rcx

commit bacaaf039091bd29603f4125cbc69c9e834fc71b
parent e167b6dbf0e90d90a749f18c87a15e4718d52869
Author: robert <robertrussell.72001@gmail.com>
Date:   Wed, 10 Aug 2022 14:34:31 -0700

Namespace all utf8 functions

Diffstat:
M
inc/cext/utf8.h
 | 
12
++++++------
M
src/utf8.c
 | 
20
++++++++++----------

2 files changed, 16 insertions(+), 16 deletions(-)
diff --git a/inc/cext/utf8.h b/inc/cext/utf8.h
@@ -2,13 +2,13 @@
 
 #include "cext/def.h"
 
-#define UTF8_SIZE 4
+#define CEXT_UTF8_SIZE 4
 
 /* Return the number of bytes needed to encode c, or 0 if c is an invalid
- * codepoint. If s is nonnull, then it must have length >= utf8encode(0, c),
- * which is guaranteed to be at most UTF8_SIZE; in this case, if c is a valid
- * codepoint, then encode c into s. */
-usize utf8encode(char *s, rune c);
+ * codepoint. If s is nonnull, then it must have length >=
+ * cext_utf8_encode(0, c), which is guaranteed to be at most CEXT_UTF8_SIZE;
+ * in this case, if c is a valid codepoint, then encode c into s. */
+usize cext_utf8_encode(char *s, rune c);
 
 /* Decode the first rune in s and return the number of consumed bytes. If this
  * succeeds and c is nonnull, then set *c to the decoded rune. Otherwise, no
@@ -18,4 +18,4 @@ usize utf8encode(char *s, rune c);
  *  - n > 0 iff the first min(n+1,slen) bytes of s are not a prefix of any
  *    valid rune (but if n < slen, then s[n] might be the first byte of a
  *    valid rune). */
-usize utf8decode(rune *c, char *s, usize slen);
+usize cext_utf8_decode(rune *c, char *s, usize slen);
diff --git a/src/utf8.c b/src/utf8.c
@@ -10,18 +10,18 @@ static const rune  utf8min[]  = { 0x0,  0x80,  0x800,  0x10000};
 static const rune  utf8max[]  = {0x7F, 0x7FF, 0xFFFF, 0x10FFFF};
 
 static bool
-utf8overlong(rune c, usize len) {
+utf8_overlong(rune c, usize len) {
 	return c < utf8min[len-1];
 }
 
 static bool
-utf8encodable(rune c) {
+utf8_encodable(rune c) {
 	return c <= RUNE_MAX && (c < SURROGATE_MIN || c > SURROGATE_MAX);
 }
 
 static usize
-utf8len(rune c) {
-	if (!utf8encodable(c))
+utf8_len(rune c) {
+	if (!utf8_encodable(c))
 		return 0;
 
 	usize len = 1;
@@ -31,8 +31,8 @@ utf8len(rune c) {
 }
 
 usize
-utf8encode(char *s, rune c) {
-	usize len = utf8len(c);
+cext_utf8_encode(char *s, rune c) {
+	usize len = utf8_len(c);
 	if (!s || len == 0)
 		return len;
 
@@ -46,7 +46,7 @@ utf8encode(char *s, rune c) {
 }
 
 usize
-utf8decode(rune *c, char *s, usize slen) {
+cext_utf8_decode(rune *c, char *s, usize slen) {
 	if (c)
 		*c = RUNE_BAD;
 
@@ -55,11 +55,11 @@ utf8decode(rune *c, char *s, usize slen) {
 
 	/* Determine encoded sequence length based on first byte */
 	usize len = 1;
-	for (; len <= UTF8_SIZE; len++) {
+	for (; len <= CEXT_UTF8_SIZE; len++) {
 		if (((uchar)s[0] & utf8mask[len-1]) == utf8byte[len-1])
 			break;
 	}
-	if (len > UTF8_SIZE) /* Invalid leading byte? */
+	if (len > CEXT_UTF8_SIZE) /* Invalid leading byte? */
 		return 1;
 
 	/* Decode codepoint */
@@ -73,7 +73,7 @@ utf8decode(rune *c, char *s, usize slen) {
 	if (len > slen)
 		return 0; /* Looks good so far, but not enough input */
 
-	if (c && utf8encodable(r) && !utf8overlong(r, len))
+	if (c && utf8_encodable(r) && !utf8_overlong(r, len))
 		*c = r;
 	return len;
 }