From 62791ac09f0e49bbfa9e056b7fd6510ab7b0b030 Mon Sep 17 00:00:00 2001 From: Michael Wallner Date: Tue, 6 Mar 2018 13:50:04 +0100 Subject: [PATCH] split utf8 ranges and single chars --- scripts/gen_utf8.php | 44 +- src/php_http_url.c | 2 +- src/php_http_utf8.h | 976 +++++++++++-------------------------------- 3 files changed, 285 insertions(+), 737 deletions(-) diff --git a/scripts/gen_utf8.php b/scripts/gen_utf8.php index 865a2f5..43b49e3 100755 --- a/scripts/gen_utf8.php +++ b/scripts/gen_utf8.php @@ -11,6 +11,8 @@ $i18n = $argc >= 2 ? $argv[1] : "/usr/share/i18n/locales/i18n"; $f = fopen($i18n, "r"); $c = false; $a = false; +$r = []; +$n = []; ob_start(null, 0xffff); while (!feof($f)) { @@ -55,23 +57,14 @@ while (!feof($f)) { sscanf($sstart, "", $start); break; } - print "\t{"; - if ($start >= 0xffff) { - printf("0x%08X, ", $start); - if ($end) { - printf("0x%08X, ", $end); - } else { - print(" 0, "); + if ($end) { + if ($step != 1) { + die("UNEXPECTED step=$step\n"); } + $r[] = [$start, $end]; } else { - printf(" 0x%04X, ", $start); - if ($end) { - printf(" 0x%04X, ", $end); - } else { - print(" 0, "); - } + $n[] = $start; } - printf("%d},\n", $step); } } break; @@ -85,6 +78,29 @@ while (!feof($f)) { } } +$maxstep = 0; +printf("static const utf8_range_t utf8_ranges[] = {\n\t{"); +foreach ($r as $i => list($start, $end)) { + if ($i) if ($i%3) { + printf(", {"); + } else { + printf(",\n\t{"); + } + + printf("0x%08X, 0x%08X}", $start, $end); +} +printf("\n};\n\n"); +printf("static const unsigned utf8_chars[] = {\n\t"); +foreach ($n as $i => $u) { + if ($i) if (($i%6)) { + printf(", "); + } else { + printf(",\n\t"); + } + printf("0x%08X", $u); +} +printf("\n};\n"); + file_put_contents("php_http_utf8.h", preg_replace('/(\/\* BEGIN::UTF8TABLE \*\/\n).*(\n\s*\/\* END::UTF8TABLE \*\/)/s', '$1'. ob_get_contents() .'$2', file_get_contents("php_http_utf8.h"))); diff --git a/src/php_http_url.c b/src/php_http_url.c index 01b556c..71ca6e9 100644 --- a/src/php_http_url.c +++ b/src/php_http_url.c @@ -743,7 +743,7 @@ static inline size_t parse_mb(struct parse_state *state, parse_mb_what_t what, c if (what == PARSE_HOSTINFO && (state->flags & PHP_HTTP_URL_PARSE_TOIDN)) { /* idna */ } else if (state->flags & PHP_HTTP_URL_PARSE_MBUTF8) { -#if 0&&PHP_HTTP_HAVE_LIBICU +#if PHP_HTTP_HAVE_LIBICU if (!u_isalnum(wchar)) { #else if (!isualnum(wchar)) { diff --git a/src/php_http_utf8.h b/src/php_http_utf8.h index 74fd19b..82a58d1 100644 --- a/src/php_http_utf8.h +++ b/src/php_http_utf8.h @@ -13,12 +13,6 @@ #ifndef PHP_HTTP_UTF8_H #define PHP_HTTP_UTF8_H -typedef struct utf8_range { - unsigned int start; - unsigned int end; - unsigned char step; -} utf8_range_t; - static const unsigned char utf8_mblen[256] = { 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, @@ -42,706 +36,234 @@ static const unsigned char utf8_mask[] = { 0, 0x7f, 0x1f, 0x0f, 0x07, 0x03, 0x01 }; -static const utf8_range_t utf8_ranges[] = { +typedef struct utf8_range { + const unsigned int start; + const unsigned int end; +} utf8_range_t; + /* BEGIN::UTF8TABLE */ - { 0x0041, 0x005A, 1}, - { 0x0061, 0x007A, 1}, - { 0x00AA, 0, 0}, - { 0x00B5, 0, 0}, - { 0x00BA, 0, 0}, - { 0x00C0, 0x00D6, 1}, - { 0x00D8, 0x00F6, 1}, - { 0x00F8, 0x02C1, 1}, - { 0x02C6, 0x02D1, 1}, - { 0x02E0, 0x02E4, 1}, - { 0x02EC, 0, 0}, - { 0x02EE, 0, 0}, - { 0x0345, 0, 0}, - { 0x0370, 0x0374, 1}, - { 0x0376, 0x0377, 1}, - { 0x037A, 0x037D, 1}, - { 0x037F, 0, 0}, - { 0x0386, 0, 0}, - { 0x0388, 0x038A, 1}, - { 0x038C, 0, 0}, - { 0x038E, 0x03A1, 1}, - { 0x03A3, 0x03F5, 1}, - { 0x03F7, 0x0481, 1}, - { 0x048A, 0x052F, 1}, - { 0x0531, 0x0556, 1}, - { 0x0559, 0, 0}, - { 0x0561, 0x0587, 1}, - { 0x05B0, 0x05BD, 1}, - { 0x05BF, 0, 0}, - { 0x05C1, 0x05C2, 1}, - { 0x05C4, 0x05C5, 1}, - { 0x05C7, 0, 0}, - { 0x05D0, 0x05EA, 1}, - { 0x05F0, 0x05F2, 1}, - { 0x0610, 0x061A, 1}, - { 0x0620, 0x0657, 1}, - { 0x0659, 0x0669, 1}, - { 0x066E, 0x06D3, 1}, - { 0x06D5, 0x06DC, 1}, - { 0x06E1, 0x06E8, 1}, - { 0x06ED, 0x06FC, 1}, - { 0x06FF, 0, 0}, - { 0x0710, 0x073F, 1}, - { 0x074D, 0x07B1, 1}, - { 0x07C0, 0x07EA, 1}, - { 0x07F4, 0x07F5, 1}, - { 0x07FA, 0, 0}, - { 0x0800, 0x0817, 1}, - { 0x081A, 0x082C, 1}, - { 0x0840, 0x0858, 1}, - { 0x0860, 0x086A, 1}, - { 0x08A0, 0x08B4, 1}, - { 0x08B6, 0x08BD, 1}, - { 0x08D4, 0x08DF, 1}, - { 0x08E3, 0x08E9, 1}, - { 0x08F0, 0x093B, 1}, - { 0x093D, 0x094C, 1}, - { 