Add process_skipped optional argument to decoding/encoding

  - Process contents matched by 'skip' wildcard as 'lax'
  - Fix test_exception_repr() including xsd prefix

CHANGELOG.rst

@@ -6,6 +6,7 @@ CHANGELOG
 ======================
 * Improve error reporting for encoded data (issue #275)
 * Fix attribute duplicates in attribute group (issue #276)
+* Add process_skipped optional argument to decoding/encoding
 
 `v1.9.0`_ (2021-11-30)
 ======================

tests/validation/test_decoding.py

@@ -778,9 +778,35 @@ def test_any_type_decoding(self):
         self.assertIsNone(any_type.decode(xml_data_1))
         xml_data_2 = ElementTree.fromstring('<root>\n    <child_1/>\n    <child_2/>\n</root>')
 
-        # Fix for processContent='lax' (issue 273, previously result was None)
+        # Fix for processContents='lax' (issue 273, previously result was None)
         self.assertEqual(any_type.decode(xml_data_2), {'child_1': [None], 'child_2': [None]})
 
+    def test_skip_wildcard_decoding(self):
+        schema = self.schema_class("""<?xml version="1.0" encoding="UTF-8"?>
+            <xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema">
+                <xs:element name="foo">
+                    <xs:complexType>
+                        <xs:sequence>
+                            <xs:any processContents="skip"/>
+                        </xs:sequence>
+                    </xs:complexType>
+                </xs:element>
+            </xs:schema>""")
+
+        self.assertIsNone(schema.decode('<foo><bar/></foo>'))
+
+        obj = schema.decode('<foo><bar/></foo>', process_skipped=True)
+        self.assertEqual(obj, {'bar': None})
+
+        root = schema.encode(obj)
+        self.assertEqual(root.tag, 'foo')
+        self.assertEqual(len(root), 0)
+
+        root = schema.encode(obj, process_skipped=True)
+        self.assertEqual(root.tag, 'foo')
+        self.assertEqual(len(root), 1)
+        self.assertEqual(root[0].tag, 'bar')
+
     def test_any_type_decoding__issue_273(self):
         schema = self.schema_class(self.casepath('issues/issue_273/issue_273.xsd'))
         data = schema.to_dict(self.casepath('issues/issue_273/issue_273.xml'))

tests/validators/test_exceptions.py

@@ -65,7 +65,7 @@ def test_exception_repr(self):
         self.assertEqual(lines[0], 'unknown error:', msg=output)
         self.assertEqual(lines[2], 'Schema:', msg=output)
         self.assertRegex(lines[4].strip(), '^<(xs:)?schema ', msg=output)
-        self.assertRegex(lines[-2].strip(), '</(xs:)?schema>$', msg=output)
+        self.assertRegex(lines[-2].strip(), '</(xs:|xsd:)?schema>$', msg=output)
 
     @unittest.skipIf(lxml_etree is None, 'lxml is not installed ...')
     def test_exception_repr_lxml(self):

xmlschema/validators/schemas.py

@@ -1856,6 +1856,7 @@ def iter_decode(self, source: Union[XMLSourceType, XMLResource],
                     filler: Optional[Callable[[Union[XsdElement, XsdAttribute]], Any]] = None,
                     fill_missing: bool = False,
                     keep_unknown: bool = False,
+                    process_skipped: bool = False,
                     max_depth: Optional[int] = None,
                     depth_filler: Optional[Callable[[XsdElement], Any]] = None,
                     value_hook: Optional[Callable[[AtomicValueType, BaseXsdType], Any]] = None,
@@ -1895,6 +1896,8 @@ def iter_decode(self, source: Union[XMLSourceType, XMLResource],
         The filling value is `None` or a typed value if the *filler* callback is provided.
         :param keep_unknown: if set to `True` unknown tags are kept and are decoded with \
         *xs:anyType*. For default unknown tags not decoded by a wildcard are discarded.
+        :param process_skipped: process XML data that match a wildcard with \
+        `processContents='skip'`.
         :param max_depth: maximum level of decoding, for default there is no limit. \
         With lazy resources is set to `source.lazy_depth` for managing lazy decoding.
         :param depth_filler: an optional callback function to replace data over the \
@@ -1946,6 +1949,8 @@ def iter_decode(self, source: Union[XMLSourceType, XMLResource],
             kwargs['fill_missing'] = fill_missing
         if keep_unknown:
             kwargs['keep_unknown'] = keep_unknown
+        if process_skipped:
+            kwargs['process_skipped'] = process_skipped
         if max_depth is not None:
             kwargs['max_depth'] = max_depth
         if depth_filler is not None:
@@ -2046,7 +2051,8 @@ def iter_encode(self, obj: Any, path: Optional[str] = None, validation: str = 'l
         :param unordered: a flag for explicitly activating unordered encoding mode for \
         content model data. This mode uses content models for a reordered-by-model \
         iteration of the child elements.
-        :param kwargs: keyword arguments containing options for converter.
+        :param kwargs: keyword arguments with other options for encoding and for \
+        building the converter instance.
         :return: yields an Element instance/s or validation/encoding errors.
         """
         self.check_validator(validation)

