static int git_wcwidth(ucs_char_t ch)
{
/*
* Sorted list of non-overlapping intervals of non-spacing characters,
*/
#include "unicode_width.h"
/* test for 8-bit control characters */
if (ch == 0)
return 0;
if (ch < 32 || (ch >= 0x7f && ch < 0xa0))
return -1;
/* binary search in table of non-spacing characters */
if (bisearch(ch, zero_width, sizeof(zero_width)
/ sizeof(struct interval) - 1))
return 0;
/* binary search in table of double width characters */
if (bisearch(ch, double_width, sizeof(double_width)
/ sizeof(struct interval) - 1))
return 2;
return 1;
}
int
xcwidth(xchar c)
{
/* null character */
if (c == 0)
return 0;
/* printable ASCII characters */
if (c >= 0x20 && c < 0x7f)
return 1;
/* control characters */
if (c < 0xa0)
return -1;
/* non-spacing characters */
if (bisearch(c, combining, lengthof(combining)))
return 0;
/* CJK ambiguous characters */
if (bisearch(c, ambiguous, lengthof(ambiguous)))
return font_ambig_wide + 1;
/* wide characters */
if (bisearch(c, wide, lengthof(wide)))
return 2;
/* anything else */
return 1;
}
TEST(Search_Binary, bisearch)
{
int size = 100;
int *data = (int *)malloc(size * sizeof(int));
int i;
for (i = 0; i < size; ++i) {
data[i] = i;
}
int result;
int *target = (int *)malloc(sizeof(int));
*target = 10;
result = bisearch(data, target, size, sizeof(int), compare);
EXPECT_EQ(10, result);
*target = 101;
result = bisearch(data, target, size, sizeof(int), compare);
EXPECT_EQ(-1, result);
*target = 99;
result = bisearch(data, target, size, sizeof(int), compare);
EXPECT_EQ(99, result);
}
vector<int> searchRange(vector<int>& nums, int target) {
vector<int> ans;
int left = bisearch(nums, target, 0);
int right = bisearch(nums, target, 1);
ans.push_back(left); ans.push_back(right);
return ans;
}
static int mk_wcwidth(uint32_t ucs)
{
/* test for 8-bit control characters */
if (ucs == 0)
return 0;
if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
return -1;
/* binary search in table of non-spacing characters */
if (bisearch(ucs, combining,
sizeof(combining) / sizeof(struct interval) - 1))
return 0;
/* if we arrive here, ucs is not a combining or C0/C1 control character */
return 1 +
(ucs >= 0x1100 &&
(ucs <= 0x115f || /* Hangul Jamo init. consonants */
ucs == 0x2329 || ucs == 0x232a ||
(ucs >= 0x2e80 && ucs <= 0xa4cf &&
ucs != 0x303f) || /* CJK ... Yi */
(ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
(ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
(ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */
(ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
(ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
(ucs >= 0xffe0 && ucs <= 0xffe6) ||
(ucs >= 0x20000 && ucs <= 0x2fffd) ||
(ucs >= 0x30000 && ucs <= 0x3fffd)));
}
float IVT::get_p(int yindex)
{
int i;
i = bisearch(yindex, offset, offset+paircnt);
if (i == -1)
return (float) MAXPLOG;
return postnode[i].p;
}
static char is_double_width(unsigned ucs)
{
static const struct interval double_width[] = {
{ 0x1100, 0x115F}, { 0x2329, 0x232A}, { 0x2E80, 0x303E},
{ 0x3040, 0xA4CF}, { 0xAC00, 0xD7A3}, { 0xF900, 0xFAFF},
{ 0xFE10, 0xFE19}, { 0xFE30, 0xFE6F}, { 0xFF00, 0xFF60},
{ 0xFFE0, 0xFFE6}, { 0x20000, 0x2FFFD}, { 0x30000, 0x3FFFD}
};
return bisearch(ucs, double_width, sizeof(double_width) / sizeof(struct interval) - 1);
}
int IVT::lookup(int key){
int i;
i = bisearch(key, maxIVT);
if ( i == -1) return 0;
index = i;
offset = ivtnode[i].offset;
paircnt = ivtnode[i].paircnt;
return paircnt;
}
int main()
{
int a;
int array[N] = {1,3,4,6,7,8,9,10,12,15};
scanf("%d",&a);
int index = bisearch(array,a,N);
if(index != -1)
printf("array[%d] is %d\n",index,a);
else
printf("not found\n");
}
int main()
{
int t;
scanf("%d", &t);
while(t--)
{
init();
bfs_init();
bisearch();
}
return 0;
}
/*
* The following functions are the same as mk_wcwidth() and
* mk_wcswidth(), except that spacing characters in the East Asian
* Ambiguous (A) category as defined in Unicode Technical Report #11
* have a column width of 2. This variant might be useful for users of
* CJK legacy encodings who want to migrate to UCS without changing
* the traditional terminal character-width behaviour. It is not
* otherwise recommended for general use.
*/
int mk_wcwidth_cjk(int ucs) {
/* sorted list of non-overlapping intervals of East Asian Ambiguous
* characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */
static const struct interval ambiguous[] = {
{0x00A1, 0x00A1}, {0x00A4, 0x00A4}, {0x00A7, 0x00A8}, {0x00AA, 0x00AA},
{0x00AE, 0x00AE}, {0x00B0, 0x00B4}, {0x00B6, 0x00BA}, {0x00BC, 0x00BF},
{0x00C6, 0x00C6}, {0x00D0, 0x00D0}, {0x00D7, 0x00D8}, {0x00DE, 0x00E1},
{0x00E6, 0x00E6}, {0x00E8, 0x00EA}, {0x00EC, 0x00ED}, {0x00F0, 0x00F0},
{0x00F2, 0x00F3}, {0x00F7, 0x00FA}, {0x00FC, 0x00FC}, {0x00FE, 0x00FE},
{0x0101, 0x0101}, {0x0111, 0x0111}, {0x0113, 0x0113}, {0x011B, 0x011B},
{0x0126, 0x0127}, {0x012B, 0x012B}, {0x0131, 0x0133}, {0x0138, 0x0138},
{0x013F, 0x0142}, {0x0144, 0x0144}, {0x0148, 0x014B}, {0x014D, 0x014D},
{0x0152, 0x0153}, {0x0166, 0x0167}, {0x016B, 0x016B}, {0x01CE, 0x01CE},
{0x01D0, 0x01D0}, {0x01D2, 0x01D2}, {0x01D4, 0x01D4}, {0x01D6, 0x01D6},
{0x01D8, 0x01D8}, {0x01DA, 0x01DA}, {0x01DC, 0x01DC}, {0x0251, 0x0251},
{0x0261, 0x0261}, {0x02C4, 0x02C4}, {0x02C7, 0x02C7}, {0x02C9, 0x02CB},
{0x02CD, 0x02CD}, {0x02D0, 0x02D0}, {0x02D8, 0x02DB}, {0x02DD, 0x02DD},
{0x02DF, 0x02DF}, {0x0391, 0x03A1}, {0x03A3, 0x03A9}, {0x03B1, 0x03C1},
{0x03C3, 0x03C9}, {0x0401, 0x0401}, {0x0410, 0x044F}, {0x0451, 0x0451},
{0x2010, 0x2010}, {0x2013, 0x2016}, {0x2018, 0x2019}, {0x201C, 0x201D},
{0x2020, 0x2022}, {0x2024, 0x2027}, {0x2030, 0x2030}, {0x2032, 0x2033},
{0x2035, 0x2035}, {0x203B, 0x203B}, {0x203E, 0x203E}, {0x2074, 0x2074},
{0x207F, 0x207F}, {0x2081, 0x2084}, {0x20AC, 0x20AC}, {0x2103, 0x2103},
{0x2105, 0x2105}, {0x2109, 0x2109}, {0x2113, 0x2113}, {0x2116, 0x2116},
{0x2121, 0x2122}, {0x2126, 0x2126}, {0x212B, 0x212B}, {0x2153, 0x2154},
{0x215B, 0x215E}, {0x2160, 0x216B}, {0x2170, 0x2179}, {0x2190, 0x2199},
{0x21B8, 0x21B9}, {0x21D2, 0x21D2}, {0x21D4, 0x21D4}, {0x21E7, 0x21E7},
{0x2200, 0x2200}, {0x2202, 0x2203}, {0x2207, 0x2208}, {0x220B, 0x220B},
{0x220F, 0x220F}, {0x2211, 0x2211}, {0x2215, 0x2215}, {0x221A, 0x221A},
{0x221D, 0x2220}, {0x2223, 0x2223}, {0x2225, 0x2225}, {0x2227, 0x222C},
{0x222E, 0x222E}, {0x2234, 0x2237}, {0x223C, 0x223D}, {0x2248, 0x2248},
{0x224C, 0x224C}, {0x2252, 0x2252}, {0x2260, 0x2261}, {0x2264, 0x2267},
{0x226A, 0x226B}, {0x226E, 0x226F}, {0x2282, 0x2283}, {0x2286, 0x2287},
{0x2295, 0x2295}, {0x2299, 0x2299}, {0x22A5, 0x22A5}, {0x22BF, 0x22BF},
{0x2312, 0x2312}, {0x2460, 0x24E9}, {0x24EB, 0x254B}, {0x2550, 0x2573},
{0x2580, 0x258F}, {0x2592, 0x2595}, {0x25A0, 0x25A1}, {0x25A3, 0x25A9},
{0x25B2, 0x25B3}, {0x25B6, 0x25B7}, {0x25BC, 0x25BD}, {0x25C0, 0x25C1},
{0x25C6, 0x25C8}, {0x25CB, 0x25CB}, {0x25CE, 0x25D1}, {0x25E2, 0x25E5},
{0x25EF, 0x25EF}, {0x2605, 0x2606}, {0x2609, 0x2609}, {0x260E, 0x260F},
{0x2614, 0x2615}, {0x261C, 0x261C}, {0x261E, 0x261E}, {0x2640, 0x2640},
{0x2642, 0x2642}, {0x2660, 0x2661}, {0x2663, 0x2665}, {0x2667, 0x266A},
{0x266C, 0x266D}, {0x266F, 0x266F}, {0x273D, 0x273D}, {0x2776, 0x277F},
{0xE000, 0xF8FF}, {0xFFFD, 0xFFFD}, {0xF0000, 0xFFFFD}, {0x100000, 0x10FFFD}
};
/* binary search in table of non-spacing characters */
if (bisearch(ucs, ambiguous, sizeof(ambiguous) / sizeof(struct interval) - 1))
return 2;
return mk_wcwidth(ucs);
