Merge branch 'main' into fix-mmap-setitem-resize-reentrancy

Author: Joekrry

Doc/library/xml.dom.minidom.rst

@@ -187,13 +187,23 @@ module documentation.  This section lists the differences between the API and
 
    The *standalone* argument behaves exactly as in :meth:`writexml`.
 
+   No indentation is added inside an element
+   which is marked with ``xml:space="preserve"``,
+   which is declared in the DTD as not having element content,
+   or, in absence of such declaration, which contains text,
+   because this would change its content.
+
    .. versionchanged:: 3.8
       The :meth:`toprettyxml` method now preserves the attribute order specified
       by the user.
 
    .. versionchanged:: 3.9
       The *standalone* parameter was added.
 
+   .. versionchanged:: next
+      Whitespace is no longer added inside an element with mixed content
+      or marked with ``xml:space="preserve"``.
+
 .. _dom-example:
 
 DOM Example

Doc/library/xml.etree.elementtree.rst

@@ -631,8 +631,16 @@ Functions
    characters by default.  For indenting partial subtrees inside of an
    already indented tree, pass the initial indentation level as *level*.
 
+   No whitespace is added inside an element
+   which is marked with ``xml:space="preserve"``
+   or which contains text, because this would change its content.
+
    .. versionadded:: 3.9
 
+   .. versionchanged:: next
+      Whitespace is no longer added inside an element with mixed content
+      or marked with ``xml:space="preserve"``.
+
 
 .. function:: iselement(element)
 

Doc/whatsnew/3.16.rst

@@ -702,6 +702,14 @@ xml
   and :meth:`!Document.createEntityReference`.
   (Contributed by Jason Orendorff and Serhiy Storchaka in :gh:`44871`.)
 
+* :meth:`~xml.dom.minidom.Node.toprettyxml` in :mod:`xml.dom.minidom`
+  and :func:`~xml.etree.ElementTree.indent` in :mod:`xml.etree.ElementTree`
+  no longer add whitespace inside an element
+  which is marked with ``xml:space="preserve"`` or which contains text.
+  :meth:`!toprettyxml` also takes into account
+  the content model declared in the DTD.
+  (Contributed by Serhiy Storchaka in :gh:`81623`.)
+
 * Add :meth:`!GetSpecifiedAttributeCount` method
   to the :mod:`XML parser <xml.parsers.expat>` objects.
   It tells how many of the reported attributes were given in the start tag
@@ -947,6 +955,15 @@ that may require changes to your code.
   Attributes defaulted in the DTD are no longer omitted when parsing.
   (Contributed by Jason Orendorff and Serhiy Storchaka in :gh:`44871`.)
 
+* :meth:`~xml.dom.minidom.Node.toprettyxml` in :mod:`xml.dom.minidom`
+  and :func:`~xml.etree.ElementTree.indent` in :mod:`xml.etree.ElementTree`
+  no longer add whitespace inside an element
+  which is marked with ``xml:space="preserve"`` or which contains text,
+  because this changed the content of the element.
+  :meth:`!toprettyxml` also takes into account
+  the content model declared in the DTD.
+  (Contributed by Serhiy Storchaka in :gh:`81623`.)
+
 * On Windows, seeking a pipe now fails instead of silently appearing to
   succeed: :func:`os.lseek` and :meth:`~io.IOBase.seek` raise :exc:`OSError`,
   and :meth:`~io.IOBase.seekable` returns ``False``.  As a consequence,

