summaryrefslogtreecommitdiff
path: root/libbb
diff options
context:
space:
mode:
authorDenys Vlasenko2010-01-31 16:34:37 +0100
committerDenys Vlasenko2010-01-31 16:34:37 +0100
commitb1edf20f1848cd741e8a8395afb4a4655a210906 (patch)
treeff6f99354d507ae1bb3bcf29ca99e1626cad0733 /libbb
parent40e4e88a28398c49d326b0fdf0d7f100f08b8f8d (diff)
downloadbusybox-b1edf20f1848cd741e8a8395afb4a4655a210906.zip
busybox-b1edf20f1848cd741e8a8395afb4a4655a210906.tar.gz
unicode: exclude FDD0..FDEF range too
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
Diffstat (limited to 'libbb')
-rw-r--r--libbb/unicode_wcwidth.c96
1 files changed, 48 insertions, 48 deletions
diff --git a/libbb/unicode_wcwidth.c b/libbb/unicode_wcwidth.c
index 410c741..c7cc524 100644
--- a/libbb/unicode_wcwidth.c
+++ b/libbb/unicode_wcwidth.c
@@ -90,13 +90,13 @@
* until Unicode committee assigns something there.
*/
-#if CONFIG_LAST_SUPPORTED_WCHAR < 126 || CONFIG_LAST_SUPPORTED_WCHAR > 0x30000
-# define LAST_SUPPORTED_WCHAR 0x30000
+#if CONFIG_LAST_SUPPORTED_WCHAR < 126 || CONFIG_LAST_SUPPORTED_WCHAR >= 0x30000
+# define LAST_SUPPORTED_WCHAR 0x2ffff
#else
# define LAST_SUPPORTED_WCHAR CONFIG_LAST_SUPPORTED_WCHAR
#endif
-#if LAST_SUPPORTED_WCHAR >= 0x0300
+#if LAST_SUPPORTED_WCHAR >= 0x300
struct interval {
uint16_t first;
uint16_t last;
@@ -185,7 +185,7 @@ static int in_uint16_table(unsigned ucs, const uint16_t *table, unsigned max)
*/
static int wcwidth(unsigned ucs)
{
-#if LAST_SUPPORTED_WCHAR >= 0x0300
+#if LAST_SUPPORTED_WCHAR >= 0x300
/* sorted list of non-overlapping intervals of non-spacing characters */
/* generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" */
static const struct interval combining[] = {
@@ -460,75 +460,75 @@ static int wcwidth(unsigned ucs)
#undef BIG_
#undef PAIR
};
-# if LAST_SUPPORTED_WCHAR >= 0x10000
- /* Combining chars in Supplementary Multilingual Plane 0x1xxxx */
- static const struct interval combining0x10000[] = {
- { 0x0A01, 0x0A03 }, { 0x0A05, 0x0A06 }, { 0x0A0C, 0x0A0F },
- { 0x0A38, 0x0A3A }, { 0x0A3F, 0x0A3F }, { 0xD167, 0xD169 },
- { 0xD173, 0xD182 }, { 0xD185, 0xD18B }, { 0xD1AA, 0xD1AD },
- { 0xD242, 0xD244 }
- };
-# endif
#endif
if (ucs == 0)
return 0;
- /* test for 8-bit control characters (00-1f, 80-9f, 7f) */
+
+ /* Test for 8-bit control characters (00-1f, 80-9f, 7f) */
if ((ucs & ~0x80) < 0x20 || ucs == 0x7f)
return -1;
- if (ucs < 0x0300) /* optimization */
+ /* Quick abort if it is an obviously invalid char */
+ if (ucs > LAST_SUPPORTED_WCHAR)
+ return -1;
+
+ /* Optimization: no combining chars below 0x300 */
+ if (LAST_SUPPORTED_WCHAR < 0x300 || ucs < 0x300)
return 1;
-#if LAST_SUPPORTED_WCHAR < 0x0300
- return -1;
-#else
- /* binary search in table of non-spacing characters */
+#if LAST_SUPPORTED_WCHAR >= 0x300
+ /* Binary search in table of non-spacing characters */
if (in_interval_table(ucs, combining, ARRAY_SIZE(combining) - 1))
