[pull] main from python:main

Doc/library/pathlib.rst

@@ -1266,6 +1266,8 @@ Reading and writing files
       >>> p.read_text()
       'Text file contents'
 
+   Return the number of characters written.
+
    An existing file of the same name is overwritten. The optional parameters
    have the same meaning as in :func:`open`.
 
@@ -1286,6 +1288,8 @@ Reading and writing files
       >>> p.read_bytes()
       b'Binary file contents'
 
+   Return the number of bytes written.
+
    An existing file of the same name is overwritten.
 
    .. versionadded:: 3.5

Include/internal/pycore_pyhash.h

@@ -27,14 +27,14 @@ _Py_HashPointerRaw(const void *ptr)
  *   pppppppp ssssssss ........  fnv -- two Py_hash_t
  *   k0k0k0k0 k1k1k1k1 ........  siphash -- two uint64_t
  *   ........ ........ ssssssss  djbx33a -- 16 bytes padding + one Py_hash_t
- *   ........ ........ eeeeeeee  pyexpat XML hash salt
+ *   eeeeeeee eeeeeeee eeeeeeee  pyexpat XML hash salt
  *
  * memory layout on 32 bit systems
  *   cccccccc cccccccc cccccccc  uc
  *   ppppssss ........ ........  fnv -- two Py_hash_t
  *   k0k0k0k0 k1k1k1k1 ........  siphash -- two uint64_t (*)
  *   ........ ........ ssss....  djbx33a -- 16 bytes padding + one Py_hash_t
- *   ........ ........ eeee....  pyexpat XML hash salt
+ *   eeeeeeee eeeeeeee eeee....  pyexpat XML hash salt
  *
  * (*) The siphash member may not be available on 32 bit platforms without
  *     an unsigned int64 data type.
@@ -58,7 +58,9 @@ typedef union {
         Py_hash_t suffix;
     } djbx33a;
     struct {
-        unsigned char padding[16];
+        /* 16 bytes for XML_SetHashSalt16Bytes */
+        uint8_t hashsalt16[16];
+        /* 4/8 bytes for legacy XML_SetHashSalt */
         Py_hash_t hashsalt;
     } expat;
 } _Py_HashSecret_t;

Include/pyexpat.h

@@ -62,6 +62,9 @@ struct PyExpat_CAPI
         XML_Parser parser, unsigned long long activationThresholdBytes);
     XML_Bool (*SetBillionLaughsAttackProtectionMaximumAmplification)(
         XML_Parser parser, float maxAmplificationFactor);
+    /* might be NULL for expat < 2.8.0 */
+    XML_Bool (*SetHashSalt16Bytes)(
+        XML_Parser parser, const uint8_t entropy[16]);
     /* always add new stuff to the end! */
 };
 

Lib/pathlib/__init__.py

@@ -989,6 +989,7 @@ def read_text(self, encoding=None, errors=None, newline=None):
     def write_bytes(self, data):
         """
         Open the file in bytes mode, write to it, and close the file.
+        Return the number of bytes written.
         """
         # type-check for the buffer interface before truncating the file
         view = memoryview(data)
@@ -998,6 +999,7 @@ def write_bytes(self, data):
     def write_text(self, data, encoding=None, errors=None, newline=None):
         """
         Open the file in text mode, write to it, and close the file.
+        Return the number of characters written.
         """
         # Call io.text_encoding() here to ensure any warning is raised at an
         # appropriate stack level.

Lib/pathlib/types.py

@@ -431,6 +431,7 @@ def __open_writer__(self, mode):
     def write_bytes(self, data):
         """
         Open the file in bytes mode, write to it, and close the file.
+        Return the number of bytes written.
         """
         # type-check for the buffer interface before truncating the file
         view = memoryview(data)
@@ -440,6 +441,7 @@ def write_bytes(self, data):
     def write_text(self, data, encoding=None, errors=None, newline=None):
         """
         Open the file in text mode, write to it, and close the file.
+        Return the number of characters written.
         """
         # Call io.text_encoding() here to ensure any warning is raised at an
         # appropriate stack level.