}
int spell(char (*dictionary)[SPELL_SIZE], int size, const char *word) {
/*****************************************************************************
* *
* Look up the word. *
* *
*****************************************************************************/
if (bisearch(dictionary, word, size, SPELL_SIZE, compare_str) >= 0)
return 1;
else
return 0;
}
int get_display_width(t_utf8 c)
{
if (c == 0)
return (0);
if (c < 32 || (c >= 0X7f && c < 0xa0))
return (-1);
if (bisearch(c))
return (0);
return (1 + (c >= 0x1100
&& (c <= 0x115f || c == 0x2329 || c == 0x232a
|| (c >= 0x2e80 && c <= 0xa4cf && c != 0x303f)
|| (c >= 0xac00 && c <= 0xd7a3)
|| (c >= 0xf900 && c <= 0xfaff)
|| (c >= 0xfe10 && c <= 0xfe19)
|| (c >= 0xfe30 && c <= 0xfe6f)
|| (c >= 0xff00 && c <= 0xff60)
|| (c >= 0xffe0 && c <= 0xffe6)
|| (c >= 0x20000 && c <= 0x2fffd)
|| (c >= 0x30000 && c <= 0x3fffd))));
}
static int
vterm_is_combining(uint32_t codepoint)
{
return bisearch(codepoint, combining, sizeof(combining) / sizeof(struct interval) - 1);
}
int wcwidth_ucs(wchar_t ucs)
{
/* 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[] = {
{ 0x0300, 0x036f }, { 0x0483, 0x0486 }, { 0x0488, 0x0489 },
{ 0x0591, 0x05bd }, { 0x05bf, 0x05bf }, { 0x05c1, 0x05c2 },
{ 0x05c4, 0x05c5 }, { 0x05c7, 0x05c7 }, { 0x0600, 0x0603 },
{ 0x0610, 0x0615 }, { 0x064b, 0x065e }, { 0x0670, 0x0670 },
{ 0x06d6, 0x06e4 }, { 0x06e7, 0x06e8 }, { 0x06ea, 0x06ed },
{ 0x070f, 0x070f }, { 0x0711, 0x0711 }, { 0x0730, 0x074a },
{ 0x07a6, 0x07b0 }, { 0x07eb, 0x07f3 }, { 0x0901, 0x0902 },
{ 0x093c, 0x093c }, { 0x0941, 0x0948 }, { 0x094d, 0x094d },
{ 0x0951, 0x0954 }, { 0x0962, 0x0963 }, { 0x0981, 0x0981 },
{ 0x09bc, 0x09bc }, { 0x09c1, 0x09c4 }, { 0x09cd, 0x09cd },
{ 0x09e2, 0x09e3 }, { 0x0a01, 0x0a02 }, { 0x0a3c, 0x0a3c },
{ 0x0a41, 0x0a42 }, { 0x0a47, 0x0a48 }, { 0x0a4b, 0x0a4d },
{ 0x0a70, 0x0a71 }, { 0x0a81, 0x0a82 }, { 0x0abc, 0x0abc },
{ 0x0ac1, 0x0ac5 }, { 0x0ac7, 0x0ac8 }, { 0x0acd, 0x0acd },
{ 0x0ae2, 0x0ae3 }, { 0x0b01, 0x0b01 }, { 0x0b3c, 0x0b3c },
{ 0x0b3f, 0x0b3f }, { 0x0b41, 0x0b43 }, { 0x0b4d, 0x0b4d },
{ 0x0b56, 0x0b56 }, { 0x0b82, 0x0b82 }, { 0x0bc0, 0x0bc0 },
{ 0x0bcd, 0x0bcd }, { 0x0c3e, 0x0c40 }, { 0x0c46, 0x0c48 },
{ 0x0c4a, 0x0c4d }, { 0x0c55, 0x0c56 }, { 0x0cbc, 0x0cbc },
{ 0x0cbf, 0x0cbf }, { 0x0cc6, 0x0cc6 }, { 0x0ccc, 0x0ccd },
{ 0x0ce2, 0x0ce3 }, { 0x0d41, 0x0d43 }, { 0x0d4d, 0x0d4d },
{ 0x0dca, 0x0dca }, { 0x0dd2, 0x0dd4 }, { 0x0dd6, 0x0dd6 },
{ 0x0e31, 0x0e31 }, { 0x0e34, 0x0e3a }, { 0x0e47, 0x0e4e },
{ 0x0eb1, 0x0eb1 }, { 0x0eb4, 0x0eb9 }, { 0x0ebb, 0x0ebc },
{ 0x0ec8, 0x0ecd }, { 0x0f18, 0x0f19 }, { 0x0f35, 0x0f35 },
{ 0x0f37, 0x0f37 }, { 0x0f39, 0x0f39 }, { 0x0f71, 0x0f7e },
{ 0x0f80, 0x0f84 }, { 0x0f86, 0x0f87 }, { 0x0f90, 0x0f97 },
{ 0x0f99, 0x0fbc }, { 0x0fc6, 0x0fc6 }, { 0x102d, 0x1030 },
{ 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 },
{ 0x1058, 0x1059 }, { 0x1160, 0x11ff }, { 0x135f, 0x135f },
{ 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 },
{ 0x1772, 0x1773 }, { 0x17b4, 0x17b5 }, { 0x17b7, 0x17bd },
{ 0x17c6, 0x17c6 }, { 0x17c9, 0x17d3 }, { 0x17dd, 0x17dd },
{ 0x180b, 0x180d }, { 0x18a9, 0x18a9 }, { 0x1920, 0x1922 },
{ 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193b },
{ 0x1a17, 0x1a18 }, { 0x1b00, 0x1b03 }, { 0x1b34, 0x1b34 },
{ 0x1b36, 0x1b3a }, { 0x1b3c, 0x1b3c }, { 0x1b42, 0x1b42 },
{ 0x1b6b, 0x1b73 }, { 0x1dc0, 0x1dca }, { 0x1dfe, 0x1dff },
{ 0x200b, 0x200f }, { 0x202a, 0x202e }, { 0x2060, 0x2063 },
{ 0x206a, 0x206f }, { 0x20d0, 0x20ef }, { 0x302a, 0x302f },
#ifndef __APPLE__
{ 0x3099, 0x309a },
#endif
{ 0xa806, 0xa806 }, { 0xa80b, 0xa80b },
{ 0xa825, 0xa826 }, { 0xfb1e, 0xfb1e }, { 0xfe00, 0xfe0f },
{ 0xfe20, 0xfe23 }, { 0xfeff, 0xfeff }, { 0xfff9, 0xfffb },
{ 0x10a01, 0x10a03 }, { 0x10a05, 0x10a06 }, { 0x10a0c, 0x10a0f },
{ 0x10a38, 0x10a3a }, { 0x10a3f, 0x10a3f }, { 0x1d167, 0x1d169 },
{ 0x1d173, 0x1d182 }, { 0x1d185, 0x1d18b }, { 0x1d1aa, 0x1d1ad },
{ 0x1d242, 0x1d244 }, { 0xe0001, 0xe0001 }, { 0xe0020, 0xe007f },
{ 0xe0100, 0xe01ef }
};
/* test for 8-bit control characters */
if (ucs == 0)
return 0;
if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
return -1;
/* binary search in table of non-spacing characters */
if (bisearch(ucs, combining,
sizeof(combining) / sizeof(struct interval) - 1))
return 0;
/* if we arrive here, ucs is not a combining or C0/C1 control character */
/* fast test for majority of non-wide scripts */
if (ucs < 0x1100)
return 1;
return 1 +
(ucs >= 0x1100 &&
(ucs <= 0x115f || /* Hangul Jamo init. consonants */
ucs == 0x2329 || ucs == 0x232a ||
(ucs >= 0x2e80 && ucs <= 0xa4cf &&
ucs != 0x303f) || /* CJK ... Yi */
(ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
(ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
(ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */
(ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
(ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
(ucs >= 0xffe0 && ucs <= 0xffe6) ||
(ucs >= 0x20000 && ucs <= 0x2fffd) ||
(ucs >= 0x30000 && ucs <= 0x3fffd)));
}
bool
indicwide(xchar c)
{
return bisearch(c, indic, lengthof(indic));
}
bool
ambigwide(xchar c)
{
return bisearch(c, ambiguous, lengthof(ambiguous))
&& !bisearch(c, wide, lengthof(wide));
}
bool
combiningdouble(xchar c)
{
return bisearch(c, combdouble, lengthof(combdouble));
}
bool
extrawide(xchar c)
{
return bisearch(c, extra, lengthof(extra));
}
int mk_wcwidth(wchar_t ucs)
{
/* sorted list of non-overlapping intervals of non-spacing characters */
/* generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" */
// From https://github.com/jquast/wcwidth/blob/master/wcwidth/table_zero.py
// at commit 0d7de112202cc8b2ebe9232ff4a5c954f19d561a (2016-07-02):
// Original source: DerivedGeneralCategory-9.0.0.txt
static const struct interval combining[] = {
{0x0300, 0x036f}, // Combining Grave Accent ..Combining Latin Small Le
{0x0483, 0x0489}, // Combining Cyrillic Titlo..Combining Cyrillic Milli
{0x0591, 0x05bd}, // Hebrew Accent Etnahta ..Hebrew Point Meteg
{0x05bf, 0x05bf}, // Hebrew Point Rafe ..Hebrew Point Rafe
{0x05c1, 0x05c2}, // Hebrew Point Shin Dot ..Hebrew Point Sin Dot
{0x05c4, 0x05c5}, // Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot
{0x05c7, 0x05c7}, // Hebrew Point Qamats Qata..Hebrew Point Qamats Qata
{0x0610, 0x061a}, // Arabic Sign Sallallahou ..Arabic Small Kasra
{0x064b, 0x065f}, // Arabic Fathatan ..Arabic Wavy Hamza Below
{0x0670, 0x0670}, // Arabic Letter Superscrip..Arabic Letter Superscrip
{0x06d6, 0x06dc}, // Arabic Small High Ligatu..Arabic Small High Seen
{0x06df, 0x06e4}, // Arabic Small High Rounde..Arabic Small High Madda
{0x06e7, 0x06e8}, // Arabic Small High Yeh ..Arabic Small High Noon
{0x06ea, 0x06ed}, // Arabic Empty Centre Low ..Arabic Small Low Meem
{0x0711, 0x0711}, // Syriac Letter Superscrip..Syriac Letter Superscrip
{0x0730, 0x074a}, // Syriac Pthaha Above ..Syriac Barrekh
{0x07a6, 0x07b0}, // Thaana Abafili ..Thaana Sukun
{0x07eb, 0x07f3}, // Nko Combining Sh||t High..Nko Combining Double Dot
{0x0816, 0x0819}, // Samaritan Mark In ..Samaritan Mark Dagesh
{0x081b, 0x0823}, // Samaritan Mark Epentheti..Samaritan Vowel Sign A
{0x0825, 0x0827}, // Samaritan Vowel Sign Sho..Samaritan Vowel Sign U
{0x0829, 0x082d}, // Samaritan Vowel Sign Lon..Samaritan Mark Nequdaa
{0x0859, 0x085b}, // Mandaic Affrication Mark..Mandaic Gemination Mark
{0x08d4, 0x08e1}, // (nil) ..
{0x08e3, 0x0902}, // Arabic Turned Damma Belo..Devanagari Sign Anusvara
{0x093a, 0x093a}, // Devanagari Vowel Sign Oe..Devanagari Vowel Sign Oe
{0x093c, 0x093c}, // Devanagari Sign Nukta ..Devanagari Sign Nukta
{0x0941, 0x0948}, // Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai
{0x094d, 0x094d}, // Devanagari Sign Virama ..Devanagari Sign Virama
{0x0951, 0x0957}, // Devanagari Stress Sign U..Devanagari Vowel Sign Uu
{0x0962, 0x0963}, // Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo
{0x0981, 0x0981}, // Bengali Sign Candrabindu..Bengali Sign Candrabindu
{0x09bc, 0x09bc}, // Bengali Sign Nukta ..Bengali Sign Nukta
{0x09c1, 0x09c4}, // Bengali Vowel Sign U ..Bengali Vowel Sign Vocal
{0x09cd, 0x09cd}, // Bengali Sign Virama ..Bengali Sign Virama
{0x09e2, 0x09e3}, // Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal
{0x0a01, 0x0a02}, // Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi
{0x0a3c, 0x0a3c}, // Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta
{0x0a41, 0x0a42}, // Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu
{0x0a47, 0x0a48}, // Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai
{0x0a4b, 0x0a4d}, // Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama
{0x0a51, 0x0a51}, // Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat
{0x0a70, 0x0a71}, // Gurmukhi Tippi ..Gurmukhi Addak
{0x0a75, 0x0a75}, // Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash
{0x0a81, 0x0a82}, // Gujarati Sign Candrabind..Gujarati Sign Anusvara
{0x0abc, 0x0abc}, // Gujarati Sign Nukta ..Gujarati Sign Nukta
{0x0ac1, 0x0ac5}, // Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand
{0x0ac7, 0x0ac8}, // Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai
{0x0acd, 0x0acd}, // Gujarati Sign Virama ..Gujarati Sign Virama
{0x0ae2, 0x0ae3}, // Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca
{0x0b01, 0x0b01}, // ||iya Sign Candrabindu ..||iya Sign Candrabindu
{0x0b3c, 0x0b3c}, // ||iya Sign Nukta ..||iya Sign Nukta
{0x0b3f, 0x0b3f}, // ||iya Vowel Sign I ..||iya Vowel Sign I
{0x0b41, 0x0b44}, // ||iya Vowel Sign U ..||iya Vowel Sign Vocalic
{0x0b4d, 0x0b4d}, // ||iya Sign Virama ..||iya Sign Virama
{0x0b56, 0x0b56}, // ||iya Ai Length Mark ..||iya Ai Length Mark
{0x0b62, 0x0b63}, // ||iya Vowel Sign Vocalic..||iya Vowel Sign Vocalic
{0x0b82, 0x0b82}, // Tamil Sign Anusvara ..Tamil Sign Anusvara
{0x0bc0, 0x0bc0}, // Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii
{0x0bcd, 0x0bcd}, // Tamil Sign Virama ..Tamil Sign Virama
{0x0c00, 0x0c00}, // Telugu Sign Combining Ca..Telugu Sign Combining Ca
{0x0c3e, 0x0c40}, // Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii
{0x0c46, 0x0c48}, // Telugu Vowel Sign E ..Telugu Vowel Sign Ai
{0x0c4a, 0x0c4d}, // Telugu Vowel Sign O ..Telugu Sign Virama
{0x0c55, 0x0c56}, // Telugu Length Mark ..Telugu Ai Length Mark
{0x0c62, 0x0c63}, // Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali
{0x0c81, 0x0c81}, // Kannada Sign Candrabindu..Kannada Sign Candrabindu
{0x0cbc, 0x0cbc}, // Kannada Sign Nukta ..Kannada Sign Nukta
{0x0cbf, 0x0cbf}, // Kannada Vowel Sign I ..Kannada Vowel Sign I
{0x0cc6, 0x0cc6}, // Kannada Vowel Sign E ..Kannada Vowel Sign E
{0x0ccc, 0x0ccd}, // Kannada Vowel Sign Au ..Kannada Sign Virama
{0x0ce2, 0x0ce3}, // Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal
{0x0d01, 0x0d01}, // Malayalam Sign Candrabin..Malayalam Sign Candrabin
{0x0d41, 0x0d44}, // Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc
{0x0d4d, 0x0d4d}, // Malayalam Sign Virama ..Malayalam Sign Virama
{0x0d62, 0x0d63}, // Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc
{0x0dca, 0x0dca}, // Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna
{0x0dd2, 0x0dd4}, // Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti
{0x0dd6, 0x0dd6}, // Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga
{0x0e31, 0x0e31}, // Thai Character Mai Han-a..Thai Character Mai Han-a
{0x0e34, 0x0e3a}, // Thai Character Sara I ..Thai Character Phinthu
{0x0e47, 0x0e4e}, // Thai Character Maitaikhu..Thai Character Yamakkan
{0x0eb1, 0x0eb1}, // Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan
{0x0eb4, 0x0eb9}, // Lao Vowel Sign I ..Lao Vowel Sign Uu
{0x0ebb, 0x0ebc}, // Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo
{0x0ec8, 0x0ecd}, // Lao Tone Mai Ek ..Lao Niggahita
{0x0f18, 0x0f19}, // Tibetan Astrological Sig..Tibetan Astrological Sig
{0x0f35, 0x0f35}, // Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung
{0x0f37, 0x0f37}, // Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung
{0x0f39, 0x0f39}, // Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru
{0x0f71, 0x0f7e}, // Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga
{0x0f80, 0x0f84}, // Tibetan Vowel Sign Rever..Tibetan Mark Halanta
{0x0f86, 0x0f87}, // Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags
{0x0f8d, 0x0f97}, // Tibetan Subjoined Sign L..Tibetan Subjoined Letter
{0x0f99, 0x0fbc}, // Tibetan Subjoined Letter..Tibetan Subjoined Letter
{0x0fc6, 0x0fc6}, // Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda
{0x102d, 0x1030}, // Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu
{0x1032, 0x1037}, // Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below
{0x1039, 0x103a}, // Myanmar Sign Virama ..Myanmar Sign Asat
{0x103d, 0x103e}, // Myanmar Consonant Sign M..Myanmar Consonant Sign M
{0x1058, 0x1059}, // Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal
{0x105e, 0x1060}, // Myanmar Consonant Sign M..Myanmar Consonant Sign M
{0x1071, 0x1074}, // Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah
{0x1082, 0x1082}, // Myanmar Consonant Sign S..Myanmar Consonant Sign S
{0x1085, 0x1086}, // Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan
{0x108d, 0x108d}, // Myanmar Sign Shan Counci..Myanmar Sign Shan Counci
{0x109d, 0x109d}, // Myanmar Vowel Sign Aiton..Myanmar Vowel Sign Aiton
{0x135d, 0x135f}, // Ethiopic Combining Gemin..Ethiopic Combining Gemin
{0x1712, 0x1714}, // Tagalog Vowel Sign I ..Tagalog Sign Virama
{0x1732, 0x1734}, // Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod
{0x1752, 0x1753}, // Buhid Vowel Sign I ..Buhid Vowel Sign U
{0x1772, 0x1773}, // Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U
{0x17b4, 0x17b5}, // Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa
{0x17b7, 0x17bd}, // Khmer Vowel Sign I ..Khmer Vowel Sign Ua
{0x17c6, 0x17c6}, // Khmer Sign Nikahit ..Khmer Sign Nikahit
{0x17c9, 0x17d3}, // Khmer Sign Muusikatoan ..Khmer Sign Bathamasat
{0x17dd, 0x17dd}, // Khmer Sign Atthacan ..Khmer Sign Atthacan
{0x180b, 0x180d}, // Mongolian Free Variation..Mongolian Free Variation
{0x1885, 0x1886}, // Mongolian Letter Ali Gal..Mongolian Letter Ali Gal
{0x18a9, 0x18a9}, // Mongolian Letter Ali Gal..Mongolian Letter Ali Gal
{0x1920, 0x1922}, // Limbu Vowel Sign A ..Limbu Vowel Sign U
{0x1927, 0x1928}, // Limbu Vowel Sign E ..Limbu Vowel Sign O
{0x1932, 0x1932}, // Limbu Small Letter Anusv..Limbu Small Letter Anusv
{0x1939, 0x193b}, // Limbu Sign Mukphreng ..Limbu Sign Sa-i
{0x1a17, 0x1a18}, // Buginese Vowel Sign I ..Buginese Vowel Sign U
{0x1a1b, 0x1a1b}, // Buginese Vowel Sign Ae ..Buginese Vowel Sign Ae
{0x1a56, 0x1a56}, // Tai Tham Consonant Sign ..Tai Tham Consonant Sign
{0x1a58, 0x1a5e}, // Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign
{0x1a60, 0x1a60}, // Tai Tham Sign Sakot ..Tai Tham Sign Sakot
{0x1a62, 0x1a62}, // Tai Tham Vowel Sign Mai ..Tai Tham Vowel Sign Mai
{0x1a65, 0x1a6c}, // Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B
{0x1a73, 0x1a7c}, // Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue
{0x1a7f, 0x1a7f}, // Tai Tham Combining Crypt..Tai Tham Combining Crypt
{0x1ab0, 0x1abe}, // Combining Doubled Circum..Combining Parentheses Ov
{0x1b00, 0x1b03}, // Balinese Sign Ulu Ricem ..Balinese Sign Surang
{0x1b34, 0x1b34}, // Balinese Sign Rerekan ..Balinese Sign Rerekan
{0x1b36, 0x1b3a}, // Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R
{0x1b3c, 0x1b3c}, // Balinese Vowel Sign La L..Balinese Vowel Sign La L
{0x1b42, 0x1b42}, // Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe
{0x1b6b, 0x1b73}, // Balinese Musical Symbol ..Balinese Musical Symbol
{0x1b80, 0x1b81}, // Sundanese Sign Panyecek ..Sundanese Sign Panglayar
{0x1ba2, 0x1ba5}, // Sundanese Consonant Sign..Sundanese Vowel Sign Pan
{0x1ba8, 0x1ba9}, // Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan
{0x1bab, 0x1bad}, // Sundanese Sign Virama ..Sundanese Consonant Sign
{0x1be6, 0x1be6}, // Batak Sign Tompi ..Batak Sign Tompi
{0x1be8, 0x1be9}, // Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee
{0x1bed, 0x1bed}, // Batak Vowel Sign Karo O ..Batak Vowel Sign Karo O
{0x1bef, 0x1bf1}, // Batak Vowel Sign U F|| S..Batak Consonant Sign H
{0x1c2c, 0x1c33}, // Lepcha Vowel Sign E ..Lepcha Consonant Sign T
{0x1c36, 0x1c37}, // Lepcha Sign Ran ..Lepcha Sign Nukta
{0x1cd0, 0x1cd2}, // Vedic Tone Karshana ..Vedic Tone Prenkha
{0x1cd4, 0x1ce0}, // Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash
{0x1ce2, 0x1ce8}, // Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda
{0x1ced, 0x1ced}, // Vedic Sign Tiryak ..Vedic Sign Tiryak
{0x1cf4, 0x1cf4}, // Vedic Tone Candra Above ..Vedic Tone Candra Above
{0x1cf8, 0x1cf9}, // Vedic Tone Ring Above ..Vedic Tone Double Ring A
{0x1dc0, 0x1df5}, // Combining Dotted Grave A..Combining Up Tack Above
{0x1dfb, 0x1dff}, // (nil) ..Combining Right Arrowhea
{0x20d0, 0x20f0}, // Combining Left Harpoon A..Combining Asterisk Above
{0x2cef, 0x2cf1}, // Coptic Combining Ni Abov..Coptic Combining Spiritu
{0x2d7f, 0x2d7f}, // Tifinagh Consonant Joine..Tifinagh Consonant Joine
{0x2de0, 0x2dff}, // Combining Cyrillic Lette..Combining Cyrillic Lette
{0x302a, 0x302d}, // Ideographic Level Tone M..Ideographic Entering Ton
{0x3099, 0x309a}, // Combining Katakana-hirag..Combining Katakana-hirag
{0xa66f, 0xa672}, // Combining Cyrillic Vzmet..Combining Cyrillic Thous
{0xa674, 0xa67d}, // Combining Cyrillic Lette..Combining Cyrillic Payer
{0xa69e, 0xa69f}, // Combining Cyrillic Lette..Combining Cyrillic Lette
{0xa6f0, 0xa6f1}, // Bamum Combining Mark Koq..Bamum Combining Mark Tuk
{0xa802, 0xa802}, // Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva
{0xa806, 0xa806}, // Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant
{0xa80b, 0xa80b}, // Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva
{0xa825, 0xa826}, // Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign
{0xa8c4, 0xa8c5}, // Saurashtra Sign Virama ..
{0xa8e0, 0xa8f1}, // Combining Devanagari Dig..Combining Devanagari Sig
{0xa926, 0xa92d}, // Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop
{0xa947, 0xa951}, // Rejang Vowel Sign I ..Rejang Consonant Sign R
{0xa980, 0xa982}, // Javanese Sign Panyangga ..Javanese Sign Layar
{0xa9b3, 0xa9b3}, // Javanese Sign Cecak Telu..Javanese Sign Cecak Telu
{0xa9b6, 0xa9b9}, // Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku
{0xa9bc, 0xa9bc}, // Javanese Vowel Sign Pepe..Javanese Vowel Sign Pepe
{0xa9e5, 0xa9e5}, // Myanmar Sign Shan Saw ..Myanmar Sign Shan Saw
{0xaa29, 0xaa2e}, // Cham Vowel Sign Aa ..Cham Vowel Sign Oe
{0xaa31, 0xaa32}, // Cham Vowel Sign Au ..Cham Vowel Sign Ue
{0xaa35, 0xaa36}, // Cham Consonant Sign La ..Cham Consonant Sign Wa
{0xaa43, 0xaa43}, // Cham Consonant Sign Fina..Cham Consonant Sign Fina
{0xaa4c, 0xaa4c}, // Cham Consonant Sign Fina..Cham Consonant Sign Fina
{0xaa7c, 0xaa7c}, // Myanmar Sign Tai Laing T..Myanmar Sign Tai Laing T
{0xaab0, 0xaab0}, // Tai Viet Mai Kang ..Tai Viet Mai Kang
{0xaab2, 0xaab4}, // Tai Viet Vowel I ..Tai Viet Vowel U
{0xaab7, 0xaab8}, // Tai Viet Mai Khit ..Tai Viet Vowel Ia
{0xaabe, 0xaabf}, // Tai Viet Vowel Am ..Tai Viet Tone Mai Ek
{0xaac1, 0xaac1}, // Tai Viet Tone Mai Tho ..Tai Viet Tone Mai Tho
{0xaaec, 0xaaed}, // Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign
{0xaaf6, 0xaaf6}, // Meetei Mayek Virama ..Meetei Mayek Virama
{0xabe5, 0xabe5}, // Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign
{0xabe8, 0xabe8}, // Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign
{0xabed, 0xabed}, // Meetei Mayek Apun Iyek ..Meetei Mayek Apun Iyek
{0xfb1e, 0xfb1e}, // Hebrew Point Judeo-spani..Hebrew Point Judeo-spani
{0xfe00, 0xfe0f}, // Variation Select||-1 ..Variation Select||-16
{0xfe20, 0xfe2f}, // Combining Ligature Left ..Combining Cyrillic Titlo
{0x101fd, 0x101fd}, // Phaistos Disc Sign Combi..Phaistos Disc Sign Combi
{0x102e0, 0x102e0}, // Coptic Epact Thousands M..Coptic Epact Thousands M
{0x10376, 0x1037a}, // Combining Old Permic Let..Combining Old Permic Let
{0x10a01, 0x10a03}, // Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo
{0x10a05, 0x10a06}, // Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O
{0x10a0c, 0x10a0f}, // Kharoshthi Vowel Length ..Kharoshthi Sign Visarga
{0x10a38, 0x10a3a}, // Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo
{0x10a3f, 0x10a3f}, // Kharoshthi Virama ..Kharoshthi Virama
{0x10ae5, 0x10ae6}, // Manichaean Abbreviation ..Manichaean Abbreviation
{0x11001, 0x11001}, // Brahmi Sign Anusvara ..Brahmi Sign Anusvara
{0x11038, 0x11046}, // Brahmi Vowel Sign Aa ..Brahmi Virama
{0x1107f, 0x11081}, // Brahmi Number Joiner ..Kaithi Sign Anusvara
{0x110b3, 0x110b6}, // Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai
{0x110b9, 0x110ba}, // Kaithi Sign Virama ..Kaithi Sign Nukta
{0x11100, 0x11102}, // Chakma Sign Candrabindu ..Chakma Sign Visarga
{0x11127, 0x1112b}, // Chakma Vowel Sign A ..Chakma Vowel Sign Uu
{0x1112d, 0x11134}, // Chakma Vowel Sign Ai ..Chakma Maayyaa
{0x11173, 0x11173}, // Mahajani Sign Nukta ..Mahajani Sign Nukta
{0x11180, 0x11181}, // Sharada Sign Candrabindu..Sharada Sign Anusvara
{0x111b6, 0x111be}, // Sharada Vowel Sign U ..Sharada Vowel Sign O
{0x111ca, 0x111cc}, // Sharada Sign Nukta ..Sharada Extra Sh||t Vowe
{0x1122f, 0x11231}, // Khojki Vowel Sign U ..Khojki Vowel Sign Ai
{0x11234, 0x11234}, // Khojki Sign Anusvara ..Khojki Sign Anusvara
{0x11236, 0x11237}, // Khojki Sign Nukta ..Khojki Sign Shadda
{0x1123e, 0x1123e}, // (nil) ..
{0x112df, 0x112df}, // Khudawadi Sign Anusvara ..Khudawadi Sign Anusvara
{0x112e3, 0x112ea}, // Khudawadi Vowel Sign U ..Khudawadi Sign Virama
{0x11300, 0x11301}, // Grantha Sign Combining A..Grantha Sign Candrabindu
{0x1133c, 0x1133c}, // Grantha Sign Nukta ..Grantha Sign Nukta
{0x11340, 0x11340}, // Grantha Vowel Sign Ii ..Grantha Vowel Sign Ii
{0x11366, 0x1136c}, // Combining Grantha Digit ..Combining Grantha Digit
{0x11370, 0x11374}, // Combining Grantha Letter..Combining Grantha Letter
{0x11438, 0x1143f}, // (nil) ..
{0x11442, 0x11444}, // (nil) ..
{0x11446, 0x11446}, // (nil) ..
{0x114b3, 0x114b8}, // Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal
{0x114ba, 0x114ba}, // Tirhuta Vowel Sign Sh||t..Tirhuta Vowel Sign Sh||t
{0x114bf, 0x114c0}, // Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara
{0x114c2, 0x114c3}, // Tirhuta Sign Virama ..Tirhuta Sign Nukta
{0x115b2, 0x115b5}, // Siddham Vowel Sign U ..Siddham Vowel Sign Vocal
{0x115bc, 0x115bd}, // Siddham Sign Candrabindu..Siddham Sign Anusvara
{0x115bf, 0x115c0}, // Siddham Sign Virama ..Siddham Sign Nukta
{0x115dc, 0x115dd}, // Siddham Vowel Sign Alter..Siddham Vowel Sign Alter
{0x11633, 0x1163a}, // Modi Vowel Sign U ..Modi Vowel Sign Ai
{0x1163d, 0x1163d}, // Modi Sign Anusvara ..Modi Sign Anusvara
{0x1163f, 0x11640}, // Modi Sign Virama ..Modi Sign Ardhacandra
{0x116ab, 0x116ab}, // Takri Sign Anusvara ..Takri Sign Anusvara
{0x116ad, 0x116ad}, // Takri Vowel Sign Aa ..Takri Vowel Sign Aa
{0x116b0, 0x116b5}, // Takri Vowel Sign U ..Takri Vowel Sign Au
{0x116b7, 0x116b7}, // Takri Sign Nukta ..Takri Sign Nukta
{0x1171d, 0x1171f}, // Ahom Consonant Sign Medi..Ahom Consonant Sign Medi
{0x11722, 0x11725}, // Ahom Vowel Sign I ..Ahom Vowel Sign Uu
{0x11727, 0x1172b}, // Ahom Vowel Sign Aw ..Ahom Sign Killer
{0x11c30, 0x11c36}, // (nil) ..
{0x11c38, 0x11c3d}, // (nil) ..
{0x11c3f, 0x11c3f}, // (nil) ..
{0x11c92, 0x11ca7}, // (nil) ..
{0x11caa, 0x11cb0}, // (nil) ..
{0x11cb2, 0x11cb3}, // (nil) ..
{0x11cb5, 0x11cb6}, // (nil) ..
{0x16af0, 0x16af4}, // Bassa Vah Combining High..Bassa Vah Combining High
{0x16b30, 0x16b36}, // Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta
{0x16f8f, 0x16f92}, // Miao Tone Right ..Miao Tone Below
{0x1bc9d, 0x1bc9e}, // Duployan Thick Letter Se..Duployan Double Mark
{0x1d167, 0x1d169}, // Musical Symbol Combining..Musical Symbol Combining
{0x1d17b, 0x1d182}, // Musical Symbol Combining..Musical Symbol Combining
{0x1d185, 0x1d18b}, // Musical Symbol Combining..Musical Symbol Combining
{0x1d1aa, 0x1d1ad}, // Musical Symbol Combining..Musical Symbol Combining
{0x1d242, 0x1d244}, // Combining Greek Musical ..Combining Greek Musical
{0x1da00, 0x1da36}, // Signwriting Head Rim ..Signwriting Air Sucking
{0x1da3b, 0x1da6c}, // Signwriting Mouth Closed..Signwriting Excitement
{0x1da75, 0x1da75}, // Signwriting Upper Body T..Signwriting Upper Body T
{0x1da84, 0x1da84}, // Signwriting Location Hea..Signwriting Location Hea
{0x1da9b, 0x1da9f}, // Signwriting Fill Modifie..Signwriting Fill Modifie
{0x1daa1, 0x1daaf}, // Signwriting Rotation Mod..Signwriting Rotation Mod
{0x1e000, 0x1e006}, // (nil) ..
{0x1e008, 0x1e018}, // (nil) ..
{0x1e01b, 0x1e021}, // (nil) ..
{0x1e023, 0x1e024}, // (nil) ..
{0x1e026, 0x1e02a}, // (nil) ..
{0x1e8d0, 0x1e8d6}, // Mende Kikakui Combining ..Mende Kikakui Combining
{0x1e944, 0x1e94a}, // (nil) ..
{0xe0100, 0xe01ef}, // Variation Select||-17 ..Variation Select||-256
};
// https://github.com/jquast/wcwidth/blob/master/wcwidth/table_wide.py
// at commit 0d7de112202cc8b2ebe9232ff4a5c954f19d561a (2016-07-02):
// Original source: EastAsianWidth-9.0.0.txt
static struct interval WIDE_GLYPH[] = {
{0x1100, 0x115f}, // Hangul Choseong Kiyeok ..Hangul Choseong Filler
{0x231a, 0x231b}, // Watch ..Hourglass
{0x2329, 0x232a}, // Left-pointing Angle Brac..Right-pointing Angle Bra
{0x23e9, 0x23ec}, // Black Right-pointing Dou..Black Down-pointing Doub
{0x23f0, 0x23f0}, // Alarm Clock ..Alarm Clock
{0x23f3, 0x23f3}, // Hourglass With Flowing S..Hourglass With Flowing S
{0x25fd, 0x25fe}, // White Medium Small Squar..Black Medium Small Squar
{0x2614, 0x2615}, // Umbrella With Rain Drops..Hot Beverage
{0x2648, 0x2653}, // Aries ..Pisces
{0x267f, 0x267f}, // Wheelchair Symbol ..Wheelchair Symbol
{0x2693, 0x2693}, // Anch|| ..Anch||
{0x26a1, 0x26a1}, // High Voltage Sign ..High Voltage Sign
{0x26aa, 0x26ab}, // Medium White Circle ..Medium Black Circle
{0x26bd, 0x26be}, // Soccer Ball ..Baseball
{0x26c4, 0x26c5}, // Snowman Without Snow ..Sun Behind Cloud
{0x26ce, 0x26ce}, // Ophiuchus ..Ophiuchus
{0x26d4, 0x26d4}, // No Entry ..No Entry
{0x26ea, 0x26ea}, // Church ..Church
{0x26f2, 0x26f3}, // Fountain ..Flag In Hole
{0x26f5, 0x26f5}, // Sailboat ..Sailboat
{0x26fa, 0x26fa}, // Tent ..Tent
{0x26fd, 0x26fd}, // Fuel Pump ..Fuel Pump
{0x2705, 0x2705}, // White Heavy Check Mark ..White Heavy Check Mark
{0x270a, 0x270b}, // Raised Fist ..Raised Hand
{0x2728, 0x2728}, // Sparkles ..Sparkles
{0x274c, 0x274c}, // Cross Mark ..Cross Mark
{0x274e, 0x274e}, // Negative Squared Cross M..Negative Squared Cross M
{0x2753, 0x2755}, // Black Question Mark ||na..White Exclamation Mark O
{0x2757, 0x2757}, // Heavy Exclamation Mark S..Heavy Exclamation Mark S
{0x2795, 0x2797}, // Heavy Plus Sign ..Heavy Division Sign
{0x27b0, 0x27b0}, // Curly Loop ..Curly Loop
{0x27bf, 0x27bf}, // Double Curly Loop ..Double Curly Loop
{0x2b1b, 0x2b1c}, // Black Large Square ..White Large Square
{0x2b50, 0x2b50}, // White Medium Star ..White Medium Star
{0x2b55, 0x2b55}, // Heavy Large Circle ..Heavy Large Circle
{0x2e80, 0x2e99}, // Cjk Radical Repeat ..Cjk Radical Rap
{0x2e9b, 0x2ef3}, // Cjk Radical Choke ..Cjk Radical C-simplified
{0x2f00, 0x2fd5}, // Kangxi Radical One ..Kangxi Radical Flute
{0x2ff0, 0x2ffb}, // Ideographic Description ..Ideographic Description
{0x3000, 0x303e}, // Ideographic Space ..Ideographic Variation In
{0x3041, 0x3096}, // Hiragana Letter Small A ..Hiragana Letter Small Ke
{0x3099, 0x30ff}, // Combining Katakana-hirag..Katakana Digraph Koto
{0x3105, 0x312d}, // Bopomofo Letter B ..Bopomofo Letter Ih
{0x3131, 0x318e}, // Hangul Letter Kiyeok ..Hangul Letter Araeae
{0x3190, 0x31ba}, // Ideographic Annotation L..Bopomofo Letter Zy
{0x31c0, 0x31e3}, // Cjk Stroke T ..Cjk Stroke Q
{0x31f0, 0x321e}, // Katakana Letter Small Ku..Parenthesized K||ean Cha
{0x3220, 0x3247}, // Parenthesized Ideograph ..Circled Ideograph Koto
{0x3250, 0x32fe}, // Partnership Sign ..Circled Katakana Wo
{0x3300, 0x4dbf}, // Square Apaato ..