0x094E, 0x0950, 1}, - { 0x0955, 0x0963, 1}, - { 0x0966, 0x096F, 1}, - { 0x0971, 0x0983, 1}, - { 0x0985, 0x098C, 1}, - { 0x098F, 0x0990, 1}, - { 0x0993, 0x09A8, 1}, - { 0x09AA, 0x09B0, 1}, - { 0x09B2, 0, 0}, - { 0x09B6, 0x09B9, 1}, - { 0x09BD, 0x09C4, 1}, - { 0x09C7, 0x09C8, 1}, - { 0x09CB, 0x09CC, 1}, - { 0x09CE, 0, 0}, - { 0x09D7, 0, 0}, - { 0x09DC, 0x09DD, 1}, - { 0x09DF, 0x09E3, 1}, - { 0x09E6, 0x09F1, 1}, - { 0x09FC, 0, 0}, - { 0x0A01, 0x0A03, 1}, - { 0x0A05, 0x0A0A, 1}, - { 0x0A0F, 0x0A10, 1}, - { 0x0A13, 0x0A28, 1}, - { 0x0A2A, 0x0A30, 1}, - { 0x0A32, 0x0A33, 1}, - { 0x0A35, 0x0A36, 1}, - { 0x0A38, 0x0A39, 1}, - { 0x0A3E, 0x0A42, 1}, - { 0x0A47, 0x0A48, 1}, - { 0x0A4B, 0x0A4C, 1}, - { 0x0A51, 0, 0}, - { 0x0A59, 0x0A5C, 1}, - { 0x0A5E, 0, 0}, - { 0x0A66, 0x0A75, 1}, - { 0x0A81, 0x0A83, 1}, - { 0x0A85, 0x0A8D, 1}, - { 0x0A8F, 0x0A91, 1}, - { 0x0A93, 0x0AA8, 1}, - { 0x0AAA, 0x0AB0, 1}, - { 0x0AB2, 0x0AB3, 1}, - { 0x0AB5, 0x0AB9, 1}, - { 0x0ABD, 0x0AC5, 1}, - { 0x0AC7, 0x0AC9, 1}, - { 0x0ACB, 0x0ACC, 1}, - { 0x0AD0, 0, 0}, - { 0x0AE0, 0x0AE3, 1}, - { 0x0AE6, 0x0AEF, 1}, - { 0x0AF9, 0x0AFC, 1}, - { 0x0B01, 0x0B03, 1}, - { 0x0B05, 0x0B0C, 1}, - { 0x0B0F, 0x0B10, 1}, - { 0x0B13, 0x0B28, 1}, - { 0x0B2A, 0x0B30, 1}, - { 0x0B32, 0x0B33, 1}, - { 0x0B35, 0x0B39, 1}, - { 0x0B3D, 0x0B44, 1}, - { 0x0B47, 0x0B48, 1}, - { 0x0B4B, 0x0B4C, 1}, - { 0x0B56, 0x0B57, 1}, - { 0x0B5C, 0x0B5D, 1}, - { 0x0B5F, 0x0B63, 1}, - { 0x0B66, 0x0B6F, 1}, - { 0x0B71, 0, 0}, - { 0x0B82, 0x0B83, 1}, - { 0x0B85, 0x0B8A, 1}, - { 0x0B8E, 0x0B90, 1}, - { 0x0B92, 0x0B95, 1}, - { 0x0B99, 0x0B9A, 1}, - { 0x0B9C, 0, 0}, - { 0x0B9E, 0x0B9F, 1}, - { 0x0BA3, 0x0BA4, 1}, - { 0x0BA8, 0x0BAA, 1}, - { 0x0BAE, 0x0BB9, 1}, - { 0x0BBE, 0x0BC2, 1}, - { 0x0BC6, 0x0BC8, 1}, - { 0x0BCA, 0x0BCC, 1}, - { 0x0BD0, 0, 0}, - { 0x0BD7, 0, 0}, - { 0x0BE6, 0x0BEF, 1}, - { 0x0C00, 0x0C03, 1}, - { 0x0C05, 0x0C0C, 1}, - { 0x0C0E, 0x0C10, 1}, - { 0x0C12, 0x0C28, 1}, - { 0x0C2A, 0x0C39, 1}, - { 0x0C3D, 0x0C44, 1}, - { 0x0C46, 0x0C48, 1}, - { 0x0C4A, 0x0C4C, 1}, - { 0x0C55, 0x0C56, 1}, - { 0x0C58, 0x0C5A, 1}, - { 0x0C60, 0x0C63, 1}, - { 0x0C66, 0x0C6F, 1}, - { 0x0C80, 0x0C83, 1}, - { 0x0C85, 0x0C8C, 1}, - { 0x0C8E, 