From: Paul Eggert <eggert@cs.ucla.edu>
Date: Fri, 22 Sep 2023 01:45:08 +0000 (-0700)
Subject: wc: stop worrying about EBCDIC, shift-JIS, etc
X-Git-Tag: v9.5~155
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=6c16044d8d28a5f6cc02280eaa531487e472f629;p=thirdparty%2Fcoreutils.git

wc: stop worrying about EBCDIC, shift-JIS, etc

* src/wc.c: Do not include mbchar.h.
(wc): Check for ASCII characters instead of using is_basic.
Other parts of Gnulib and coreutils already assume the encoding
is upward compatible with ASCII, and the old code wouldn’t
have worked anyway with shift-JIS.
---

diff --git a/src/wc.c b/src/wc.c
index 6b802f5c7f..130be8c32c 100644
--- a/src/wc.c
+++ b/src/wc.c
@@ -31,7 +31,6 @@
 #include "argmatch.h"
 #include "argv-iter.h"
 #include "fadvise.h"
-#include "mbchar.h"
 #include "physmem.h"
 #include "readtokens0.h"
 #include "safe-read.h"
@@ -490,7 +489,7 @@ wc (int fd, char const *file_x, struct fstatus *fstatus, off_t current_pos)
               size_t n;
               bool wide = true;
 
-              if (!in_shift && is_basic (*p))
+              if (!in_shift && 0 <= *p && *p < 0x80)
                 {
                   /* Handle most ASCII characters quickly, without calling
                      mbrtowc().  */