xmlschema/validators/wildcards.py

@@ -467,7 +467,8 @@ def iter_decode(self, obj: ElementType, validation: str = 'lax', **kwargs: Any)
             yield self.validation_error(validation, reason, obj, **kwargs)
 
         if self.process_contents == 'skip':
-            return
+            if 'process_skipped' not in kwargs or not kwargs['process_skipped']:
+                return
 
         namespace = get_namespace(obj.tag)
         if not self.maps.load_namespace(namespace):
@@ -482,14 +483,15 @@ def iter_decode(self, obj: ElementType, validation: str = 'lax', **kwargs: Any)
                 return
 
         if XSI_TYPE in obj.attrib:
-            if self.process_contents == 'lax':
+            if self.process_contents == 'strict':
                 xsd_element = self.maps.validator.create_element(
-                    obj.tag, parent=self, nillable='true', form='unqualified'
+                    obj.tag, parent=self, form='unqualified'
                 )
             else:
                 xsd_element = self.maps.validator.create_element(
-                    obj.tag, parent=self, form='unqualified'
+                    obj.tag, parent=self, nillable='true', form='unqualified'
                 )
+
             yield from xsd_element.iter_decode(obj, validation, **kwargs)
             return
 
@@ -507,7 +509,8 @@ def iter_encode(self, obj: Tuple[str, ElementType], validation: str = 'lax', **k
             yield self.validation_error(validation, reason, value, **kwargs)
 
         if self.process_contents == 'skip':
-            return
+            if 'process_skipped' not in kwargs or not kwargs['process_skipped']:
+                return
 
         if not self.maps.load_namespace(namespace):
             reason = f"unavailable namespace {namespace!r}"
@@ -522,13 +525,13 @@ def iter_encode(self, obj: Tuple[str, ElementType], validation: str = 'lax', **k
 
         # Check if there is an xsi:type attribute, but it has to extract
         # attributes using the converter instance.
-        if self.process_contents == 'lax':
+        if self.process_contents == 'strict':
             xsd_element = self.maps.validator.create_element(
-                name, parent=self, nillable='true', form='unqualified'
+                name, parent=self, form='unqualified'
             )
         else:
             xsd_element = self.maps.validator.create_element(
-                name, parent=self, form='unqualified'
+                name, parent=self, nillable='true', form='unqualified'
             )
 
         try:
@@ -642,8 +645,10 @@ def iter_decode(self, obj: Tuple[str, str], validation: str = 'lax', **kwargs: A
             yield self.validation_error(validation, reason, obj, **kwargs)
 
         if self.process_contents == 'skip':
-            return
-        elif self.maps.load_namespace(get_namespace(name)):
+            if 'process_skipped' not in kwargs or not kwargs['process_skipped']:
+                return
+
+        if self.maps.load_namespace(get_namespace(name)):
             try:
                 xsd_attribute = self.maps.lookup_attribute(name)
             except LookupError:
@@ -670,8 +675,10 @@ def iter_encode(self, obj: Tuple[str, AtomicValueType], validation: str = 'lax',
             yield self.validation_error(validation, reason, obj, **kwargs)
 
         if self.process_contents == 'skip':
-            return
-        elif self.maps.load_namespace(namespace):
+            if 'process_skipped' not in kwargs or not kwargs['process_skipped']:
+                return
+
+        if self.maps.load_namespace(namespace):
             try:
                 xsd_attribute = self.maps.lookup_attribute(name)
             except LookupError: