pythongh-121940: Update so write size is limited larger

 - Unify capping code to always respect character
   boundaries.
 - Make a soft cap rather than a hard limit
 - Make the cap for what _should_ be
   non-interactive / filesystem files 5 times that
   of interactive files (so big writes are faster)
 - Make write size for expected intractive to be
   1 MB (1024 * 1024), feels relatively responsive
   on my machines.

Author: cmaloney

Include/internal/pycore_fileutils.h

@@ -329,6 +329,11 @@ extern int _Py_GetTicksPerSecond(long *ticks_per_second);
 // Export for '_testcapi' shared extension
 PyAPI_FUNC(int) _Py_IsValidFD(int fd);
 
+#ifdef MS_WINDOWS
+size_t _Py_LimitConsoleWriteSize(const void *buf, size_t requested_size,
+                                 size_t cap_size);
+#endif
+
 #ifdef __cplusplus
 }
 #endif

Modules/_io/winconsoleio.c

@@ -48,6 +48,10 @@
    of less than one character */
 #define SMALLBUF 4
 
+/* Limit write size to consoles so that interruptss feel
+   responsive. */
+#define WRITE_LIMIT_CONSOLE (1024 * 1024)
+
 char _get_console_type(HANDLE handle) {
     DWORD mode, peek_count;
 
@@ -134,7 +138,6 @@ char _PyIO_get_console_type(PyObject *path_or_fd) {
     return m;
 }
 
-
 /*[clinic input]
 module _io
 class _io._WindowsConsoleIO "winconsoleio *" "clinic_state()->PyWindowsConsoleIO_Type"
@@ -999,11 +1002,21 @@ _io__WindowsConsoleIO_write_impl(winconsoleio *self, PyTypeObject *cls,
     if (!b->len) {
         return PyLong_FromLong(0);
     }
-    if (b->len > BUFMAX)
-        len = BUFMAX;
+    /* Ensure len fits in a DWORD. This cap is larger than the write
+       limit because it doesn't respect utf-8 characters boundaries.
+       Rely on _Py_LimitConsoleWriteSize to do a character split. */
+    if (b->len > WRITE_LIMIT_CONSOLE * 2)
+        len = WRITE_LIMIT_CONSOLE * 2;
     else
         len = (DWORD)b->len;
 
+
+    /* Limit console write size to keep interactivity.
+
+       This is a soft cap / wlen may be higher, but that is
+       okay because it isn't a hard OS limit in Windows 8+. */
+    len = (DWORD)_Py_LimitConsoleWriteSize(b->buf, len, WRITE_LIMIT_CONSOLE);
+
     Py_BEGIN_ALLOW_THREADS
     wlen = MultiByteToWideChar(CP_UTF8, 0, b->buf, len, NULL, 0);
     Py_END_ALLOW_THREADS

Python/fileutils.c

@@ -52,6 +52,17 @@ int _Py_open_cloexec_works = -1;
 // The value must be the same in unicodeobject.c.
 #define MAX_UNICODE 0x10ffff
 
+/* Limit write size on terminals in Windows to keep the interpreter
+   feeling responsive.
+
+   This is higher than WRITE_LIMIT_CONSOLE because `.write()`
+   is targeted at non-console I/O (but may happen to touch a tty). Use
+   WinConsoleIO for best console interactivity.
+
+   This should ideally be bigger than DEFAULT_BUFFER_SIZE so common
+   case write to file on disk is quick. */
+#define WRITE_LIMIT_INTERACTIVE (5 * 1024 * 1024)
+
 // mbstowcs() and mbrtowc() errors
 static const size_t DECODE_ERROR = ((size_t)-1);
 static const size_t INCOMPLETE_CHARACTER = (size_t)-2;
@@ -1922,6 +1933,24 @@ _Py_write_impl(int fd, const void *buf, size_t count, int gil_held)
     int async_err = 0;
 
     _Py_BEGIN_SUPPRESS_IPH
+#ifdef MS_WINDOWS
+    /* isatty is guarded because don't want it in common case of
+       writing DEFAULT_BUFFER_SIZE to regular files (gh-121940). */
+    if (count > WRITE_LIMIT_INTERACTIVE) {
+        if (gil_held) {
+            Py_BEGIN_ALLOW_THREADS
+            if (isatty(fd)) {
+                count = _Py_LimitConsoleWriteSize(buf, count, WRITE_LIMIT_INTERACTIVE);
+            }
+            Py_END_ALLOW_THREADS
+        } else {
+            if (isatty(fd)) {
+                count = _Py_LimitConsoleWriteSize(buf, count, WRITE_LIMIT_INTERACTIVE);
+            }
+        }
+    }
+
+#endif
     if (count > _PY_WRITE_MAX) {
         count = _PY_WRITE_MAX;
     }
@@ -3081,3 +3110,52 @@ _Py_IsValidFD(int fd)
     return (fstat(fd, &st) == 0);
 #endif
 }
+
+#ifdef MS_WINDOWS
+static size_t
+_find_last_utf8_boundary(const char *buf, size_t len)
+{
+    /* This function never returns 0, returns the original len instead */
+    DWORD count = 1;
+    if (len == 0 || (buf[len - 1] & 0x80) == 0) {
+        return len;
+    }
+    for (;; count++) {
+        if (count > 3 || count >= len) {
+            return len;
+        }
+        if ((buf[len - count] & 0xc0) != 0x80) {
+            return len - count;
+        }
+    }
+}
+
+/* Put a soft limit on the number of bytes to be written.
+
+   In older versions of Windows a hard limit was necessary because
+   there was a hard limit to the number of bytes (bpo-11395), but that
+   is not the case in Windows 8+.
+
+   For Windows 8+ the console host synchronizes I/O operations which
+   means a Ctrl-C doesn't generate an interrupt until after the write
+   is completed. That means large writes which take multiple seconds
+   will reduce responsiveness to interrupts.
+
+   This does a "soft cap" (not exact number of utf-16 bytes, but close
+   enough) to maintain responsiveness of consoles on
+   Windows (gh-121940). */
+size_t _Py_LimitConsoleWriteSize(const void *buf, size_t requested_size,
+                                 size_t cap_size) {
+    if (requested_size <= cap_size) {
+        return requested_size;
+    }
+
+    /* Fix for github issues gh-110913 and gh-82052.
+
+       Splitting utf-8 can't be done at arbitrary byte boundaries
+       because that results in broken utf-8 byte sequences being
+       presented to the user. */
+    return _find_last_utf8_boundary(buf, cap_size);
+}
+
+#endif