elementpath 5.1.1__tar.gz → 5.1.2__tar.gz

{elementpath-5.1.1 → elementpath-5.1.2}/CHANGELOG.rst

@@ -2,6 +2,11 @@
 CHANGELOG
 *********
 
+`v5.1.2`_ (2026-06-13)
+======================
+* Include PR #101 (invalid sequence type error code for external functions)
+* Fix issues #100 and #102
+
 `v5.1.1`_ (2026-01-20)
 ======================
 * Fix external function registrations (issue #099)
@@ -537,3 +542,4 @@ CHANGELOG
 .. _v5.0.4: https://github.com/sissaschool/elementpath/compare/v5.0.3...v5.0.4
 .. _v5.1.0: https://github.com/sissaschool/elementpath/compare/v5.0.4...v5.1.0
 .. _v5.1.1: https://github.com/sissaschool/elementpath/compare/v5.1.0...v5.1.1
+.. _v5.1.2: https://github.com/sissaschool/elementpath/compare/v5.1.1...v5.1.2

{elementpath-5.1.1/elementpath.egg-info → elementpath-5.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: elementpath
-Version: 5.1.1
+Version: 5.1.2
 Summary: XPath 1.0/2.0/3.0/3.1 parsers and selectors for ElementTree and lxml
 Author-email: Davide Brunato <brunato@sissa.it>
 License-Expression: MIT

{elementpath-5.1.1 → elementpath-5.1.2}/doc/conf.py

@@ -31,7 +31,7 @@ author = 'Davide Brunato'
 # The short X.Y version
 version = '5.1'
 # The full version, including alpha/beta/rc tags
-release = '5.1.1'
+release = '5.1.2'
 
 # -- General configuration ---------------------------------------------------
 

{elementpath-5.1.1 → elementpath-5.1.2}/elementpath/__init__.py

@@ -7,7 +7,7 @@
 #
 # @author Davide Brunato <brunato@sissa.it>
 #
-__version__ = '5.1.1'
+__version__ = '5.1.2'
 __author__ = "Davide Brunato"
 __contact__ = "brunato@sissa.it"
 __copyright__ = "Copyright 2018-2026, SISSA"

{elementpath-5.1.1 → elementpath-5.1.2}/elementpath/datatypes/any_types.py

@@ -7,6 +7,7 @@
 #
 # @author Davide Brunato <brunato@sissa.it>
 #
+import sys
 from abc import ABCMeta, abstractmethod
 from types import MappingProxyType
 from typing import Any
@@ -58,7 +59,7 @@ class AtomicTypeMeta(ABCMeta):
             extended_name = f'{{{namespace}}}{name}' if namespace else name
             prefixed_name = f'{prefix}:{name}' if prefix else name
 
-            if not cls.__doc__:
+            if not cls.__doc__ and sys.flags.optimize < 2:
                 if ver := getattr(cls, '_xsd_version', ''):
                     ver = ver + ' '
                 params = getattr(cls, '__init__', None).__doc__ or ''

{elementpath-5.1.1 → elementpath-5.1.2}/elementpath/datatypes/untyped.py

@@ -32,7 +32,7 @@ class UntypedAtomic(AnyAtomicType):
     name = 'untypedAtomic'
     value: str
 
-    __slots__ = ('value', '_xsd_version', 'parser')
+    __slots__ = ('value', 'parser')
 
     @classmethod
     def make(cls, value: Any, **kwargs: Any) -> 'UntypedAtomic':

{elementpath-5.1.1 → elementpath-5.1.2}/elementpath/helpers.py

@@ -112,6 +112,13 @@ class LazyPattern:
             self._compiled = re.compile(self._pattern, self._flags)
             return self._compiled.search(string)
 
+    def split(self, string: str) -> list[str]:
+        try:
+            return self._compiled.split(string)
+        except AttributeError:
+            self._compiled = re.compile(self._pattern, self._flags)
+            return self._compiled.split(string)
+
 
 class Patterns:
     """

