fold: check that characters are not non-breaking spaces when -s is used

NetBSD 10 and Solaris 11.4 treat non-breaking spaces as blank
characters unlike glibc.

* src/system.h: Include uchar.h.
(c32isnbspace): New function based on iswnbspace from src/wc.c.
* src/fold.c (fold_file): Use it.
* src/wc.c (iswnbspace): Remove function.
(maybe_c32isnbspace): New function.
(wc, main): Use it.
Fixes https://bugs.gnu.org/79300

diff --git a/src/fold.c b/src/fold.c
index 5f71d5c5530c938e483530ec92847fd2b8fd5106..b90bc7d80a38e3818239e47eca8edf58933e1b3e 100644 (file)
--- a/src/fold.c
+++ b/src/fold.c
@@ -216,7 +216,7 @@ fold_file (char const *filename, size_t width)
                   for (mcel_t g2; logical_p < logical_lim; logical_p += g2.len)
                     {
                       g2 = mcel_scan (logical_p, logical_lim);
-                      if (c32isblank (g2.ch))
+                      if (c32isblank (g2.ch) && ! c32isnbspace (g2.ch))
                         {
                           space_length = g2.len;
                           logical_end = logical_p - line_out;

diff --git a/src/system.h b/src/system.h
index 5cb751cc89a4024c88e4091e2c0ce475b2429d7d..2296c8bbb9396b65802fca4534e2b3934b3002a7 100644 (file)
--- a/src/system.h
+++ b/src/system.h
@@ -70,6 +70,7 @@
 #include <stdckdint.h>
 #include <stddef.h>
 #include <string.h>
+#include <uchar.h>
 #include <errno.h>
 
 /* Some systems don't define this; POSIX mentions it but says it is
@@ -148,6 +149,14 @@ enum
    errors that the cast doesn't.  */
 static inline unsigned char to_uchar (char ch) { return ch; }
 
+/* Return non zero if a non breaking space.  */
+ATTRIBUTE_PURE
+static inline int
+c32isnbspace (char32_t wc)
+{
+  return wc == 0x00A0 || wc == 0x2007 || wc == 0x202F || wc == 0x2060;
+}
+
 #include <locale.h>
 
 /* Take care of NLS matters.  */

diff --git a/src/wc.c b/src/wc.c
index 05e78676e35aa5aec4cd7dc868595ee682b1d66d..f22f658b4f7b476822f3bdeff17db1c821cc56c3 100644 (file)
--- a/src/wc.c
+++ b/src/wc.c
@@ -191,14 +191,13 @@ the following order: newline, word, character, byte, maximum line length.\n\
   exit (status);
 }
 
-/* Return non zero if a non breaking space.  */
+/* Return non zero if POSIXLY_CORRECT is not set and WC is a non breaking
+   space.  */
 ATTRIBUTE_PURE
 static int
-iswnbspace (wint_t wc)
+maybe_c32isnbspace (char32_t wc)
 {
-  return ! posixly_correct
-         && (wc == 0x00A0 || wc == 0x2007
-             || wc == 0x202F || wc == 0x2060);
+  return ! posixly_correct && c32isnbspace (wc);
 }
 
 /* FILE is the name of the file (or null for standard input)
@@ -525,8 +524,8 @@ wc (int fd, char const *file_x, struct fstatus *fstatus)
                           if (width > 0)
                             linepos += width;
                         }
-                      in_word2 = ! iswspace (wide_char)
-                                 && ! iswnbspace (wide_char);
+                      in_word2 = (! iswspace (wide_char)
+                                  && ! maybe_c32isnbspace (wide_char));
                     }
 
                   /* Count words by counting word starts, i.e., each
@@ -798,7 +797,7 @@ main (int argc, char **argv)
       wc_isprint[i] = !!isprint (i);
   if (print_words)
     for (int i = 0; i <= UCHAR_MAX; i++)
-      wc_isspace[i] = isspace (i) || iswnbspace (btoc32 (i));
+      wc_isspace[i] = isspace (i) || maybe_c32isnbspace (btoc32 (i));
 
   bool read_tokens = false;
   struct argv_iterator *ai;