{0x4e00, 0xa48c}, // Cjk Unified Ideograph-4e..Yi Syllable Yyr
{0xa490, 0xa4c6}, // Yi Radical Qot ..Yi Radical Ke
{0xa960, 0xa97c}, // Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo
{0xac00, 0xd7a3}, // Hangul Syllable Ga ..Hangul Syllable Hih
{0xf900, 0xfaff}, // Cjk Compatibility Ideogr..
{0xfe10, 0xfe19}, // Presentation F||m F|| Ve..Presentation F||m F|| Ve
{0xfe30, 0xfe52}, // Presentation F||m F|| Ve..Small Full Stop
{0xfe54, 0xfe66}, // Small Semicolon ..Small Equals Sign
{0xfe68, 0xfe6b}, // Small Reverse Solidus ..Small Commercial At
{0xff01, 0xff60}, // Fullwidth Exclamation Ma..Fullwidth Right White Pa
{0xffe0, 0xffe6}, // Fullwidth Cent Sign ..Fullwidth Won Sign
{0x16fe0, 0x16fe0}, // (nil) ..
{0x17000, 0x187ec}, // (nil) ..
{0x18800, 0x18af2}, // (nil) ..
{0x1b000, 0x1b001}, // Katakana Letter Archaic ..Hiragana Letter Archaic
{0x1f004, 0x1f004}, // Mahjong Tile Red Dragon ..Mahjong Tile Red Dragon
{0x1f0cf, 0x1f0cf}, // Playing Card Black Joker..Playing Card Black Joker
{0x1f18e, 0x1f18e}, // Negative Squared Ab ..Negative Squared Ab
{0x1f191, 0x1f19a}, // Squared Cl ..Squared Vs
{0x1f200, 0x1f202}, // Square Hiragana Hoka ..Squared Katakana Sa
{0x1f210, 0x1f23b}, // Squared Cjk Unified Ideo..
{0x1f240, 0x1f248}, // T||toise Shell Bracketed..T||toise Shell Bracketed
{0x1f250, 0x1f251}, // Circled Ideograph Advant..Circled Ideograph Accept
{0x1f300, 0x1f320}, // Cyclone ..Shooting Star
{0x1f32d, 0x1f335}, // Hot Dog ..Cactus
{0x1f337, 0x1f37c}, // Tulip ..Baby Bottle
{0x1f37e, 0x1f393}, // Bottle With Popping C||k..Graduation Cap
{0x1f3a0, 0x1f3ca}, // Carousel H||se ..Swimmer
{0x1f3cf, 0x1f3d3}, // Cricket Bat And Ball ..Table Tennis Paddle And
{0x1f3e0, 0x1f3f0}, // House Building ..European Castle
{0x1f3f4, 0x1f3f4}, // Waving Black Flag ..Waving Black Flag
{0x1f3f8, 0x1f43e}, // Badminton Racquet And Sh..Paw Prints
{0x1f440, 0x1f440}, // Eyes ..Eyes
{0x1f442, 0x1f4fc}, // Ear ..Videocassette
{0x1f4ff, 0x1f53d}, // Prayer Beads ..Down-pointing Small Red
{0x1f54b, 0x1f54e}, // Kaaba ..Men||ah With Nine Branch
{0x1f550, 0x1f567}, // Clock Face One Oclock ..Clock Face Twelve-thirty
{0x1f57a, 0x1f57a}, // (nil) ..
{0x1f595, 0x1f596}, // Reversed Hand With Middl..Raised Hand With Part Be
{0x1f5a4, 0x1f5a4}, // (nil) ..
{0x1f5fb, 0x1f64f}, // Mount Fuji ..Person With Folded Hands
{0x1f680, 0x1f6c5}, // Rocket ..Left Luggage
{0x1f6cc, 0x1f6cc}, // Sleeping Accommodation ..Sleeping Accommodation
{0x1f6d0, 0x1f6d2}, // Place Of W||ship ..
{0x1f6eb, 0x1f6ec}, // Airplane Departure ..Airplane Arriving
{0x1f6f4, 0x1f6f6}, // (nil) ..
{0x1f910, 0x1f91e}, // Zipper-mouth Face ..
{0x1f920, 0x1f927}, // (nil) ..
{0x1f930, 0x1f930}, // (nil) ..
{0x1f933, 0x1f93e}, // (nil) ..
{0x1f940, 0x1f94b}, // (nil) ..
{0x1f950, 0x1f95e}, // (nil) ..
{0x1f980, 0x1f991}, // Crab ..
{0x1f9c0, 0x1f9c0}, // Cheese Wedge ..Cheese Wedge
{0x20000, 0x2fffd}, // Cjk Unified Ideograph-20..
{0x30000, 0x3fffd}, // (nil) ..
};
/* test for 8-bit control characters */
if (ucs == 0)
return 0;
if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
return -1;
/* Fast return for latin. */
if (ucs < 0x300) return 1;
/* Binary search in table of non-spacing characters. */
if (bisearch(ucs, combining,
sizeof(combining) / sizeof(struct interval) - 1))
return 0;
/* Other zero-width characters not in table above. */
if ((0x200B <= ucs && ucs <= 0x200F) ||
ucs == 0x2028 ||
ucs == 0x2029 ||
(0x202A <= ucs && ucs <= 0x202E) ||
(0x2060 <= ucs && ucs <= 0x2063))
return 0;
/* If we arrive here, ucs is not a combining or C0/C1 control character */
if (bisearch(ucs, WIDE_GLYPH,
sizeof(WIDE_GLYPH) / sizeof(struct interval) - 1))
return 2;
return 1;
}
static int git_wcwidth(ucs_char_t ch)
{
/*
* 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[] = {
{ 0x0300, 0x0357 }, { 0x035D, 0x036F }, { 0x0483, 0x0486 },
{ 0x0488, 0x0489 }, { 0x0591, 0x05A1 }, { 0x05A3, 0x05B9 },
{ 0x05BB, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 },
{ 0x05C4, 0x05C4 }, { 0x0600, 0x0603 }, { 0x0610, 0x0615 },
{ 0x064B, 0x0658 }, { 0x0670, 0x0670 }, { 0x06D6, 0x06E4 },
{ 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED }, { 0x070F, 0x070F },
{ 0x0711, 0x0711 }, { 0x0730, 0x074A }, { 0x07A6, 0x07B0 },
{ 0x0901, 0x0902 }, { 0x093C, 0x093C }, { 0x0941, 0x0948 },
{ 0x094D, 0x094D }, { 0x0951, 0x0954 }, { 0x0962, 0x0963 },
{ 0x0981, 0x0981 }, { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 },
{ 0x09CD, 0x09CD }, { 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 },
{ 0x0A3C, 0x0A3C }, { 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 },
{ 0x0A4B, 0x0A4D }, { 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 },
{ 0x0ABC, 0x0ABC }, { 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 },
{ 0x0ACD, 0x0ACD }, { 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 },
{ 0x0B3C, 0x0B3C }, { 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 },
{ 0x0B4D, 0x0B4D }, { 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 },
{ 0x0BC0, 0x0BC0 }, { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 },
{ 0x0C46, 0x0C48 }, { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 },
{ 0x0CBC, 0x0CBC }, { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 },
{ 0x0CCC, 0x0CCD }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D },
{ 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
{ 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E },
{ 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC },
{ 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 },
{ 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E },
{ 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 },
{ 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 },
{ 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 },
{ 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x1712, 0x1714 },
{ 0x1732, 0x1734 }, { 0x1752, 0x1753 }, { 0x1772, 0x1773 },
{ 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD }, { 0x17C6, 0x17C6 },
{ 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD }, { 0x180B, 0x180D },
{ 0x18A9, 0x18A9 }, { 0x1920, 0x1922 }, { 0x1927, 0x1928 },
{ 0x1932, 0x1932 }, { 0x1939, 0x193B }, { 0x200B, 0x200F },
{ 0x202A, 0x202E }, { 0x2060, 0x2063 }, { 0x206A, 0x206F },
{ 0x20D0, 0x20EA }, { 0x302A, 0x302F }, { 0x3099, 0x309A },
{ 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F }, { 0xFE20, 0xFE23 },
{ 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB }, { 0x1D167, 0x1D169 },
{ 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B },
{ 0x1D1AA, 0x1D1AD }, { 0xE0001, 0xE0001 },
{ 0xE0020, 0xE007F }, { 0xE0100, 0xE01EF }
};
/* test for 8-bit control characters */
if (ch == 0)
return 0;
if (ch < 32 || (ch >= 0x7f && ch < 0xa0))
return -1;
/* binary search in table of non-spacing characters */
if (bisearch(ch, combining, sizeof(combining)
/ sizeof(struct interval) - 1))
return 0;
/*
* If we arrive here, ch is neither a combining nor a C0/C1
* control character.
*/
return 1 +
(ch >= 0x1100 &&
/* Hangul Jamo init. consonants */
(ch <= 0x115f ||
ch == 0x2329 || ch == 0x232a ||
/* CJK ... Yi */
(ch >= 0x2e80 && ch <= 0xa4cf &&
ch != 0x303f) ||
/* Hangul Syllables */
(ch >= 0xac00 && ch <= 0xd7a3) ||
/* CJK Compatibility Ideographs */
(ch >= 0xf900 && ch <= 0xfaff) ||
/* CJK Compatibility Forms */
(ch >= 0xfe30 && ch <= 0xfe6f) ||
/* Fullwidth Forms */
(ch >= 0xff00 && ch <= 0xff60) ||
(ch >= 0xffe0 && ch <= 0xffe6) ||
(ch >= 0x20000 && ch <= 0x2fffd) ||
(ch >= 0x30000 && ch <= 0x3fffd)));
}
/*
* The following functions are the same as mk_wcwidth() and
* mk_wcwidth_cjk(), except that spacing characters in the East Asian
* Ambiguous (A) category as defined in Unicode Technical Report #11
* have a column width of 2. This variant might be useful for users of
* CJK legacy encodings who want to migrate to UCS without changing
* the traditional terminal character-width behaviour. It is not
* otherwise recommended for general use.
*/
int
mk_wcwidth_cjk(wchar_t ucs)
{
/* sorted list of non-overlapping intervals of East Asian Ambiguous
* characters, generated by
*
* uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf \
* +E000..F8FF \
* +F0000..FFFFD \
* +100000..10FFFD c
*
* "WIDTH-A" is a file extracted from EastAsianWidth.txt by selecting
* only those with width "A", and omitting:
*
* 0xAD
* all lines with "COMBINING"
*
* (uniset does not recognize the range expressions in WIDTH-A).
