fyb/calcurse-edge
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update UTF-8 base code

Browse Source 
UTF-8 encodes characters in one to four bytes (since 2003).

Because 0 is a valid code point, the decode function utf8_ord()
should return -1, not 0, on error. As a consequence utf8_width()
should return 0 for a continuation byte (as it did previously).

Signed-off-by: Lukas Fleischer <lfleischer@calcurse.org>
This commit is contained in:
Lars Henriksen 2017-11-29 22:19:10 +01:00 committed by Lukas Fleischer
parent edc44d613b
commit 95c5d576fa
2 changed files with 11 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/calcurse.h
View File

@ -225,13 +225,10 @@
#define TOSTRING(x) STRINGIFY(x) #define TOSTRING(x) STRINGIFY(x)
#define __FILE_POS__ __FILE__ ":" TOSTRING(__LINE__) #define __FILE_POS__ __FILE__ ":" TOSTRING(__LINE__)
#define UTF8_MAXLEN 6 #define UTF8_MAXLEN 4
#define UTF8_LENGTH(ch) ((unsigned char)ch >= 0xFC ? 6 : \ #define UTF8_LENGTH(ch) ((unsigned char)ch >= 0xF0 ? 4 : \
((unsigned char)ch >= 0xF8 ? 5 : \
((unsigned char)ch >= 0xF0 ? 4 : \
((unsigned char)ch >= 0xE0 ? 3 : \ ((unsigned char)ch >= 0xE0 ? 3 : \
((unsigned char)ch >= 0xC0 ? 2 : 1))))) ((unsigned char)ch >= 0xC0 ? 2 : 1)))
#define UTF8_ISMULTI(ch) ((unsigned char)ch >= 0x80)
#define UTF8_ISCONT(ch) ((unsigned char)ch >= 0x80 && \ #define UTF8_ISCONT(ch) ((unsigned char)ch >= 0x80 && \
(unsigned char)ch <= 0xBF) (unsigned char)ch <= 0xBF)

23
src/utf8.c
View File

@ -269,11 +269,11 @@ static const struct utf8_range utf8_widthtab[] = {
{0xe0100, 0xe01ef, 0} {0xe0100, 0xe01ef, 0}
}; };
/* Decode a UTF-8 code point. */ /* Decode a UTF-8 encoded character. Return the Unicode code point. */
int utf8_ord(const char *s) int utf8_ord(const char *s)
{ {
if (UTF8_ISCONT(*s)) if (UTF8_ISCONT(*s))
return 0; return -1;
switch (UTF8_LENGTH(*s)) { switch (UTF8_LENGTH(*s)) {
case 1: case 1:
@ -285,17 +285,9 @@ int utf8_ord(const char *s)
(s[0] & 0x0f) << 12; (s[0] & 0x0f) << 12;
case 4: case 4:
return (((s[3] & 0x3f) | (s[2] & 0x3f) << 6) | return (((s[3] & 0x3f) | (s[2] & 0x3f) << 6) |
(s[1] & 0x3f) << 12) | (s[0] & 0x3f) << 18; (s[1] & 0x3f) << 12) | (s[0] & 0x7) << 18;
case 5:
return ((((s[4] & 0x3f) | (s[3] & 0x3f) << 6) |
(s[2] & 0x3f) << 12) | (s[1] & 0x3f) << 18) |
(s[0] & 0x3f) << 24;
case 6:
return (((((s[5] & 0x3f) | (s[4] & 0x3f) << 6) |
(s[3] & 0x3f) << 12) | (s[2] & 0x3f) << 18) |
(s[1] & 0x3f) << 24) | (s[0] & 0x3f) << 30;
default: default:
return 0; return -1;
} }
} }
@ -304,6 +296,8 @@ int utf8_width(char *s)
{ {
int val, low, high, cur; int val, low, high, cur;
if (UTF8_ISCONT(*s))
return 0;
val = utf8_ord(s); val = utf8_ord(s);
low = 0; low = 0;
high = ARRAY_SIZE(utf8_widthtab); high = ARRAY_SIZE(utf8_widthtab);
@ -328,11 +322,8 @@ int utf8_strwidth(char *s)
{ {
int width = 0; int width = 0;
for (; s && *s; s++) { for (; *s; s++)
if (!UTF8_ISCONT(*s))
width += utf8_width(s); width += utf8_width(s);
}
return width; return width;
} }