master 3b7d55a801 2/2: Speed up count_size_as_multibyte

[Mattias Engdegård]

branch: master
commit 3b7d55a8013914b6707211d148a6e878ca118ad9
Author: Mattias Engdegård <mattiase@acm.org>
Commit: Mattias Engdegård <mattiase@acm.org>

    Speed up count_size_as_multibyte
    
    This function is used in many places to calculate the length of
    a unibyte string converted to multibyte.
    
    * src/character.c (count_size_as_multibyte): Move the overflow test
    outside the loop, which makes it much faster.  Standard compilers
    will even vectorise it if asked to (-O2 in Clang, -O3 in GCC).
---
 src/character.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/src/character.c b/src/character.c
index eba417d005..c1a1b55389 100644
--- a/src/character.c
+++ b/src/character.c
@@ -654,15 +654,14 @@ str_as_multibyte (unsigned char *str, ptrdiff_t len, 
ptrdiff_t nbytes,
 ptrdiff_t
 count_size_as_multibyte (const unsigned char *str, ptrdiff_t len)
 {
-  const unsigned char *endp = str + len;
+  /* Count the number of non-ASCII (raw) bytes, since they will occupy
+     two bytes in a multibyte string.  */
+  ptrdiff_t nonascii = 0;
+  for (ptrdiff_t i = 0; i < len; i++)
+    nonascii += str[i] >> 7;
   ptrdiff_t bytes;
-
-  for (bytes = 0; str < endp; str++)
-    {
-      int n = *str < 0x80 ? 1 : 2;
-      if (INT_ADD_WRAPV (bytes, n, &bytes))
-        string_overflow ();
-    }
+  if (INT_ADD_WRAPV (len, nonascii, &bytes))
+    string_overflow ();
   return bytes;
 }