*/
/* *INDENT-OFF* */
static const struct interval ambiguous[] = {
{ 0x00A1, 0x00A1 }, { 0x00A4, 0x00A4 }, { 0x00A7, 0x00A8 },
{ 0x00AA, 0x00AA }, { 0x00AE, 0x00AE }, { 0x00B0, 0x00B4 },
{ 0x00B6, 0x00BA }, { 0x00BC, 0x00BF }, { 0x00C6, 0x00C6 },
{ 0x00D0, 0x00D0 }, { 0x00D7, 0x00D8 }, { 0x00DE, 0x00E1 },
{ 0x00E6, 0x00E6 }, { 0x00E8, 0x00EA }, { 0x00EC, 0x00ED },
{ 0x00F0, 0x00F0 }, { 0x00F2, 0x00F3 }, { 0x00F7, 0x00FA },
{ 0x00FC, 0x00FC }, { 0x00FE, 0x00FE }, { 0x0101, 0x0101 },
{ 0x0111, 0x0111 }, { 0x0113, 0x0113 }, { 0x011B, 0x011B },
{ 0x0126, 0x0127 }, { 0x012B, 0x012B }, { 0x0131, 0x0133 },
{ 0x0138, 0x0138 }, { 0x013F, 0x0142 }, { 0x0144, 0x0144 },
{ 0x0148, 0x014B }, { 0x014D, 0x014D }, { 0x0152, 0x0153 },
{ 0x0166, 0x0167 }, { 0x016B, 0x016B }, { 0x01CE, 0x01CE },
{ 0x01D0, 0x01D0 }, { 0x01D2, 0x01D2 }, { 0x01D4, 0x01D4 },
{ 0x01D6, 0x01D6 }, { 0x01D8, 0x01D8 }, { 0x01DA, 0x01DA },
{ 0x01DC, 0x01DC }, { 0x0251, 0x0251 }, { 0x0261, 0x0261 },
{ 0x02C4, 0x02C4 }, { 0x02C7, 0x02C7 }, { 0x02C9, 0x02CB },
{ 0x02CD, 0x02CD }, { 0x02D0, 0x02D0 }, { 0x02D8, 0x02DB },
{ 0x02DD, 0x02DD }, { 0x02DF, 0x02DF }, { 0x0391, 0x03A1 },
{ 0x03A3, 0x03A9 }, { 0x03B1, 0x03C1 }, { 0x03C3, 0x03C9 },
{ 0x0401, 0x0401 }, { 0x0410, 0x044F }, { 0x0451, 0x0451 },
{ 0x2010, 0x2010 }, { 0x2013, 0x2016 }, { 0x2018, 0x2019 },
{ 0x201C, 0x201D }, { 0x2020, 0x2022 }, { 0x2024, 0x2027 },
{ 0x2030, 0x2030 }, { 0x2032, 0x2033 }, { 0x2035, 0x2035 },
{ 0x203B, 0x203B }, { 0x203E, 0x203E }, { 0x2074, 0x2074 },
{ 0x207F, 0x207F }, { 0x2081, 0x2084 }, { 0x20AC, 0x20AC },
{ 0x2103, 0x2103 }, { 0x2105, 0x2105 }, { 0x2109, 0x2109 },
{ 0x2113, 0x2113 }, { 0x2116, 0x2116 }, { 0x2121, 0x2122 },
{ 0x2126, 0x2126 }, { 0x212B, 0x212B }, { 0x2153, 0x2154 },
{ 0x215B, 0x215E }, { 0x2160, 0x216B }, { 0x2170, 0x2179 },
{ 0x2190, 0x2199 }, { 0x21B8, 0x21B9 }, { 0x21D2, 0x21D2 },
{ 0x21D4, 0x21D4 }, { 0x21E7, 0x21E7 }, { 0x2200, 0x2200 },
{ 0x2202, 0x2203 }, { 0x2207, 0x2208 }, { 0x220B, 0x220B },
{ 0x220F, 0x220F }, { 0x2211, 0x2211 }, { 0x2215, 0x2215 },
{ 0x221A, 0x221A }, { 0x221D, 0x2220 }, { 0x2223, 0x2223 },
{ 0x2225, 0x2225 }, { 0x2227, 0x222C }, { 0x222E, 0x222E },
{ 0x2234, 0x2237 }, { 0x223C, 0x223D }, { 0x2248, 0x2248 },
{ 0x224C, 0x224C }, { 0x2252, 0x2252 }, { 0x2260, 0x2261 },
{ 0x2264, 0x2267 }, { 0x226A, 0x226B }, { 0x226E, 0x226F },
{ 0x2282, 0x2283 }, { 0x2286, 0x2287 }, { 0x2295, 0x2295 },
{ 0x2299, 0x2299 }, { 0x22A5, 0x22A5 }, { 0x22BF, 0x22BF },
{ 0x2312, 0x2312 }, { 0x2460, 0x24E9 }, { 0x24EB, 0x254B },
{ 0x2550, 0x2573 }, { 0x2580, 0x258F }, { 0x2592, 0x2595 },
{ 0x25A0, 0x25A1 }, { 0x25A3, 0x25A9 }, { 0x25B2, 0x25B3 },
{ 0x25B6, 0x25B7 }, { 0x25BC, 0x25BD }, { 0x25C0, 0x25C1 },
{ 0x25C6, 0x25C8 }, { 0x25CB, 0x25CB }, { 0x25CE, 0x25D1 },
{ 0x25E2, 0x25E5 }, { 0x25EF, 0x25EF }, { 0x2605, 0x2606 },
{ 0x2609, 0x2609 }, { 0x260E, 0x260F }, { 0x2614, 0x2615 },
{ 0x261C, 0x261C }, { 0x261E, 0x261E }, { 0x2640, 0x2640 },
{ 0x2642, 0x2642 }, { 0x2660, 0x2661 }, { 0x2663, 0x2665 },
{ 0x2667, 0x266A }, { 0x266C, 0x266D }, { 0x266F, 0x266F },
{ 0x273D, 0x273D }, { 0x2776, 0x277F }, { 0xE000, 0xF8FF },
{ 0xFFFD, 0xFFFD }, { 0xF0000, 0xFFFFD }, { 0x100000, 0x10FFFD }
};
/* *INDENT-ON* */
/* binary search in table of non-spacing characters */
if (bisearch((unsigned long) ucs, ambiguous,
(int) (sizeof(ambiguous) / sizeof(struct interval) - 1)))
return 2;
return mk_wcwidth(ucs);
}
int wcwidth(wchar_t ucs)
{
/* sorted list of non-overlapping intervals of non-spacing characters */
static const struct interval combining[] = {
{ 0x0300, 0x034E }, { 0x0360, 0x0362 }, { 0x0483, 0x0486 },
{ 0x0488, 0x0489 }, { 0x0591, 0x05A1 }, { 0x05A3, 0x05B9 },
{ 0x05BB, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 },
{ 0x05C4, 0x05C4 }, { 0x064B, 0x0655 }, { 0x0670, 0x0670 },
{ 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED },
{ 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A },
{ 0x07A6, 0x07B0 }, { 0x0901, 0x0902 }, { 0x093C, 0x093C },
{ 0x0941, 0x0948 }, { 0x094D, 0x094D }, { 0x0951, 0x0954 },
{ 0x0962, 0x0963 }, { 0x0981, 0x0981 }, { 0x09BC, 0x09BC },
{ 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD }, { 0x09E2, 0x09E3 },
{ 0x0A02, 0x0A02 }, { 0x0A3C, 0x0A3C }, { 0x0A41, 0x0A42 },
{ 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D }, { 0x0A70, 0x0A71 },
{ 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC }, { 0x0AC1, 0x0AC5 },
{ 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD }, { 0x0B01, 0x0B01 },
{ 0x0B3C, 0x0B3C }, { 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 },
{ 0x0B4D, 0x0B4D }, { 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 },
{ 0x0BC0, 0x0BC0 }, { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 },
{ 0x0C46, 0x0C48 }, { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 },
{ 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD },
{ 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D }, { 0x0DCA, 0x0DCA },
{ 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 }, { 0x0E31, 0x0E31 },
{ 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E }, { 0x0EB1, 0x0EB1 },
{ 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC }, { 0x0EC8, 0x0ECD },
{ 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 }, { 0x0F37, 0x0F37 },
{ 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E }, { 0x0F80, 0x0F84 },
{ 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 }, { 0x0F99, 0x0FBC },
{ 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 }, { 0x1032, 0x1032 },
{ 0x1036, 0x1037 }, { 0x1039, 0x1039 }, { 0x1058, 0x1059 },
{ 0x1160, 0x11FF }, { 0x17B7, 0x17BD }, { 0x17C6, 0x17C6 },
{ 0x17C9, 0x17D3 }, { 0x180B, 0x180E }, { 0x18A9, 0x18A9 },
{ 0x200B, 0x200F }, { 0x202A, 0x202E }, { 0x206A, 0x206F },
{ 0x20D0, 0x20E3 }, { 0x302A, 0x302F }, { 0x3099, 0x309A },
{ 0xFB1E, 0xFB1E }, { 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF },
{ 0xFFF9, 0xFFFB }
};
/* test for 8-bit control characters */
if (ucs == 0)
return 0;
if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
return -1;
/* binary search in table of non-spacing characters */
if (bisearch(ucs, combining,
sizeof(combining) / sizeof(struct interval) - 1))
return 0;
/* if we arrive here, ucs is not a combining or C0/C1 control character */
return 1 +
(ucs >= 0x1100 &&
(ucs <= 0x115f || /* Hangul Jamo init. consonants */
(ucs >= 0x2e80 && ucs <= 0xa4cf && (ucs & ~0x0011) != 0x300a &&
ucs != 0x303f) || /* CJK ... Yi */
(ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
(ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
(ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
(ucs >= 0xff00 && ucs <= 0xff5f) || /* Fullwidth Forms */
(ucs >= 0xffe0 && ucs <= 0xffe6) ||
(ucs >= 0x20000 && ucs <= 0x2ffff)));
}
int inSet(int s)
{
return bisearch(set,s,0,count-1);
}
int TBL::getindex(char* word)
{
// char -> index
return bisearch(word);
}
int wcwidth_cjk(wchar_t ucs)
{
/* sorted list of non-overlapping intervals of East Asian Ambiguous
* characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */
static const struct interval ambiguous[] = {
{ 0x00a1, 0x00a1 }, { 0x00a4, 0x00a4 }, { 0x00a7, 0x00a8 },
{ 0x00aa, 0x00aa }, { 0x00ae, 0x00ae }, { 0x00b0, 0x00b4 },
{ 0x00b6, 0x00ba }, { 0x00bc, 0x00bf }, { 0x00c6, 0x00c6 },
{ 0x00d0, 0x00d0 }, { 0x00d7, 0x00d8 }, { 0x00de, 0x00e1 },
{ 0x00e6, 0x00e6 }, { 0x00e8, 0x00ea }, { 0x00ec, 0x00ed },
{ 0x00f0, 0x00f0 }, { 0x00f2, 0x00f3 }, { 0x00f7, 0x00fa },
{ 0x00fc, 0x00fc }, { 0x00fe, 0x00fe }, { 0x0101, 0x0101 },
{ 0x0111, 0x0111 }, { 0x0113, 0x0113 }, { 0x011b, 0x011b },
{ 0x0126, 0x0127 }, { 0x012b, 0x012b }, { 0x0131, 0x0133 },
{ 0x0138, 0x0138 }, { 0x013f, 0x0142 }, { 0x0144, 0x0144 },
{ 0x0148, 0x014b }, { 0x014d, 0x014d }, { 0x0152, 0x0153 },
{ 0x0166, 0x0167 }, { 0x016b, 0x016b }, { 0x01ce, 0x01ce },
{ 0x01d0, 0x01d0 }, { 0x01d2, 0x01d2 }, { 0x01d4, 0x01d4 },
{ 0x01d6, 0x01d6 }, { 0x01d8, 0x01d8 }, { 0x01da, 0x01da },
{ 0x01dc, 0x01dc }, { 0x0251, 0x0251 }, { 0x0261, 0x0261 },
{ 0x02c4, 0x02c4 }, { 0x02c7, 0x02c7 }, { 0x02c9, 0x02cb },
{ 0x02cd, 0x02cd }, { 0x02d0, 0x02d0 }, { 0x02d8, 0x02db },
{ 0x02dd, 0x02dd }, { 0x02df, 0x02df }, { 0x0391, 0x03a1 },
{ 0x03a3, 0x03a9 }, { 0x03b1, 0x03c1 }, { 0x03c3, 0x03c9 },
{ 0x0401, 0x0401 }, { 0x0410, 0x044f }, { 0x0451, 0x0451 },
{ 0x2010, 0x2010 }, { 0x2013, 0x2016 }, { 0x2018, 0x2019 },
{ 0x201c, 0x201d }, { 0x2020, 0x2022 }, { 0x2024, 0x2027 },
{ 0x2030, 0x2030 }, { 0x2032, 0x2033 }, { 0x2035, 0x2035 },
{ 0x203b, 0x203b }, { 0x203e, 0x203e }, { 0x2074, 0x2074 },
{ 0x207f, 0x207f }, { 0x2081, 0x2084 }, { 0x20ac, 0x20ac },
{ 0x2103, 0x2103 }, { 0x2105, 0x2105 }, { 0x2109, 0x2109 },
{ 0x2113, 0x2113 }, { 0x2116, 0x2116 }, { 0x2121, 0x2122 },
{ 0x2126, 0x2126 }, { 0x212b, 0x212b }, { 0x2153, 0x2154 },
{ 0x215b, 0x215e }, { 0x2160, 0x216b }, { 0x2170, 0x2179 },
{ 0x2190, 0x2199 }, { 0x21b8, 0x21b9 }, { 0x21d2, 0x21d2 },
{ 0x21d4, 0x21d4 }, { 0x21e7, 0x21e7 }, { 0x2200, 0x2200 },
{ 0x2202, 0x2203 }, { 0x2207, 0x2208 }, { 0x220b, 0x220b },
{ 0x220f, 0x220f }, { 0x2211, 0x2211 }, { 0x2215, 0x2215 },
{ 0x221a, 0x221a }, { 0x221d, 0x2220 }, { 0x2223, 0x2223 },
{ 0x2225, 0x2225 }, { 0x2227, 0x222c }, { 0x222e, 0x222e },
{ 0x2234, 0x2237 }, { 0x223c, 0x223d }, { 0x2248, 0x2248 },
{ 0x224c, 0x224c }, { 0x2252, 0x2252 }, { 0x2260, 0x2261 },
{ 0x2264, 0x2267 }, { 0x226a, 0x226b }, { 0x226e, 0x226f },
{ 0x2282, 0x2283 }, { 0x2286, 0x2287 }, { 0x2295, 0x2295 },
{ 0x2299, 0x2299 }, { 0x22a5, 0x22a5 }, { 0x22bf, 0x22bf },
{ 0x2312, 0x2312 }, { 0x2460, 0x24e9 }, { 0x24eb, 0x254b },
{ 0x2550, 0x2573 }, { 0x2580, 0x258f }, { 0x2592, 0x2595 },
{ 0x25a0, 0x25a1 }, { 0x25a3, 0x25a9 }, { 0x25b2, 0x25b3 },
{ 0x25b6, 0x25b7 }, { 0x25bc, 0x25bd }, { 0x25c0, 0x25c1 },
