34636: replace broken isprint() on Mac OS X

ChangeLog

@@ -1,3 +1,8 @@
+2015-03-05  Jun-ichi Takimoto <takimoto-j@kba.biglobe.ne.jp>
+
+	* 34636: Src/compat.c, Src/pattern.c, Src/utils.c, Src/ztype.c,
+	configure.ac: replace broken isprint() on Mac OS X.
+
 2015-03-04  Peter Stephenson  <p.stephenson@samsung.com>
 
 	* 34641: Src/lex.c, Test/A02alias.ztst: make it possible to

Src/compat.c

@@ -951,3 +951,18 @@ int mk_wcswidth_cjk(const wchar_t *pwcs, size_t n)
 /**/
 #endif /* BROKEN_WCWIDTH && (__STDC_ISO_10646__ || __APPLE__) */
 
+/**/
+#if defined(__APPLE__) && defined(BROKEN_ISPRINT)
+
+/**/
+int
+isprint_ascii(int c)
+{
+    if (!strcmp(nl_langinfo(CODESET), "UTF-8"))
+	return (c >= 0x20 && c <= 0x7e);
+    else
+	return isprint(c);
+}
+
+/**/
+#endif /* __APPLE__ && BROKEN_ISPRINT */

Src/pattern.c

@@ -3622,7 +3622,7 @@ patmatchrange(char *range, int ch, int *indptr, int *mtp)
 		    return 1;
 		break;
 	    case PP_PRINT:
-		if (isprint(ch))
+		if (ISPRINT(ch))
 		    return 1;
 		break;
 	    case PP_PUNCT:

Src/utils.c

@@ -414,7 +414,7 @@ nicechar(int c)
     static char buf[6];
     char *s = buf;
     c &= 0xff;
-    if (isprint(c))
+    if (ISPRINT(c))
 	goto done;
     if (c & 0x80) {
 	if (isset(PRINTEIGHTBIT))
@@ -423,7 +423,7 @@ nicechar(int c)
 	*s++ = 'M';
 	*s++ = '-';
 	c &= 0x7f;
-	if(isprint(c))
+	if(ISPRINT(c))
 	    goto done;
     }
     if (c == 0x7f) {

Src/ztype.h

@@ -75,3 +75,9 @@
 #define WC_ZISTYPE(X,Y)	zistype((X),(Y))
 #define WC_ISPRINT(X)	isprint(X)
 #endif
+
+#if defined(__APPLE__) && defined(BROKEN_ISPRINT)
+#define ISPRINT(c)  isprint_ascii(c)
+#else
+#define ISPRINT(c)  isprint(c)
+#endif

configure.ac

@@ -2567,6 +2567,8 @@ AH_TEMPLATE([MULTIBYTE_SUPPORT],
 [Define to 1 if you want support for multibyte character sets.])
 AH_TEMPLATE([BROKEN_WCWIDTH],
 [Define to 1 if the wcwidth() function is present but broken.])
+AH_TEMPLATE([BROKEN_ISPRINT],
+[Define to 1 if the isprint() function is broken under UTF-8 locale.])
 if test x$zsh_cv_c_unicode_support = xyes; then
   AC_DEFINE(MULTIBYTE_SUPPORT)
 
@@ -2622,6 +2624,38 @@ if test x$zsh_cv_c_unicode_support = xyes; then
   if test x$zsh_cv_c_broken_wcwidth = xyes; then
     AC_DEFINE(BROKEN_WCWIDTH)
   fi
+
+  dnl Check if isprint() behaves correctly under UTF-8 locale.
+  dnl On some platform (maybe only on Mac OS X), isprint() returns
+  dnl true for all characters in the range from 0xa0 to 0xff if
+  dnl called under UTF-8 locale.
+  [locale_prog='char *my_locales[] = {
+  "en_US.UTF-8", "en_GB.UTF-8", "en.UTF-8", '
+  locale_prog="$locale_prog"`locale -a 2>/dev/null | \
+    sed -e 's/utf8/UTF-8/' | grep UTF-8 | \
+    while read line; do echo " \"$line\","; done;`
+  locale_prog="$locale_prog 0 };
+  #include <locale.h>
+  #include <ctype.h>
+
+  int main() {
+    char **localep;
+    for (localep = my_locales; *localep; localep++)
+      if (setlocale(LC_ALL, *localep) && isprint(0xa0))
+	return 0;
+    return 1;
+  }
+  "]
+
+  AC_CACHE_CHECK(if the isprint() function is broken,
+  zsh_cv_c_broken_isprint,
+  [AC_TRY_RUN([$locale_prog],
+  zsh_cv_c_broken_isprint=yes,
+  zsh_cv_c_broken_isprint=no,
+  zsh_cv_c_broken_isprint=no)])
+  if test x$zsh_cv_c_broken_isprint = xyes; then
+    AC_DEFINE(BROKEN_ISPRINT)
+  fi
 fi
 
 dnl