{elementpath-5.1.1 → elementpath-5.1.2}/elementpath/regex/character_classes.py

@@ -14,6 +14,7 @@ from collections.abc import Callable, Iterator, MutableSet
 from itertools import chain
 from typing import AbstractSet, Any, Optional, Union
 
+from elementpath.helpers import LazyPattern
 from .codepoints import RegexError
 from .unicode_subsets import UnicodeSubset, lazy_subset, unicode_subset, unicode_category
 
@@ -87,6 +88,29 @@ CHARACTER_ESCAPES: dict[str, Union[str, Callable[[], UnicodeSubset]]] = {
     '\\W': w_shortcut,
 }
 
+re_char_set = LazyPattern(r'(\\[nrt|.\-^?*+{}()\]sSdDiIcCwW]|\\[pP]{[a-zA-Z\-0-9]+})')
+
+
+def get_charset_parts(charset: str) -> list[str]:
+    parts: list[str] = []
+    prev = ''
+    for part in re_char_set.split(charset):
+        if not part:
+            continue
+        elif part.endswith('-') and part != '\\-':
+            prev = part
+        elif part.startswith('-') and parts:
+            parts[-1] += prev + part
+            prev = ''
+        else:
+            parts.append(prev + part)
+            prev = ''
+    else:
+        if prev:
+            parts.append(prev)
+
+    return parts
+
 
 class CharacterClass(MutableSet[int]):
     """
@@ -96,7 +120,7 @@ class CharacterClass(MutableSet[int]):
     :param xsd_version: the reference XSD version for syntax variants. Defaults to '1.0'.
     TODO: implement __ior__, __iand__, __ixor__ operators for a full mutable set class.
     """
-    _re_char_set = re.compile(r'(?<!.-)(\\[nrt|.\-^?*+{}()\]sSdDiIcCwW]|\\[pP]{[a-zA-Z\-0-9]+})')
+    _re_char_set = re.compile(r'(\\[nrt|.\-^?*+{}()\]sSdDiIcCwW]|\\[pP]{[a-zA-Z\-0-9]+})')
     _re_unicode_ref = re.compile(r'\\([pP]){([\w-]+)}')
 
     __slots__ = 'xsd_version', 'positive', 'negative'
@@ -172,7 +196,7 @@ class CharacterClass(MutableSet[int]):
         if isinstance(charset, int):
             charset = chr(charset)
 
-        for part in self._re_char_set.split(charset):
+        for part in get_charset_parts(charset):
             if part in CHARACTER_ESCAPES:
                 value = CHARACTER_ESCAPES[part]
                 if isinstance(value, str):
@@ -204,7 +228,7 @@ class CharacterClass(MutableSet[int]):
         if isinstance(charset, int):
             charset = chr(charset)
 
-        for part in self._re_char_set.split(charset):
+        for part in get_charset_parts(charset):
             if part in CHARACTER_ESCAPES:
                 value = CHARACTER_ESCAPES[part]
                 if isinstance(value, str):

{elementpath-5.1.1 → elementpath-5.1.2}/elementpath/serialization.py

@@ -38,6 +38,31 @@ SER_PARAM_STANDALONE = '{%s}standalone' % XSLT_XQUERY_SERIALIZATION_NAMESPACE
 SER_PARAM_ITEM_SEPARATOR = '{%s}item-separator' % XSLT_XQUERY_SERIALIZATION_NAMESPACE
 
 
+class MapEncodingDict(dict[AnyAtomicType | None, Any]):
+    """
+    A bridge dict-type for encoding XPath maps to JSON.
+    """
+    def __init__(self, items: Any) -> None:
+        self[None] = None
+        self._items = items
+
+    def __getitem__(self, key: AnyAtomicType | None, /) -> Any:
+        for k, v in self._items:
+            if key == k:
+                return v
+        raise KeyError(key)
+
+    def __iter__(self) -> Iterator[AnyAtomicType | None]:
+        for k, _ in self._items:
+            yield k
+
+    def __len__(self) -> int:
+        return len(self._items)
+
+    def items(self) -> Any:
+        return self._items
+
+
 def get_serialization_params(params: Union[None, ElementNode, XPathMap] = None,
                              token: Optional[XPathToken] = None) -> dict['str', Any]:
 