Lib/test/test_capi/test_marshal.py

@@ -0,0 +1,127 @@
+import marshal
+import os.path
+import unittest
+
+from test import support
+from test.support import import_helper
+from test.support import os_helper
+from test.test_marshal import HelperMixin, omit_last_byte
+
+
+# Skip this test if _testcapi is are not available.
+_testcapi = import_helper.import_module('_testcapi')
+
+
+@support.cpython_only
+class CAPI_TestCase(unittest.TestCase, HelperMixin):
+
+    def test_read_from_file_error(self):
+        # A read error is reported as OSError, not EOFError.
+        # A directory cannot be read (on some platforms it cannot even
+        # be opened, which is reported as OSError as well).
+        os.mkdir(os_helper.TESTFN)
+        self.addCleanup(os_helper.rmdir, os_helper.TESTFN)
+        for func in (_testcapi.pymarshal_read_short_from_file,
+                     _testcapi.pymarshal_read_long_from_file,
+                     _testcapi.pymarshal_read_object_from_file,
+                     _testcapi.pymarshal_read_last_object_from_file):
+            with self.subTest(func=func.__name__):
+                self.assertRaises(OSError, func, os_helper.TESTFN)
+
+    @unittest.skipUnless(os.path.exists('/dev/full'), 'requires /dev/full')
+    def test_write_to_file_error(self):
+        # A write error is reported as OSError.
+        # The data is large enough to not fit in the stdio buffer, so that
+        # the error is detected before the file is closed.
+        obj = b'x' * 100000
+        with self.assertRaises(OSError):
+            _testcapi.pymarshal_write_object_to_file(obj, '/dev/full',
+                                                     marshal.version)
+
+    def test_write_unmarshallable_to_file(self):
+        self.addCleanup(os_helper.unlink, os_helper.TESTFN)
+        with self.assertRaisesRegex(ValueError, 'unmarshallable object'):
+            _testcapi.pymarshal_write_object_to_file(object(), os_helper.TESTFN,
+                                                     marshal.version)
+
+    def test_write_long_to_file(self):
+        for v in range(marshal.version + 1):
+            _testcapi.pymarshal_write_long_to_file(0x12345678, os_helper.TESTFN, v)
+            with open(os_helper.TESTFN, 'rb') as f:
+                data = f.read()
+            os_helper.unlink(os_helper.TESTFN)
+            self.assertEqual(data, b'\x78\x56\x34\x12')
+
+    def test_write_object_to_file(self):
+        obj = ('\u20ac', b'abc', 123, 45.6, 7+8j, 'long line '*1000)
+        for v in range(marshal.version + 1):
+            _testcapi.pymarshal_write_object_to_file(obj, os_helper.TESTFN, v)
+            with open(os_helper.TESTFN, 'rb') as f:
+                data = f.read()
+            os_helper.unlink(os_helper.TESTFN)
+            self.assertEqual(marshal.loads(data), obj)
+
+    def test_read_short_from_file(self):
+        with open(os_helper.TESTFN, 'wb') as f:
+            f.write(b'\x34\x12xxxx')
+        r, p = _testcapi.pymarshal_read_short_from_file(os_helper.TESTFN)
+        os_helper.unlink(os_helper.TESTFN)
+        self.assertEqual(r, 0x1234)
+        self.assertEqual(p, 2)
+
+        with open(os_helper.TESTFN, 'wb') as f:
+            f.write(b'\x12')
+        with self.assertRaises(EOFError):
+            _testcapi.pymarshal_read_short_from_file(os_helper.TESTFN)
+        os_helper.unlink(os_helper.TESTFN)
+
+    def test_read_long_from_file(self):
+        with open(os_helper.TESTFN, 'wb') as f:
+            f.write(b'\x78\x56\x34\x12xxxx')
+        r, p = _testcapi.pymarshal_read_long_from_file(os_helper.TESTFN)
+        os_helper.unlink(os_helper.TESTFN)
+        self.assertEqual(r, 0x12345678)
+        self.assertEqual(p, 4)
+
+        with open(os_helper.TESTFN, 'wb') as f:
+            f.write(b'\x56\x34\x12')
+        with self.assertRaises(EOFError):
+            _testcapi.pymarshal_read_long_from_file(os_helper.TESTFN)
+        os_helper.unlink(os_helper.TESTFN)
+
+    def test_read_last_object_from_file(self):
+        obj = ('\u20ac', b'abc', 123, 45.6, 7+8j)
+        for v in range(marshal.version + 1):
+            data = marshal.dumps(obj, v)
+            with open(os_helper.TESTFN, 'wb') as f:
+                f.write(data + b'xxxx')
+            r, p = _testcapi.pymarshal_read_last_object_from_file(os_helper.TESTFN)
+            os_helper.unlink(os_helper.TESTFN)
+            self.assertEqual(r, obj)
+
+            with open(os_helper.TESTFN, 'wb') as f:
+                f.write(omit_last_byte(data))
+            with self.assertRaises(EOFError):
+                _testcapi.pymarshal_read_last_object_from_file(os_helper.TESTFN)
+            os_helper.unlink(os_helper.TESTFN)
+
+    def test_read_object_from_file(self):
+        obj = ('\u20ac', b'abc', 123, 45.6, 7+8j)
+        for v in range(marshal.version + 1):
+            data = marshal.dumps(obj, v)
+            with open(os_helper.TESTFN, 'wb') as f:
+                f.write(data + b'xxxx')
+            r, p = _testcapi.pymarshal_read_object_from_file(os_helper.TESTFN)
+            os_helper.unlink(os_helper.TESTFN)
+            self.assertEqual(r, obj)
+            self.assertEqual(p, len(data))
+
+            with open(os_helper.TESTFN, 'wb') as f:
+                f.write(omit_last_byte(data))
+            with self.assertRaises(EOFError):
+                _testcapi.pymarshal_read_object_from_file(os_helper.TESTFN)
+            os_helper.unlink(os_helper.TESTFN)
+
+
+if __name__ == "__main__":
+    unittest.main()

Lib/test/test_marshal.py

@@ -797,117 +797,6 @@ def test_slice(self):
                     with self.assertRaises(ValueError):
                         marshal.dumps(obj, version)
 
