import absolute_import
+
+from lxml import etree
+
+from .ns import nsmap
+
+
+# configure XML parser
+element_class_lookup = etree.ElementNamespaceClassLookup()
+oxml_parser = etree.XMLParser(remove_blank_text=True)
+oxml_parser.set_element_class_lookup(element_class_lookup)
+
+
+def register_custom_element_class(tag, cls):
+    """
+    Register *cls* to be constructed when the oxml parser encounters an
+    element with matching *tag*. *tag* is a string of the form
+    ``nspfx:tagroot``, e.g. ``'w:document'``.
+    """
+    nspfx, tagroot = tag.split(':')
+    namespace = element_class_lookup.get_namespace(nsmap[nspfx])
+    namespace[tagroot] = cls
 
 
 # ===========================================================================
diff --git a/docx/oxml/shared.py b/docx/oxml/shared.py
@@ -4,20 +4,17 @@
 Objects shared by modules in the docx.oxml subpackage.
 """
 
+from __future__ import absolute_import
+
 from lxml import etree
 
 import re
 
+from . import oxml_parser
 from .exceptions import ValidationError
 from .ns import nsmap
 
 
-# configure XML parser
-element_class_lookup = etree.ElementNamespaceClassLookup()
-oxml_parser = etree.XMLParser(remove_blank_text=True)
-oxml_parser.set_element_class_lookup(element_class_lookup)
-
-
 # ===========================================================================
 # utility functions
 # ===========================================================================
@@ -119,17 +116,6 @@ def qn(tag):
     return '{%s}%s' % (uri, tagroot)
 
 
-def register_custom_element_class(tag, cls):
-    """
-    Register *cls* to be constructed when the oxml parser encounters an
-    element with matching *tag*. *tag* is a string of the form
-    ``nspfx:tagroot``, e.g. ``'w:document'``.
-    """
-    nspfx, tagroot = tag.split(':')
-    namespace = element_class_lookup.get_namespace(nsmap[nspfx])
-    namespace[tagroot] = cls
-
-
 def serialize_for_reading(element):
     """
     Serialize *element* to human-readable XML suitable for tests. No XML