{ 0x25c6, 0x25c8 }, { 0x25cb, 0x25cb }, { 0x25ce, 0x25d1 },
{ 0x25e2, 0x25e5 }, { 0x25ef, 0x25ef }, { 0x2605, 0x2606 },
{ 0x2609, 0x2609 }, { 0x260e, 0x260f }, { 0x2614, 0x2615 },
{ 0x261c, 0x261c }, { 0x261e, 0x261e }, { 0x2640, 0x2640 },
{ 0x2642, 0x2642 }, { 0x2660, 0x2661 }, { 0x2663, 0x2665 },
{ 0x2667, 0x266a }, { 0x266c, 0x266d }, { 0x266f, 0x266f },
{ 0x273d, 0x273d }, { 0x2776, 0x277f }, { 0xe000, 0xf8ff },
{ 0xfffd, 0xfffd }, { 0xf0000, 0xffffd }, { 0x100000, 0x10fffd }
};
#ifdef JA_LEGACY
/* For Japanese legacy encodings, the following characters are added. */
static const struct interval legacy_ja[] = {
{ 0x00A2, 0x00A3 }, { 0x00A5, 0x00A6 }, { 0x00AC, 0x00AC },
{ 0x00AF, 0x00AF }, { 0x2212, 0x2212 }
};
#endif /* JA_LEGACY */
/* binary search in table of non-spacing characters */
if (bisearch(ucs, ambiguous,
sizeof(ambiguous) / sizeof(struct interval) - 1))
return 2;
#ifdef JA_LEGACY
if (bisearch(ucs, legacy_ja,
sizeof(legacy_ja) / sizeof(struct interval) - 1))
return 2;
#endif /* JA_LEGACY */
return wcwidth_ucs(ucs);
}
int mk_wcwidth(wchar_t ucs)
{
/* 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[] = {
{ 0x0300, 0x036F }, { 0x0483, 0x0486 }, { 0x0488, 0x0489 },
{ 0x0591, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 },
{ 0x05C4, 0x05C5 }, { 0x05C7, 0x05C7 }, { 0x0600, 0x0603 },
{ 0x0610, 0x0615 }, { 0x064B, 0x065E }, { 0x0670, 0x0670 },
{ 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED },
{ 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A },
{ 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x0901, 0x0902 },
{ 0x093C, 0x093C }, { 0x0941, 0x0948 }, { 0x094D, 0x094D },
{ 0x0951, 0x0954 }, { 0x0962, 0x0963 }, { 0x0981, 0x0981 },
{ 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD },
{ 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 }, { 0x0A3C, 0x0A3C },
{ 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D },
{ 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC },
{ 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD },
{ 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 }, { 0x0B3C, 0x0B3C },
{ 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 }, { 0x0B4D, 0x0B4D },
{ 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 }, { 0x0BC0, 0x0BC0 },
{ 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 },
{ 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 }, { 0x0CBC, 0x0CBC },
{ 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD },
{ 0x0CE2, 0x0CE3 }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D },
{ 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
{ 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E },
{ 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC },
{ 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 },
{ 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E },
{ 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 },
{ 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 },
{ 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 },
{ 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x135F, 0x135F },
{ 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 },
{ 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD },
{ 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD },
{ 0x180B, 0x180D }, { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 },
{ 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193B },
{ 0x1A17, 0x1A18 }, { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 },
{ 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C }, { 0x1B42, 0x1B42 },
{ 0x1B6B, 0x1B73 }, { 0x1DC0, 0x1DCA }, { 0x1DFE, 0x1DFF },
{ 0x200B, 0x200F }, { 0x202A, 0x202E }, { 0x2060, 0x2063 },
{ 0x206A, 0x206F }, { 0x20D0, 0x20EF }, { 0x302A, 0x302F },
{ 0x3099, 0x309A }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B },
{ 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F },
{ 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB },
{ 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F },
{ 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x1D167, 0x1D169 },
{ 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD },
{ 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 }, { 0xE0020, 0xE007F },
{ 0xE0100, 0xE01EF }
};
/* test for 8-bit control characters */
if (ucs == 0)
return 0;
if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
return -1;
/* binary search in table of non-spacing characters */
if (bisearch(ucs, combining,
sizeof(combining) / sizeof(struct interval) - 1))
return 0;
/* if we arrive here, ucs is not a combining or C0/C1 control character */
return 1 +
(ucs >= 0x1100 &&
(ucs <= 0x115f || /* Hangul Jamo init. consonants */
ucs == 0x2329 || ucs == 0x232a ||
(ucs >= 0x2e80 && ucs <= 0xa4cf &&
ucs != 0x303f) || /* CJK ... Yi */
(ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
(ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
(ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */
(ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
(ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
(ucs >= 0xffe0 && ucs <= 0xffe6) ||
(ucs >= 0x20000 && ucs <= 0x2fffd) ||
(ucs >= 0x30000 && ucs <= 0x3fffd)));
}
int mk_wcwidth(wchar_t ucs)
{
/* sorted list of non-overlapping intervals of non-spacing characters */
/* generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" */
/* "uniset cat:Me + cat:Mn + cat:Cf - U+00AD + U+1160..U+11FF + U+200B" */
static const struct interval combining[] = {
{ 0x0300, 0x036F }, { 0x0483, 0x0489 }, { 0x0591, 0x05BD },
{ 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, { 0x05C4, 0x05C5 },
{ 0x05C7, 0x05C7 }, { 0x0600, 0x0604 }, { 0x0610, 0x061A },
{ 0x064B, 0x065F }, { 0x0670, 0x0670 }, { 0x06D6, 0x06DD },
{ 0x06DF, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED },
{ 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A },
{ 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x0816, 0x0819 },
{ 0x081B, 0x0823 }, { 0x0825, 0x0827 }, { 0x0829, 0x082D },
{ 0x0859, 0x085B }, { 0x08E4, 0x08FE }, { 0x0900, 0x0902 },
{ 0x093A, 0x093A }, { 0x093C, 0x093C }, { 0x0941, 0x0948 },
{ 0x094D, 0x094D }, { 0x0951, 0x0957 }, { 0x0962, 0x0963 },
{ 0x0981, 0x0981 }, { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 },
{ 0x09CD, 0x09CD }, { 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 },
{ 0x0A3C, 0x0A3C }, { 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 },
{ 0x0A4B, 0x0A4D }, { 0x0A51, 0x0A51 }, { 0x0A70, 0x0A71 },
{ 0x0A75, 0x0A75 }, { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC },
{ 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD },
{ 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 }, { 0x0B3C, 0x0B3C },
{ 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B44 }, { 0x0B4D, 0x0B4D },
{ 0x0B56, 0x0B56 }, { 0x0B62, 0x0B63 }, { 0x0B82, 0x0B82 },
{ 0x0BC0, 0x0BC0 }, { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 },
{ 0x0C46, 0x0C48 }, { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 },
{ 0x0C62, 0x0C63 }, { 0x0CBC, 0x0CBC }, { 0x0CBF, 0x0CBF },
{ 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD }, { 0x0CE2, 0x0CE3 },
{ 0x0D41, 0x0D44 }, { 0x0D4D, 0x0D4D }, { 0x0D62, 0x0D63 },
{ 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
{ 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E },
{ 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC },
{ 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 },
{ 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E },
{ 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F8D, 0x0F97 },
{ 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 },
{ 0x1032, 0x1037 }, { 0x1039, 0x103A }, { 0x103D, 0x103E },
{ 0x1058, 0x1059 }, { 0x105E, 0x1060 }, { 0x1071, 0x1074 },
{ 0x1082, 0x1082 }, { 0x1085, 0x1086 }, { 0x108D, 0x108D },
{ 0x109D, 0x109D }, { 0x1160, 0x11FF }, { 0x135D, 0x135F },
{ 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 },
{ 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD },
{ 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD },
{ 0x180B, 0x180D }, { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 },
{ 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193B },
{ 0x1A17, 0x1A18 }, { 0x1A56, 0x1A56 }, { 0x1A58, 0x1A5E },
{ 0x1A60, 0x1A60 }, { 0x1A62, 0x1A62 }, { 0x1A65, 0x1A6C },
{ 0x1A73, 0x1A7C }, { 0x1A7F, 0x1A7F }, { 0x1B00, 0x1B03 },
{ 0x1B34, 0x1B34 }, { 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C },
{ 0x1B42, 0x1B42 }, { 0x1B6B, 0x1B73 }, { 0x1B80, 0x1B81 },
{ 0x1BA2, 0x1BA5 }, { 0x1BA8, 0x1BA9 }, { 0x1BAB, 0x1BAB },
{ 0x1BE6, 0x1BE6 }, { 0x1BE8, 0x1BE9 }, { 0x1BED, 0x1BED },
{ 0x1BEF, 0x1BF1 }, { 0x1C2C, 0x1C33 }, { 0x1C36, 0x1C37 },
{ 0x1CD0, 0x1CD2 }, { 0x1CD4, 0x1CE0 }, { 0x1CE2, 0x1CE8 },
{ 0x1CED, 0x1CED }, { 0x1CF4, 0x1CF4 }, { 0x1DC0, 0x1DE6 },
{ 0x1DFC, 0x1DFF }, { 0x200B, 0x200F }, { 0x202A, 0x202E },
{ 0x2060, 0x2064 }, { 0x206A, 0x206F }, { 0x20D0, 0x20F0 },
{ 0x2CEF, 0x2CF1 }, { 0x2D7F, 0x2D7F }, { 0x2DE0, 0x2DFF },
{ 0x302A, 0x302D }, { 0x3099, 0x309A }, { 0xA66F, 0xA672 },
{ 0xA674, 0xA67D }, { 0xA69F, 0xA69F }, { 0xA6F0, 0xA6F1 },
{ 0xA802, 0xA802 }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B },
{ 0xA825, 0xA826 }, { 0xA8C4, 0xA8C4 }, { 0xA8E0, 0xA8F1 },
{ 0xA926, 0xA92D }, { 0xA947, 0xA951 }, { 0xA980, 0xA982 },
{ 0xA9B3, 0xA9B3 }, { 0xA9B6, 0xA9B9 }, { 0xA9BC, 0xA9BC },
{ 0xAA29, 0xAA2E }, { 0xAA31, 0xAA32 }, { 0xAA35, 0xAA36 },
{ 0xAA43, 0xAA43 }, { 0xAA4C, 0xAA4C }, { 0xAAB0, 0xAAB0 },
{ 0xAAB2, 0xAAB4 }, { 0xAAB7, 0xAAB8 }, { 0xAABE, 0xAABF },
{ 0xAAC1, 0xAAC1 }, { 0xAAEC, 0xAAED }, { 0xAAF6, 0xAAF6 },
{ 0xABE5, 0xABE5 }, { 0xABE8, 0xABE8 }, { 0xABED, 0xABED },
{ 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F }, { 0xFE20, 0xFE26 },