0x0C90, 1}, - { 0x0C92, 0x0CA8, 1}, - { 0x0CAA, 0x0CB3, 1}, - { 0x0CB5, 0x0CB9, 1}, - { 0x0CBD, 0x0CC4, 1}, - { 0x0CC6, 0x0CC8, 1}, - { 0x0CCA, 0x0CCC, 1}, - { 0x0CD5, 0x0CD6, 1}, - { 0x0CDE, 0, 0}, - { 0x0CE0, 0x0CE3, 1}, - { 0x0CE6, 0x0CEF, 1}, - { 0x0CF1, 0x0CF2, 1}, - { 0x0D00, 0x0D03, 1}, - { 0x0D05, 0x0D0C, 1}, - { 0x0D0E, 0x0D10, 1}, - { 0x0D12, 0x0D3A, 1}, - { 0x0D3D, 0x0D44, 1}, - { 0x0D46, 0x0D48, 1}, - { 0x0D4A, 0x0D4C, 1}, - { 0x0D4E, 0, 0}, - { 0x0D54, 0x0D57, 1}, - { 0x0D5F, 0x0D63, 1}, - { 0x0D66, 0x0D6F, 1}, - { 0x0D7A, 0x0D7F, 1}, - { 0x0D82, 0x0D83, 1}, - { 0x0D85, 0x0D96, 1}, - { 0x0D9A, 0x0DB1, 1}, - { 0x0DB3, 0x0DBB, 1}, - { 0x0DBD, 0, 0}, - { 0x0DC0, 0x0DC6, 1}, - { 0x0DCF, 0x0DD4, 1}, - { 0x0DD6, 0, 0}, - { 0x0DD8, 0x0DDF, 1}, - { 0x0DE6, 0x0DEF, 1}, - { 0x0DF2, 0x0DF3, 1}, - { 0x0E01, 0x0E3A, 1}, - { 0x0E40, 0x0E46, 1}, - { 0x0E4D, 0, 0}, - { 0x0E50, 0x0E59, 1}, - { 0x0E81, 0x0E82, 1}, - { 0x0E84, 0, 0}, - { 0x0E87, 0x0E88, 1}, - { 0x0E8A, 0, 0}, - { 0x0E8D, 0, 0}, - { 0x0E94, 0x0E97, 1}, - { 0x0E99, 0x0E9F, 1}, - { 0x0EA1, 0x0EA3, 1}, - { 0x0EA5, 0, 0}, - { 0x0EA7, 0, 0}, - { 0x0EAA, 0x0EAB, 1}, - { 0x0EAD, 0x0EB9, 1}, - { 0x0EBB, 0x0EBD, 1}, - { 0x0EC0, 0x0EC4, 1}, - { 0x0EC6, 0, 0}, - { 0x0ECD, 0, 0}, - { 0x0ED0, 0x0ED9, 1}, - { 0x0EDC, 0x0EDF, 1}, - { 0x0F00, 0, 0}, - { 0x0F20, 0x0F29, 1}, - { 0x0F40, 0x0F47, 1}, - { 0x0F49, 0x0F6C, 1}, - { 0x0F71, 0x0F81, 1}, - { 0x0F88, 0x0F97, 1}, - { 0x0F99, 0x0FBC, 1}, - { 0x1000, 0x1036, 1}, - { 0x1038, 0, 0}, - { 0x103B, 0x1049, 1}, - { 0x1050, 0x1062, 1}, - { 0x1065, 0x1068, 1}, - { 0x106E, 0x1086, 1}, - { 0x108E, 0, 0}, - { 0x1090, 0x1099, 1}, - { 0x109C, 0x109D, 1}, - { 0x10A0, 0x10C5, 1}, - { 0x10C7, 0, 0}, - { 0x10CD, 0, 0}, - { 0x10D0, 0x10FA, 1}, - { 0x10FC, 0x1248, 1}, - { 0x124A, 0x124D, 1}, - { 0x1250, 0x1256, 1}, - { 0x1258, 0, 0}, - { 0x125A, 0x125D, 1}, - { 0x1260, 0x1288, 1}, - { 0x128A, 0x128D, 1}, - { 0x1290, 0x12B0, 1}, - { 0x12B2, 0x12B5, 1}, - { 0x12B8, 0x12BE, 1}, - { 0x12C0, 0, 0}, - { 0x12C2, 0x12C5, 1}, - { 0x12C8, 0x12D6, 1}, - { 0x12D8, 0x1310, 1}, - { 0x1312, 0x1315, 1}, - { 0x1318, 0x135A, 1}, - { 0x135F, 0, 0}, - { 0x1380, 0x138F, 1}, - { 0x13A0, 