nano

commit 66d9d6c6d236ef1ed9bfc7545b227c8fbd80671b
parent de816840cb39c915b20ecf5225acded37f95ba9d
Author: Benno Schulenberg <bensberg@telfort.nl>
Date:   Thu, 25 Mar 2021 10:52:42 +0100

tweaks: elide the pointless is_valid_unicode() function

The call of this function in make_mbchar() does not add anything,
because wctomb() already returns -1 for codes U+D800 to U+DFFF,
and parse_verbatim_kbinput() already rejects anything that starts
with U+11.... or higher, so make_mbchar() is never called for codes
beyond U+10FFFF.

And the call in display_string() just needs to check for wc <= 0x10FFFF
because mbtowc() already returns -1 for codes U+D800 to U+DFFF.

Diffstat:
M
src/chars.c
 | 
11
+----------
M
src/prototypes.h
 | 
3
---
M
src/winio.c
 | 
2
+-

3 files changed, 2 insertions(+), 14 deletions(-)
diff --git a/src/chars.c b/src/chars.c
@@ -212,8 +212,7 @@ char *make_mbchar(long code, int *length)
 
 	*length = wctomb(mb_char, (wchar_t)code);
 
-	/* Reject invalid Unicode characters. */
-	if (*length < 0 || !is_valid_unicode((wchar_t)code)) {
+	if (*length < 0) {
 		IGNORE_CALL_RESULT(wctomb(NULL, 0));
 		*length = 0;
 	}
@@ -615,11 +614,3 @@ bool white_string(const char *string)
 
 	return !*string;
 }
-
-#ifdef ENABLE_UTF8
-/* Return TRUE if wc is valid Unicode, and FALSE otherwise. */
-bool is_valid_unicode(wchar_t wc)
-{
-	return ((0 <= wc && wc <= 0xD7FF) || (0xE000 <= wc && wc <= 0x10FFFF));
-}
-#endif
diff --git a/src/prototypes.h b/src/prototypes.h
@@ -230,9 +230,6 @@ char *mbrevstrpbrk(const char *head, const char *accept, const char *pointer);
 bool has_blank_char(const char *string);
 #endif
 bool white_string(const char *string);
-#ifdef ENABLE_UTF8
-bool is_valid_unicode(wchar_t wc);
-#endif
 
 /* Most functions in color.c. */
 #ifdef ENABLE_COLOR
diff --git a/src/winio.c b/src/winio.c
@@ -1823,7 +1823,7 @@ char *display_string(const char *buf, size_t column, size_t span,
 		charlength = mbtowc(&wc, buf, MAXCHARLEN);
 
 		/* Represent an invalid character with the Replacement Character. */
-		if (charlength < 0 || !is_valid_unicode(wc)) {
+		if (charlength < 0 || wc > 0x10FFFF) {
 			converted[index++] = '\xEF';
 			converted[index++] = '\xBF';
 			converted[index++] = '\xBD';