{ 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB }, { 0x101FD, 0x101FD },
{ 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F },
{ 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x11001, 0x11001 },
{ 0x11038, 0x11046 }, { 0x11080, 0x11081 }, { 0x110B3, 0x110B6 },
{ 0x110B9, 0x110BA }, { 0x110BD, 0x110BD }, { 0x11100, 0x11102 },
{ 0x11127, 0x1112B }, { 0x1112D, 0x11134 }, { 0x11180, 0x11181 },
{ 0x111B6, 0x111BE }, { 0x116AB, 0x116AB }, { 0x116AD, 0x116AD },
{ 0x116B0, 0x116B5 }, { 0x116B7, 0x116B7 }, { 0x16F8F, 0x16F92 },
{ 0x1D167, 0x1D169 }, { 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B },
{ 0x1D1AA, 0x1D1AD }, { 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 },
{ 0xE0020, 0xE007F }, { 0xE0100, 0xE01EF },
};
/* test for 8-bit control characters */
if (ucs == 0)
return 0;
if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
return -1;
/* binary search in table of non-spacing characters */
if (bisearch(ucs, combining,
sizeof(combining) / sizeof(struct interval) - 1))
return 0;
/* if we arrive here, ucs is not a combining or C0/C1 control character */
return 1 +
(ucs >= 0x1100 &&
(ucs <= 0x115f || /* Hangul Jamo init. consonants */
ucs == 0x2329 || ucs == 0x232a ||
(ucs >= 0x2e80 && ucs <= 0xa4cf &&
ucs != 0x303f) || /* CJK ... Yi */
(ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
(ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
(ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */
(ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
(ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
(ucs >= 0xffe0 && ucs <= 0xffe6)
#ifndef CYGWIN
||
(ucs >= 0x20000 && ucs <= 0x2fffd) ||
(ucs >= 0x30000 && ucs <= 0x3fffd)
#endif
)
);
}
int __wcwidth(__CONST wint_t ucs)
{
#ifdef _MB_CAPABLE
/* sorted list of non-overlapping intervals of East Asian Ambiguous
* characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */
static const struct interval ambiguous[] = {
{ 0x00A1, 0x00A1 }, { 0x00A4, 0x00A4 }, { 0x00A7, 0x00A8 },
{ 0x00AA, 0x00AA }, { 0x00AE, 0x00AE }, { 0x00B0, 0x00B4 },
{ 0x00B6, 0x00BA }, { 0x00BC, 0x00BF }, { 0x00C6, 0x00C6 },
{ 0x00D0, 0x00D0 }, { 0x00D7, 0x00D8 }, { 0x00DE, 0x00E1 },
{ 0x00E6, 0x00E6 }, { 0x00E8, 0x00EA }, { 0x00EC, 0x00ED },
{ 0x00F0, 0x00F0 }, { 0x00F2, 0x00F3 }, { 0x00F7, 0x00FA },
{ 0x00FC, 0x00FC }, { 0x00FE, 0x00FE }, { 0x0101, 0x0101 },
{ 0x0111, 0x0111 }, { 0x0113, 0x0113 }, { 0x011B, 0x011B },
{ 0x0126, 0x0127 }, { 0x012B, 0x012B }, { 0x0131, 0x0133 },
{ 0x0138, 0x0138 }, { 0x013F, 0x0142 }, { 0x0144, 0x0144 },
{ 0x0148, 0x014B }, { 0x014D, 0x014D }, { 0x0152, 0x0153 },
{ 0x0166, 0x0167 }, { 0x016B, 0x016B }, { 0x01CE, 0x01CE },
{ 0x01D0, 0x01D0 }, { 0x01D2, 0x01D2 }, { 0x01D4, 0x01D4 },
{ 0x01D6, 0x01D6 }, { 0x01D8, 0x01D8 }, { 0x01DA, 0x01DA },
{ 0x01DC, 0x01DC }, { 0x0251, 0x0251 }, { 0x0261, 0x0261 },
{ 0x02C4, 0x02C4 }, { 0x02C7, 0x02C7 }, { 0x02C9, 0x02CB },
{ 0x02CD, 0x02CD }, { 0x02D0, 0x02D0 }, { 0x02D8, 0x02DB },
{ 0x02DD, 0x02DD }, { 0x02DF, 0x02DF }, { 0x0391, 0x03A1 },
{ 0x03A3, 0x03A9 }, { 0x03B1, 0x03C1 }, { 0x03C3, 0x03C9 },
{ 0x0401, 0x0401 }, { 0x0410, 0x044F }, { 0x0451, 0x0451 },
{ 0x2010, 0x2010 }, { 0x2013, 0x2016 }, { 0x2018, 0x2019 },
{ 0x201C, 0x201D }, { 0x2020, 0x2022 }, { 0x2024, 0x2027 },
{ 0x2030, 0x2030 }, { 0x2032, 0x2033 }, { 0x2035, 0x2035 },
{ 0x203B, 0x203B }, { 0x203E, 0x203E }, { 0x2074, 0x2074 },
{ 0x207F, 0x207F }, { 0x2081, 0x2084 }, { 0x20AC, 0x20AC },
{ 0x2103, 0x2103 }, { 0x2105, 0x2105 }, { 0x2109, 0x2109 },
{ 0x2113, 0x2113 }, { 0x2116, 0x2116 }, { 0x2121, 0x2122 },
{ 0x2126, 0x2126 }, { 0x212B, 0x212B }, { 0x2153, 0x2154 },
{ 0x215B, 0x215E }, { 0x2160, 0x216B }, { 0x2170, 0x2179 },
{ 0x2190, 0x2199 }, { 0x21B8, 0x21B9 }, { 0x21D2, 0x21D2 },
{ 0x21D4, 0x21D4 }, { 0x21E7, 0x21E7 }, { 0x2200, 0x2200 },
{ 0x2202, 0x2203 }, { 0x2207, 0x2208 }, { 0x220B, 0x220B },
{ 0x220F, 0x220F }, { 0x2211, 0x2211 }, { 0x2215, 0x2215 },
{ 0x221A, 0x221A }, { 0x221D, 0x2220 }, { 0x2223, 0x2223 },
{ 0x2225, 0x2225 }, { 0x2227, 0x222C }, { 0x222E, 0x222E },
{ 0x2234, 0x2237 }, { 0x223C, 0x223D }, { 0x2248, 0x2248 },
{ 0x224C, 0x224C }, { 0x2252, 0x2252 }, { 0x2260, 0x2261 },
{ 0x2264, 0x2267 }, { 0x226A, 0x226B }, { 0x226E, 0x226F },
{ 0x2282, 0x2283 }, { 0x2286, 0x2287 }, { 0x2295, 0x2295 },
{ 0x2299, 0x2299 }, { 0x22A5, 0x22A5 }, { 0x22BF, 0x22BF },
{ 0x2312, 0x2312 }, { 0x2460, 0x24E9 }, { 0x24EB, 0x254B },
{ 0x2550, 0x2573 }, { 0x2580, 0x258F }, { 0x2592, 0x2595 },
{ 0x25A0, 0x25A1 }, { 0x25A3, 0x25A9 }, { 0x25B2, 0x25B3 },
{ 0x25B6, 0x25B7 }, { 0x25BC, 0x25BD }, { 0x25C0, 0x25C1 },
{ 0x25C6, 0x25C8 }, { 0x25CB, 0x25CB }, { 0x25CE, 0x25D1 },
{ 0x25E2, 0x25E5 }, { 0x25EF, 0x25EF }, { 0x2605, 0x2606 },
{ 0x2609, 0x2609 }, { 0x260E, 0x260F }, { 0x2614, 0x2615 },
{ 0x261C, 0x261C }, { 0x261E, 0x261E }, { 0x2640, 0x2640 },
{ 0x2642, 0x2642 }, { 0x2660, 0x2661 }, { 0x2663, 0x2665 },
{ 0x2667, 0x266A }, { 0x266C, 0x266D }, { 0x266F, 0x266F },
{ 0x273D, 0x273D }, { 0x2776, 0x277F }, { 0xE000, 0xF8FF },
{ 0xFFFD, 0xFFFD }, { 0xF0000, 0xFFFFD }, { 0x100000, 0x10FFFD }
};
/* 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[] = {
{ 0x0300, 0x036F }, { 0x0483, 0x0486 }, { 0x0488, 0x0489 },
{ 0x0591, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 },
{ 0x05C4, 0x05C5 }, { 0x05C7, 0x05C7 }, { 0x0600, 0x0603 },
{ 0x0610, 0x0615 }, { 0x064B, 0x065E }, { 0x0670, 0x0670 },
{ 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED },
{ 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A },
{ 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x0901, 0x0902 },
{ 0x093C, 0x093C }, { 0x0941, 0x0948 }, { 0x094D, 0x094D },
{ 0x0951, 0x0954 }, { 0x0962, 0x0963 }, { 0x0981, 0x0981 },
{ 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD },
{ 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 }, { 0x0A3C, 0x0A3C },
{ 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D },
{ 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC },
{ 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD },
{ 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 }, { 0x0B3C, 0x0B3C },
{ 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 }, { 0x0B4D, 0x0B4D },
{ 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 }, { 0x0BC0, 0x0BC0 },
{ 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 },
{ 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 }, { 0x0CBC, 0x0CBC },
{ 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD },
{ 0x0CE2, 0x0CE3 }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D },
{ 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
{ 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E },
{ 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC },
{ 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 },
{ 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E },
{ 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 },
{ 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 },
{ 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 },
{ 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x135F, 0x135F },
{ 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 },
{ 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD },
{ 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD },
{ 0x180B, 0x180D }, { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 },
{ 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193B },
{ 0x1A17, 0x1A18 }, { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 },
{ 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C }, { 0x1B42, 0x1B42 },
{ 0x1B6B, 0x1B73 }, { 0x1DC0, 0x1DCA }, { 0x1DFE, 0x1DFF },
{ 0x200B, 0x200F }, { 0x202A, 0x202E }, { 0x2060, 0x2063 },
{ 0x206A, 0x206F }, { 0x20D0, 0x20EF }, { 0x302A, 0x302F },
{ 0x3099, 0x309A }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B },
{ 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F },
{ 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB },
{ 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F },
{ 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x1D167, 0x1D169 },
{ 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD },
{ 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 }, { 0xE0020, 0xE007F },
{ 0xE0100, 0xE01EF }
};
/* Test for NUL character */
if (ucs == 0)
return 0;
/* Test for printable ASCII characters */
if (ucs >= 0x20 && ucs < 0x7f)
return 1;
/* Test for control characters */
if (ucs < 0xa0)
return -1;
/* Test for surrogate pair values. */
if (ucs >= 0xd800 && ucs <= 0xdfff)
return -1;
/* binary search in table of ambiguous characters */
if (__locale_cjk_lang ()
&& bisearch(ucs, ambiguous,
sizeof(ambiguous) / sizeof(struct interval) - 1))
return 2;
/* binary search in table of non-spacing characters */
if (bisearch(ucs, combining,
sizeof(combining) / sizeof(struct interval) - 1))
return 0;
/* if we arrive here, ucs is not a combining or C0/C1 control character */
return 1 +
(ucs >= 0x1100 &&
(ucs <= 0x115f || /* Hangul Jamo init. consonants */
ucs == 0x2329 || ucs == 0x232a ||
(ucs >= 0x2e80 && ucs <= 0xa4cf &&
ucs != 0x303f) || /* CJK ... Yi */
(ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
(ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
(ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */
(ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
(ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
(ucs >= 0xffe0 && ucs <= 0xffe6) ||
(ucs >= 0x20000 && ucs <= 0x2fffd) ||
(ucs >= 0x30000 && ucs <= 0x3fffd)));
#else /* !_MB_CAPABLE */
if (iswprint (ucs))
return 1;
if (iswcntrl (ucs) || ucs == L'\0')
return 0;
return -1;
#endif /* _MB_CAPABLE */
}
INTERNAL int vterm_unicode_is_combining(int codepoint)
{
return bisearch(codepoint, combining, sizeof(combining) / sizeof(struct interval) - 1);
}