0x13F5, 1}, - { 0x13F8, 0x13FD, 1}, - { 0x1401, 0x166C, 1}, - { 0x166F, 0x167F, 1}, - { 0x1681, 0x169A, 1}, - { 0x16A0, 0x16EA, 1}, - { 0x16EE, 0x16F8, 1}, - { 0x1700, 0x170C, 1}, - { 0x170E, 0x1713, 1}, - { 0x1720, 0x1733, 1}, - { 0x1740, 0x1753, 1}, - { 0x1760, 0x176C, 1}, - { 0x176E, 0x1770, 1}, - { 0x1772, 0x1773, 1}, - { 0x1780, 0x17B3, 1}, - { 0x17B6, 0x17C8, 1}, - { 0x17D7, 0, 0}, - { 0x17DC, 0, 0}, - { 0x17E0, 0x17E9, 1}, - { 0x1810, 0x1819, 1}, - { 0x1820, 0x1877, 1}, - { 0x1880, 0x18AA, 1}, - { 0x18B0, 0x18F5, 1}, - { 0x1900, 0x191E, 1}, - { 0x1920, 0x192B, 1}, - { 0x1930, 0x1938, 1}, - { 0x1946, 0x196D, 1}, - { 0x1970, 0x1974, 1}, - { 0x1980, 0x19AB, 1}, - { 0x19B0, 0x19C9, 1}, - { 0x19D0, 0x19D9, 1}, - { 0x1A00, 0x1A1B, 1}, - { 0x1A20, 0x1A5E, 1}, - { 0x1A61, 0x1A74, 1}, - { 0x1A80, 0x1A89, 1}, - { 0x1A90, 0x1A99, 1}, - { 0x1AA7, 0, 0}, - { 0x1B00, 0x1B33, 1}, - { 0x1B35, 0x1B43, 1}, - { 0x1B45, 0x1B4B, 1}, - { 0x1B50, 0x1B59, 1}, - { 0x1B80, 0x1BA9, 1}, - { 0x1BAC, 0x1BE5, 1}, - { 0x1BE7, 0x1BF1, 1}, - { 0x1C00, 0x1C35, 1}, - { 0x1C40, 0x1C49, 1}, - { 0x1C4D, 0x1C7D, 1}, - { 0x1C80, 0x1C88, 1}, - { 0x1CE9, 0x1CEC, 1}, - { 0x1CEE, 0x1CF3, 1}, - { 0x1CF5, 0x1CF6, 1}, - { 0x1D00, 0x1DBF, 1}, - { 0x1DE7, 0x1DF4, 1}, - { 0x1E00, 0x1F15, 1}, - { 0x1F18, 0x1F1D, 1}, - { 0x1F20, 0x1F45, 1}, - { 0x1F48, 0x1F4D, 1}, - { 0x1F50, 0x1F57, 1}, - { 0x1F59, 0, 0}, - { 0x1F5B, 0, 0}, - { 0x1F5D, 0, 0}, - { 0x1F5F, 0x1F7D, 1}, - { 0x1F80, 0x1FB4, 1}, - { 0x1FB6, 0x1FBC, 1}, - { 0x1FBE, 0, 0}, - { 0x1FC2, 0x1FC4, 1}, - { 0x1FC6, 0x1FCC, 1}, - { 0x1FD0, 0x1FD3, 1}, - { 0x1FD6, 0x1FDB, 1}, - { 0x1FE0, 0x1FEC, 1}, - { 0x1FF2, 0x1FF4, 1}, - { 0x1FF6, 0x1FFC, 1}, - { 0x2071, 0, 0}, - { 0x207F, 0, 0}, - { 0x2090, 0x209C, 1}, - { 0x2102, 0, 0}, - { 0x2107, 0, 0}, - { 0x210A, 0x2113, 1}, - { 0x2115, 0, 0}, - { 0x2119, 0x211D, 1}, - { 0x2124, 0, 0}, - { 0x2126, 0, 0}, - { 0x2128, 0, 0}, - { 0x212A, 0x212D, 1}, - { 0x212F, 0x2139, 1}, - { 0x213C, 0x213F, 1}, - { 0x2145, 0x2149, 1}, - { 0x214E, 0, 0}, - { 0x2160, 0x2188, 1}, - { 0x24B6, 0x24E9, 1}, - { 0x2C00, 0x2C2E, 1}, - { 0x2C30, 0x2C5E, 1}, - { 0x2C60, 0x2CE4, 1}, - { 0x2CEB, 0x2CEE, 1}, - { 0x2CF2, 0x2CF3, 