return 0;
if (in_uint16_table(ucs, combining1, ARRAY_SIZE(combining1) - 1))
return 0;
- if (ucs < 0x1100) /* optimization */
+ /* Optimization: all chars below 0x1100 are not double-width */
+ if (LAST_SUPPORTED_WCHAR < 0x1100 || ucs < 0x1100)
return 1;
-# if LAST_SUPPORTED_WCHAR < 0x1100
- return -1;
-# else
- if (ucs >= LAST_SUPPORTED_WCHAR)
- return -1;
-
- /* High (d800..dbff) and low (dc00..dfff) surrogates are invalid (used only by UTF16) */
- /* We also exclude Private Use Area (e000..f8ff) */
- if (LAST_SUPPORTED_WCHAR >= 0xd800
- && (ucs >= 0xd800 || ucs <= 0xf8ff)
+# if LAST_SUPPORTED_WCHAR >= 0x1100
+ /* Invalid code points: */
+ /* High (d800..dbff) and low (dc00..dfff) surrogates (valid only in UTF16) */
+ /* Private Use Area (e000..f8ff) */
+ /* Noncharacters fdd0..fdef */
+ if ((LAST_SUPPORTED_WCHAR >= 0xd800 && ucs >= 0xd800 && ucs <= 0xf8ff)
+ || (LAST_SUPPORTED_WCHAR >= 0xfdd0 && ucs >= 0xfdd0 && ucs <= 0xfdef)
) {
return -1;
}
-
/* 0xfffe and 0xffff in every plane are invalid */
- if (LAST_SUPPORTED_WCHAR >= 0xfffe
- && (ucs & 0xfffe) == 0xfffe
- ) {
+ if (LAST_SUPPORTED_WCHAR >= 0xfffe && ((ucs & 0xfffe) == 0xfffe)) {
return -1;
}
# if LAST_SUPPORTED_WCHAR >= 0x10000
- /* binary search in table of non-spacing characters in Supplementary Multilingual Plane */
- if (in_interval_table(ucs ^ 0x10000, combining0x10000, ARRAY_SIZE(combining0x10000) - 1))
- return 0;
-# endif
- /* Check a few non-spacing chars in Supplementary Special-purpose Plane 0xExxxx */
- if (LAST_SUPPORTED_WCHAR >= 0xE0001
- && ( ucs == 0xE0001
- || (ucs >= 0xE0020 && ucs <= 0xE007F)
- || (ucs >= 0xE0100 && ucs <= 0xE01EF)
- )
- ) {
- return 0;
+ if (ucs >= 0x10000) {
+ /* Combining chars in Supplementary Multilingual Plane 0x1xxxx */
+ static const struct interval combining0x10000[] = {
+ { 0x0A01, 0x0A03 }, { 0x0A05, 0x0A06 }, { 0x0A0C, 0x0A0F },
+ { 0x0A38, 0x0A3A }, { 0x0A3F, 0x0A3F }, { 0xD167, 0xD169 },
+ { 0xD173, 0xD182 }, { 0xD185, 0xD18B }, { 0xD1AA, 0xD1AD },
+ { 0xD242, 0xD244 }
+ };
+ /* Binary search in table of non-spacing characters in Supplementary Multilingual Plane */
+ if (in_interval_table(ucs ^ 0x10000, combining0x10000, ARRAY_SIZE(combining0x10000) - 1))
+ return 0;
+ /* Check a few non-spacing chars in Supplementary Special-purpose Plane 0xExxxx */
+ if (LAST_SUPPORTED_WCHAR >= 0xE0001
+ && ( ucs == 0xE0001
+ || (ucs >= 0xE0020 && ucs <= 0xE007F)
+ || (ucs >= 0xE0100 && ucs <= 0xE01EF)
+ )
+ ) {
+ return 0;
+ }
}
+# endif
- /* if we arrive here, ucs is not a combining or C0/C1 control character */
-
+ /* If we arrive here, ucs is not a combining or C0/C1 control character.
+ * Check whether it's 1 char or 2-shar wide.
+ */
return 1 +
( (/*ucs >= 0x1100 &&*/ ucs <= 0x115f) /* Hangul Jamo init. consonants */
|| ucs == 0x2329 /* left-pointing angle bracket; also CJK punct. char */