Lib/test/test_pyexpat.py

@@ -712,6 +712,20 @@ def test_change_size_2(self):
         parser.Parse(xml2, True)
         self.assertEqual(self.n, 4)
 
+    @support.requires_resource('cpu')
+    @support.requires_resource('walltime')
+    @support.bigmemtest(size=2**31, memuse=4, dry_run=False)
+    def test_large_character_data_does_not_crash(self):
+        # See https://github.com/python/cpython/issues/148441
+        parser = expat.ParserCreate()
+        parser.buffer_text = True
+        parser.buffer_size = 2**31 - 1  # INT_MAX
+        N = 2049 * (1 << 20) - 3  # Character data greater than INT_MAX
+        self.assertGreater(N, parser.buffer_size)
+        parser.CharacterDataHandler = lambda text: None
+        xml_data = b"<r>" + b"A" * N + b"</r>"
+        self.assertEqual(parser.Parse(xml_data, True), 1)
+
 class ElementDeclHandlerTest(unittest.TestCase):
     def test_trigger_leak(self):
         # Unfixed, this test would leak the memory of the so-called

Misc/NEWS.d/next/Library/2026-04-23-12-50-15.gh-issue-148441.zvpCkR.rst

@@ -0,0 +1,4 @@
+:mod:`xml.parsers.expat`: prevent a crash in
+:meth:`~xml.parsers.expat.xmlparser.CharacterDataHandler`
+when the character data size exceeds the parser's
+:attr:`buffer size <xml.parsers.expat.xmlparser.buffer_size>`.

Misc/NEWS.d/next/Security/2026-04-26-19-30-45.gh-issue-149018.a9SqWb.rst

@@ -0,0 +1,3 @@
+Improved protection against XML hash-flooding attacks in
+:mod:`xml.parsers.expat` and :mod:`xml.etree.ElementTree` when Python is
+compiled with libExpat 2.8.0 or later.

Modules/_elementtree.c

@@ -3735,8 +3735,12 @@ _elementtree_XMLParser___init___impl(XMLParserObject *self, PyObject *target,
         PyErr_NoMemory();
         return -1;
     }
-    /* expat < 2.1.0 has no XML_SetHashSalt() */
-    if (EXPAT(st, SetHashSalt) != NULL) {
+    // Prefer 16-byte entropy, only expat >= 2.8.0. See gh-149018
+    if (EXPAT(st, SetHashSalt16Bytes) != NULL) {
+        EXPAT(st, SetHashSalt16Bytes)(self->parser,
+                                      _Py_HashSecret.expat.hashsalt16);
+    }
+    else if (EXPAT(st, SetHashSalt) != NULL) {
         EXPAT(st, SetHashSalt)(self->parser,
                            (unsigned long)_Py_HashSecret.expat.hashsalt);
     }

Modules/pyexpat.c

@@ -393,7 +393,7 @@ my_CharacterDataHandler(void *userData, const XML_Char *data, int len)
     if (self->buffer == NULL)
         call_character_handler(self, data, len);
     else {
-        if ((self->buffer_used + len) > self->buffer_size) {
+        if (len > (self->buffer_size - self->buffer_used)) {
             if (flush_character_buffer(self) < 0)
                 return;
             /* handler might have changed; drop the rest on the floor
@@ -1533,7 +1533,10 @@ newxmlparseobject(pyexpat_state *state, const char *encoding,
         Py_DECREF(self);
         return NULL;
     }
-#if XML_COMBINED_VERSION >= 20100
+#if XML_COMBINED_VERSION >= 20800
+    /* This feature was added upstream in libexpat 2.8.0. */
+    XML_SetHashSalt16Bytes(self->itself, _Py_HashSecret.expat.hashsalt16);
+#elif XML_COMBINED_VERSION >= 20100
     /* This feature was added upstream in libexpat 2.1.0. */
     XML_SetHashSalt(self->itself,
                     (unsigned long)_Py_HashSecret.expat.hashsalt);
@@ -2427,6 +2430,11 @@ pyexpat_exec(PyObject *mod)
 #else
     capi->SetHashSalt = NULL;
 #endif
+#if XML_COMBINED_VERSION >= 20800
+    capi->SetHashSalt16Bytes = XML_SetHashSalt16Bytes;
+#else
+    capi->SetHashSalt16Bytes = NULL;
+#endif
 #if XML_COMBINED_VERSION >= 20600
     capi->SetReparseDeferralEnabled = XML_SetReparseDeferralEnabled;
 #else