@@ -337,14 +362,6 @@ def serialize_to_json(elements: Iterable[Any],
     if etree_module is None:
         etree_module = ElementTree
 
-    class MapEncodingDict(dict):  # type: ignore[type-arg]
-        def __init__(self, items: Any) -> None:
-            self[None] = None
-            self._items = items
-
-        def items(self) -> Any:
-            return self._items
-
     class XPathEncoder(json.JSONEncoder):
 
         def default(self, obj: Any) -> Any:

{elementpath-5.1.1 → elementpath-5.1.2}/elementpath/xpath_tokens/base.py

@@ -154,6 +154,10 @@ class XPathToken(Token[ta.XPathTokenType]):
             return True
         return not self._items[1].label.endswith('function')
 
+    def is_reference(self) -> bool:
+        """Is `True` if the token is a function reference, `False` otherwise."""
+        return False
+
     ###
     # Tokens tree analysis methods
     def iter_leaf_elements(self) -> Iterator[str]:
@@ -321,7 +325,7 @@ class XPathToken(Token[ta.XPathTokenType]):
             else:
                 return default
         else:
-            if isinstance(token, XPathToken) and callable(token) and token.is_reference():
+            if token.is_reference():
                 return token  # It's a function reference
 
             item = None

{elementpath-5.1.1 → elementpath-5.1.2}/elementpath/xpath_tokens/functions.py

@@ -227,10 +227,8 @@ class XPathFunction(XPathToken):
         else:
             return None
 
-    def is_reference(self) -> int:
-        if not isinstance(self.nargs, int):
-            return False
-        return self.nargs and not len(self._items)
+    def is_reference(self) -> bool:
+        return isinstance(self.nargs, int) and self.nargs != 0 and not self._items
 
     def nud(self) -> 'XPathFunction':
         if not self.parser.parse_arguments:
@@ -413,12 +411,12 @@ class ExternalFunction(XPathFunction):
             for k, (arg, st) in enumerate(zip(args, self.sequence_types), start=1):
                 if not match_sequence_type(arg, st, self.parser):
                     msg = f"{ordinal(k)} argument does not match sequence type {st!r}"
-                    raise self.error('XPDY0050', msg)
+                    raise self.error('XPTY0004', msg)
 
             result = self.callback(*args)
             if not match_sequence_type(result, self.sequence_types[-1], self.parser):
                 msg = f"Result does not match sequence type {self.sequence_types[-1]!r}"
-                raise self.error('XPDY0050', msg)
+                raise self.error('XPTY0004', msg)
             return result
 
         return self.callback(*args)

{elementpath-5.1.1 → elementpath-5.1.2/elementpath.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: elementpath
-Version: 5.1.1
+Version: 5.1.2
 Summary: XPath 1.0/2.0/3.0/3.1 parsers and selectors for ElementTree and lxml
 Author-email: Davide Brunato <brunato@sissa.it>
 License-Expression: MIT

{elementpath-5.1.1 → elementpath-5.1.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "elementpath"
-version = "5.1.1"
+version = "5.1.2"
 description = "XPath 1.0/2.0/3.0/3.1 parsers and selectors for ElementTree and lxml"
 readme = "README.rst"
 license = "MIT"

{elementpath-5.1.1 → elementpath-5.1.2}/tests/test_regex.py

@@ -799,6 +799,10 @@ class TestPatterns(unittest.TestCase):
         self.assertIsNone(pattern.search('first\tsecond\tthird'))
         self.assertEqual(pattern.search('first second third').group(0), 'first second third')
 
