IGNIETFERRO-1816 Update Python 3 from 3.9.12 to 3.10.4

ref:9f96be6d02ee8044fdd6f124b799b270c20ce641

1 files changed, 18 insertions, 21 deletions

diff --git a/contrib/tools/python3/src/Objects/stringlib/codecs.h b/contrib/tools/python3/src/Objects/stringlib/codecs.h
index 9b2a29ba3b8..b17cda18f54 100644
--- a/contrib/tools/python3/src/Objects/stringlib/codecs.h
+++ b/contrib/tools/python3/src/Objects/stringlib/codecs.h
@@ -4,16 +4,16 @@
 # error "codecs.h is specific to Unicode"
 #endif
 
-#include "pycore_byteswap.h"      // _Py_bswap32()
+#include "pycore_bitutils.h"      // _Py_bswap32()
 
-/* Mask to quickly check whether a C 'long' contains a
+/* Mask to quickly check whether a C 'size_t' contains a
    non-ASCII, UTF8-encoded char. */
-#if (SIZEOF_LONG == 8)
-# define ASCII_CHAR_MASK 0x8080808080808080UL
-#elif (SIZEOF_LONG == 4)
-# define ASCII_CHAR_MASK 0x80808080UL
+#if (SIZEOF_SIZE_T == 8)
+# define ASCII_CHAR_MASK 0x8080808080808080ULL
+#elif (SIZEOF_SIZE_T == 4)
+# define ASCII_CHAR_MASK 0x80808080U
 #else
-# error C 'long' size should be either 4 or 8!
+# error C 'size_t' size should be either 4 or 8!
 #endif
 
 /* 10xxxxxx */
@@ -26,7 +26,6 @@ STRINGLIB(utf8_decode)(const char **inptr, const char *end,
 {
     Py_UCS4 ch;
     const char *s = *inptr;
-    const char *aligned_end = (const char *) _Py_ALIGN_DOWN(end, SIZEOF_LONG);
     STRINGLIB_CHAR *p = dest + *outpos;
 
     while (s < end) {
@@ -36,19 +35,19 @@ STRINGLIB(utf8_decode)(const char **inptr, const char *end,
             /* Fast path for runs of ASCII characters. Given that common UTF-8
                input will consist of an overwhelming majority of ASCII
                characters, we try to optimize for this case by checking
-               as many characters as a C 'long' can contain.
+               as many characters as a C 'size_t' can contain.
                First, check if we can do an aligned read, as most CPUs have
                a penalty for unaligned reads.
             */
-            if (_Py_IS_ALIGNED(s, SIZEOF_LONG)) {
+            if (_Py_IS_ALIGNED(s, ALIGNOF_SIZE_T)) {
                 /* Help register allocation */
                 const char *_s = s;
                 STRINGLIB_CHAR *_p = p;
-                while (_s < aligned_end) {
-                    /* Read a whole long at a time (either 4 or 8 bytes),
+                while (_s + SIZEOF_SIZE_T <= end) {
+                    /* Read a whole size_t at a time (either 4 or 8 bytes),
                        and do a fast unrolled copy if it only contains ASCII
                        characters. */
-                    unsigned long value = *(const unsigned long *) _s;
+                    size_t value = *(const size_t *) _s;
                     if (value & ASCII_CHAR_MASK)
                         break;
 #if PY_LITTLE_ENDIAN
@@ -56,14 +55,14 @@ STRINGLIB(utf8_decode)(const char **inptr, const char *end,
                     _p[1] = (STRINGLIB_CHAR)((value >> 8) & 0xFFu);
                     _p[2] = (STRINGLIB_CHAR)((value >> 16) & 0xFFu);
                     _p[3] = (STRINGLIB_CHAR)((value >> 24) & 0xFFu);
-# if SIZEOF_LONG == 8
+# if SIZEOF_SIZE_T == 8
                     _p[4] = (STRINGLIB_CHAR)((value >> 32) & 0xFFu);
                     _p[5] = (STRINGLIB_CHAR)((value >> 40) & 0xFFu);
                     _p[6] = (STRINGLIB_CHAR)((value >> 48) & 0xFFu);
                     _p[7] = (STRINGLIB_CHAR)((value >> 56) & 0xFFu);
 # endif
 #else
-# if SIZEOF_LONG == 8
+# if SIZEOF_SIZE_T == 8
                     _p[0] = (STRINGLIB_CHAR)((value >> 56) & 0xFFu);
                     _p[1] = (STRINGLIB_CHAR)((value >> 48) & 0xFFu);
                     _p[2] = (STRINGLIB_CHAR)((value >> 40) & 0xFFu);
@@ -79,8 +78,8 @@ STRINGLIB(utf8_decode)(const char **inptr, const char *end,
                     _p[3] = (STRINGLIB_CHAR)(value & 0xFFu);
 # endif
 #endif
-                    _s += SIZEOF_LONG;
-                    _p += SIZEOF_LONG;
+                    _s += SIZEOF_SIZE_T;
+                    _p += SIZEOF_SIZE_T;
                 }
                 s = _s;
                 p = _p;
@@ -496,8 +495,6 @@ STRINGLIB(utf16_decode)(const unsigned char **inptr, const unsigned char *e,
                         int native_ordering)
 {
     Py_UCS4 ch;
-    const unsigned char *aligned_end =
-            (const unsigned char *) _Py_ALIGN_DOWN(e, SIZEOF_LONG);
     const unsigned char *q = *inptr;
     STRINGLIB_CHAR *p = dest + *outpos;
     /* Offsets from q for retrieving byte pairs in the right order. */
@@ -512,10 +509,10 @@ STRINGLIB(utf16_decode)(const unsigned char **inptr, const unsigned char *e,
         Py_UCS4 ch2;
         /* First check for possible aligned read of a C 'long'. Unaligned
            reads are more expensive, better to defer to another iteration. */
-        if (_Py_IS_ALIGNED(q, SIZEOF_LONG)) {
+        if (_Py_IS_ALIGNED(q, ALIGNOF_LONG)) {
             /* Fast path for runs of in-range non-surrogate chars. */
             const unsigned char *_q = q;
-            while (_q < aligned_end) {
+            while (_q + SIZEOF_LONG <= e) {
                 unsigned long block = * (const unsigned long *) _q;
                 if (native_ordering) {
                     /* Can use buffer directly */