-@support.cpython_only
-@unittest.skipUnless(_testcapi, 'requires _testcapi')
-class CAPI_TestCase(unittest.TestCase, HelperMixin):
-
-    def test_read_from_file_error(self):
-        # A read error is reported as OSError, not EOFError.
-        # A directory cannot be read (on some platforms it cannot even
-        # be opened, which is reported as OSError as well).
-        os.mkdir(os_helper.TESTFN)
-        self.addCleanup(os_helper.rmdir, os_helper.TESTFN)
-        for func in (_testcapi.pymarshal_read_short_from_file,
-                     _testcapi.pymarshal_read_long_from_file,
-                     _testcapi.pymarshal_read_object_from_file,
-                     _testcapi.pymarshal_read_last_object_from_file):
-            with self.subTest(func=func.__name__):
-                self.assertRaises(OSError, func, os_helper.TESTFN)
-
-    @unittest.skipUnless(os.path.exists('/dev/full'), 'requires /dev/full')
-    def test_write_to_file_error(self):
-        # A write error is reported as OSError.
-        # The data is large enough to not fit in the stdio buffer, so that
-        # the error is detected before the file is closed.
-        obj = b'x' * 100000
-        with self.assertRaises(OSError):
-            _testcapi.pymarshal_write_object_to_file(obj, '/dev/full',
-                                                     marshal.version)
-
-    def test_write_unmarshallable_to_file(self):
-        self.addCleanup(os_helper.unlink, os_helper.TESTFN)
-        with self.assertRaisesRegex(ValueError, 'unmarshallable object'):
-            _testcapi.pymarshal_write_object_to_file(object(), os_helper.TESTFN,
-                                                     marshal.version)
-
-    def test_write_long_to_file(self):
-        for v in range(marshal.version + 1):
-            _testcapi.pymarshal_write_long_to_file(0x12345678, os_helper.TESTFN, v)
-            with open(os_helper.TESTFN, 'rb') as f:
-                data = f.read()
-            os_helper.unlink(os_helper.TESTFN)
-            self.assertEqual(data, b'\x78\x56\x34\x12')
-
-    def test_write_object_to_file(self):
-        obj = ('\u20ac', b'abc', 123, 45.6, 7+8j, 'long line '*1000)
-        for v in range(marshal.version + 1):
-            _testcapi.pymarshal_write_object_to_file(obj, os_helper.TESTFN, v)
-            with open(os_helper.TESTFN, 'rb') as f:
-                data = f.read()
-            os_helper.unlink(os_helper.TESTFN)
-            self.assertEqual(marshal.loads(data), obj)
-
-    def test_read_short_from_file(self):
-        with open(os_helper.TESTFN, 'wb') as f:
-            f.write(b'\x34\x12xxxx')
-        r, p = _testcapi.pymarshal_read_short_from_file(os_helper.TESTFN)
-        os_helper.unlink(os_helper.TESTFN)
-        self.assertEqual(r, 0x1234)
-        self.assertEqual(p, 2)
-
-        with open(os_helper.TESTFN, 'wb') as f:
-            f.write(b'\x12')
-        with self.assertRaises(EOFError):
-            _testcapi.pymarshal_read_short_from_file(os_helper.TESTFN)
-        os_helper.unlink(os_helper.TESTFN)
-
-    def test_read_long_from_file(self):
-        with open(os_helper.TESTFN, 'wb') as f:
-            f.write(b'\x78\x56\x34\x12xxxx')
-        r, p = _testcapi.pymarshal_read_long_from_file(os_helper.TESTFN)
-        os_helper.unlink(os_helper.TESTFN)
-        self.assertEqual(r, 0x12345678)
-        self.assertEqual(p, 4)
-
-        with open(os_helper.TESTFN, 'wb') as f:
-            f.write(b'\x56\x34\x12')
-        with self.assertRaises(EOFError):
-            _testcapi.pymarshal_read_long_from_file(os_helper.TESTFN)
-        os_helper.unlink(os_helper.TESTFN)
-
-    def test_read_last_object_from_file(self):
-        obj = ('\u20ac', b'abc', 123, 45.6, 7+8j)
-        for v in range(marshal.version + 1):
-            data = marshal.dumps(obj, v)
-            with open(os_helper.TESTFN, 'wb') as f:
-                f.write(data + b'xxxx')
-            r, p = _testcapi.pymarshal_read_last_object_from_file(os_helper.TESTFN)
-            os_helper.unlink(os_helper.TESTFN)
-            self.assertEqual(r, obj)
-
-            with open(os_helper.TESTFN, 'wb') as f:
-                f.write(omit_last_byte(data))
-            with self.assertRaises(EOFError):
-                _testcapi.pymarshal_read_last_object_from_file(os_helper.TESTFN)
-            os_helper.unlink(os_helper.TESTFN)
-
-    def test_read_object_from_file(self):
-        obj = ('\u20ac', b'abc', 123, 45.6, 7+8j)
-        for v in range(marshal.version + 1):
-            data = marshal.dumps(obj, v)
-            with open(os_helper.TESTFN, 'wb') as f:
-                f.write(data + b'xxxx')
-            r, p = _testcapi.pymarshal_read_object_from_file(os_helper.TESTFN)
-            os_helper.unlink(os_helper.TESTFN)
-            self.assertEqual(r, obj)
-            self.assertEqual(p, len(data))
-
-            with open(os_helper.TESTFN, 'wb') as f:
-                f.write(omit_last_byte(data))
-            with self.assertRaises(EOFError):
-                _testcapi.pymarshal_read_object_from_file(os_helper.TESTFN)
-            os_helper.unlink(os_helper.TESTFN)
-
 
 if __name__ == "__main__":
     unittest.main()