+    def test_issue_100(self):
+        self.assertNotIn('\\s', translate_pattern(r"[\s\-',]{1,255}"))
+        self.assertNotIn('\\s', translate_pattern(r"[\-\s',]{1,255}"))
+
     def test_dot_wildcard(self):
         regex = translate_pattern('.+', anchors=False)
         self.assertEqual(regex, '^([^\\r\\n]+)$(?!\\n\\Z)')

{elementpath-5.1.1 → elementpath-5.1.2}/tests/test_xpath2_parser.py

@@ -1287,7 +1287,7 @@ class XPath2ParserTest(test_xpath1_parser.XPath1ParserTest):
         self.check_selector('//@*/local-name()', root, result)
         self.check_selector('//@*/name()', root, result)
 
-    def test_external_function_registration(self):
+    def test_external_function_registration__issue_099(self):
         parser = self.parser.__class__(namespaces={'tns0': 'https://elementpath.test/tns0'})
 
         def foo(x):
@@ -1354,6 +1354,20 @@ class XPath2ParserTest(test_xpath1_parser.XPath1ParserTest):
 
         assert issubclass(token_class, ProxyToken)
         self.assertEqual(token_class.lookup_name, 'foo')
+        self.assertFalse(hasattr(token_class, 'nargs'))
+        self.assertIsNone(token_class.namespace)
+
+        token_class = parser.symbol_table['{https://elementpath.test/tns0}foo']
+        self.assertTrue(issubclass(token_class, XPathFunction))
+
+        assert issubclass(token_class, XPathFunction)
+        self.assertEqual(token_class.lookup_name, '{https://elementpath.test/tns0}foo')
+        self.assertEqual(token_class.nargs, 2)
+        self.assertEqual(token_class.namespace, 'https://elementpath.test/tns0')
+
+        with self.assertRaises(ValueError) as ctx:
+            parser.external_function(foo2, 'foo', prefix='tns0')
+        self.assertEqual(str(ctx.exception), "function 'tns0:foo' is already registered")
 
         token = parser.parse('foo(8)')
         self.assertEqual(token.evaluate(), '8')

{elementpath-5.1.1 → elementpath-5.1.2}/tox.ini

@@ -4,10 +4,10 @@
 # and then run "tox" from this directory.
 
 [tox]
-min_version = 4.0
+min_version = 4.50
 envlist =
-    py{310,311,312,313,314,314,315,315-lxml,py3}, docs, flake8,
-    mypy-py{310,311,312,313,314,315,py3}, pytest, coverage,
+    flake8, py{310,311,312,313,314,314,314t,314-opt,315,315-lxml,py310,py311},
+    docs, mypy-py{310,311,312,313,314,315}, pytest, coverage,
     xmlschema{401,410}, w3c-xsdtests, w3c-qt3tests
 skip_missing_interpreters = true
 work_dir = {tox_root}/../.tox/elementpath
@@ -22,6 +22,18 @@ set_env =
     py313: TEST_UNICODE_INSTALLATION = 6.2.0
 commands = python -m unittest
 
+[testenv:py314-opt]
+deps =
+    lxml
+    xmlschema~=4.2.0
+commands = python -OO -m unittest
+
+[testenv:py314t]
+deps =
+    lxml
+    xmlschema~=4.2.0
+commands = python -Xgil=0 -m unittest
+
 [testenv:py315]
 deps =
     xmlschema~=4.2.0
@@ -54,10 +66,9 @@ commands =
     flake8 elementpath
     flake8 tests
 
-[testenv:mypy-py{310,311,312,313,314,315,py3}]
+[testenv:mypy-py{310,311,312,313,314,315}]
 deps =
-    mypy==1.19.1; platform_python_implementation != 'PyPy'
-    mypy==1.18.2; platform_python_implementation == 'PyPy'
+    mypy==2.1.0
     xmlschema~=4.2.0
     lxml-stubs
 commands =
@@ -89,7 +100,7 @@ set_env =
     xmlschema420: VERSION = 4.2.0
 change_dir = {env_tmp_dir}
 deps =
-    mypy==1.19.1
+    mypy==2.1.0
     lxml
     lxml-stubs
     jinja2