Merge branch 'development' of https://gitlab.lrz.de/badw-it/DHParser into development

# Conflicts:
#	DHParser/ebnf.py

DHParser/syntaxtree.py

@@ -1379,8 +1379,7 @@ class Node:  # (collections.abc.Sized): Base class omitted for cython-compatibil
             items = tuple(child for child in self._children if mf(child))
             if items:
                 return items if len(items) >= 2 else items[0]
-            raise IndexError('index out of range') if isinstance(key, int) \
-                else KeyError(str(key))
+            raise IndexError('index out of range') if isinstance(key, int) else KeyError(str(key))
 
     def __delitem__(self, key: Union[int, slice, CriteriaType]):
         """

DHParser/toolkit.py

@@ -75,8 +75,10 @@ __all__ = ('typing',
            'ThreadLocalSingletonFactory',
            'RX_NEVER_MATCH',
            'RX_ENTITY',
+           'RX_NON_ASCII',
            'validate_XML_attribute_value',
            'fix_XML_attribute_value',
+           'fix_lxml_attribute_value',
            'RxPatternType',
            're_find',
            'escape_re',
@@ -574,7 +576,7 @@ def validate_XML_attribute_value(value: Any) -> str:
 
 
 def fix_XML_attribute_value(value: Any) -> str:
-    """Returns the quotes XML-attribute value. In case the values
+    """Returns the quoted XML-attribute value. In case the values
     contains illegal characters, like '<', these will be replaced by
     XML-entities."""
     value = str(value)
@@ -593,6 +595,22 @@ def fix_XML_attribute_value(value: Any) -> str:
     return value
 
 
+RX_NON_ASCII = re.compile(r'[^\U00000000-\U00000100]')
+
+
+def lxml_XML_attribute_value(value: Any) -> str:
+    """Makes sure that the attribute value works with the lxml-library,
+    at the cost of replacing all characters with a code > 256 by
+    a quesiton mark.
+
+    :param value: the original attribute value
+    :return: the quoted and lxml-compatible attribute value.
+    """
+    value = str(value)
+    value = RX_NON_ASCII.sub('?', value)
+    return fix_XML_attribute_value(value)
+
+
 #######################################################################
 #
 # type system support

examples/EBNF/grammar_examples/BNF.ebnf

+@literalws = right
+definitions = ~ definition { definition } EOF
+definition  = definiendum ":=" definiens
+definiendum = word
+definiens   = word { word }
+word        = /[A-Z]?[a-z]*/
+EOF         = /$/

pyproject.toml

@@ -53,7 +53,7 @@ packages = [
 
 [tool.poetry.dependencies]
 python = "^3.5"
-regex = { version = "^2.5", optional = true }
+regex = { version = "*", optional = true }
 cython = { version = "^0.29", optional = true }