From 95c5d576fafa2f705e6562f57bab9a9d583c8776 Mon Sep 17 00:00:00 2001 From: Lars Henriksen Date: Wed, 29 Nov 2017 22:19:10 +0100 Subject: Update UTF-8 base code 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 --- src/calcurse.h | 9 +++------ src/utf8.c | 25 ++++++++----------------- 2 files changed, 11 insertions(+), 23 deletions(-) diff --git a/src/calcurse.h b/src/calcurse.h index f4f0e6c..5bf32cf 100644 --- a/src/calcurse.h +++ b/src/calcurse.h @@ -225,13 +225,10 @@ #define TOSTRING(x) STRINGIFY(x) #define __FILE_POS__ __FILE__ ":" TOSTRING(__LINE__) -#define UTF8_MAXLEN 6 -#define UTF8_LENGTH(ch) ((unsigned char)ch >= 0xFC ? 6 : \ - ((unsigned char)ch >= 0xF8 ? 5 : \ - ((unsigned char)ch >= 0xF0 ? 4 : \ +#define UTF8_MAXLEN 4 +#define UTF8_LENGTH(ch) ((unsigned char)ch >= 0xF0 ? 4 : \ ((unsigned char)ch >= 0xE0 ? 3 : \ - ((unsigned char)ch >= 0xC0 ? 2 : 1))))) -#define UTF8_ISMULTI(ch) ((unsigned char)ch >= 0x80) + ((unsigned char)ch >= 0xC0 ? 2 : 1))) #define UTF8_ISCONT(ch) ((unsigned char)ch >= 0x80 && \ (unsigned char)ch <= 0xBF) diff --git a/src/utf8.c b/src/utf8.c index 47d83dc..e7754ae 100644 --- a/src/utf8.c +++ b/src/utf8.c @@ -269,11 +269,11 @@ static const struct utf8_range utf8_widthtab[] = { {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) { if (UTF8_ISCONT(*s)) - return 0; + return -1; switch (UTF8_LENGTH(*s)) { case 1: @@ -285,17 +285,9 @@ int utf8_ord(const char *s) (s[0] & 0x0f) << 12; case 4: return (((s[3] & 0x3f) | (s[2] & 0x3f) << 6) | - (s[1] & 0x3f) << 12) | (s[0] & 0x3f) << 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; + (s[1] & 0x3f) << 12) | (s[0] & 0x7) << 18; default: - return 0; + return -1; } } @@ -304,6 +296,8 @@ int utf8_width(char *s) { int val, low, high, cur; + if (UTF8_ISCONT(*s)) + return 0; val = utf8_ord(s); low = 0; high = ARRAY_SIZE(utf8_widthtab); @@ -328,11 +322,8 @@ int utf8_strwidth(char *s) { int width = 0; - for (; s && *s; s++) { - if (!UTF8_ISCONT(*s)) - width += utf8_width(s); - } - + for (; *s; s++) + width += utf8_width(s); return width; } -- cgit v1.2.3-54-g00ecf