1}, - { 0x2D00, 0x2D25, 1}, - { 0x2D27, 0, 0}, - { 0x2D2D, 0, 0}, - { 0x2D30, 0x2D67, 1}, - { 0x2D6F, 0, 0}, - { 0x2D80, 0x2D96, 1}, - { 0x2DA0, 0x2DA6, 1}, - { 0x2DA8, 0x2DAE, 1}, - { 0x2DB0, 0x2DB6, 1}, - { 0x2DB8, 0x2DBE, 1}, - { 0x2DC0, 0x2DC6, 1}, - { 0x2DC8, 0x2DCE, 1}, - { 0x2DD0, 0x2DD6, 1}, - { 0x2DD8, 0x2DDE, 1}, - { 0x2DE0, 0x2DFF, 1}, - { 0x2E2F, 0, 0}, - { 0x3005, 0x3007, 1}, - { 0x3021, 0x3029, 1}, - { 0x3031, 0x3035, 1}, - { 0x3038, 0x303C, 1}, - { 0x3041, 0x3096, 1}, - { 0x309D, 0x309F, 1}, - { 0x30A1, 0x30FA, 1}, - { 0x30FC, 0x30FF, 1}, - { 0x3105, 0x312E, 1}, - { 0x3131, 0x318E, 1}, - { 0x31A0, 0x31BA, 1}, - { 0x31F0, 0x31FF, 1}, - { 0x3400, 0x4DB5, 1}, - { 0x4E00, 0x9FEA, 1}, - { 0xA000, 0xA48C, 1}, - { 0xA4D0, 0xA4FD, 1}, - { 0xA500, 0xA60C, 1}, - { 0xA610, 0xA62B, 1}, - { 0xA640, 0xA66E, 1}, - { 0xA674, 0xA67B, 1}, - { 0xA67F, 0xA6EF, 1}, - { 0xA717, 0xA71F, 1}, - { 0xA722, 0xA788, 1}, - { 0xA78B, 0xA7AE, 1}, - { 0xA7B0, 0xA7B7, 1}, - { 0xA7F7, 0xA801, 1}, - { 0xA803, 0xA805, 1}, - { 0xA807, 0xA80A, 1}, - { 0xA80C, 0xA827, 1}, - { 0xA840, 0xA873, 1}, - { 0xA880, 0xA8C3, 1}, - { 0xA8C5, 0, 0}, - { 0xA8D0, 0xA8D9, 1}, - { 0xA8F2, 0xA8F7, 1}, - { 0xA8FB, 0, 0}, - { 0xA8FD, 0, 0}, - { 0xA900, 0xA92A, 1}, - { 0xA930, 0xA952, 1}, - { 0xA960, 0xA97C, 1}, - { 0xA980, 0xA9B2, 1}, - { 0xA9B4, 0xA9BF, 1}, - { 0xA9CF, 0xA9D9, 1}, - { 0xA9E0, 0xA9E4, 1}, - { 0xA9E6, 0xA9FE, 1}, - { 0xAA00, 0xAA36, 1}, - { 0xAA40, 0xAA4D, 1}, - { 0xAA50, 0xAA59, 1}, - { 0xAA60, 0xAA76, 1}, - { 0xAA7A, 0, 0}, - { 0xAA7E, 0xAABE, 1}, - { 0xAAC0, 0, 0}, - { 0xAAC2, 0, 0}, - { 0xAADB, 0xAADD, 1}, - { 0xAAE0, 0xAAEF, 1}, - { 0xAAF2, 0xAAF5, 1}, - { 0xAB01, 0xAB06, 1}, - { 0xAB09, 0xAB0E, 1}, - { 0xAB11, 0xAB16, 1}, - { 0xAB20, 0xAB26, 1}, - { 0xAB28, 0xAB2E, 1}, - { 0xAB30, 0xAB5A, 1}, - { 0xAB5C, 0xAB65, 1}, - { 0xAB70, 0xABEA, 1}, - { 0xABF0, 0xABF9, 1}, - { 0xAC00, 0xD7A3, 1}, - { 0xD7B0, 0xD7C6, 1}, - { 0xD7CB, 0xD7FB, 1}, - { 0xF900, 0xFA6D, 1}, - { 0xFA70, 0xFAD9, 1}, - { 0xFB00, 0xFB06, 1}, - { 0xFB13, 0xFB17, 1}, - { 0xFB1D, 0xFB28, 1}, - { 0xFB2A, 0xFB36, 1}, - { 0xFB38, 0xFB3C, 1}, - { 0xFB3E, 0, 0}, - { 0xFB40, 0xFB41, 1}, - { 0xFB43, 0xFB44, 1}, - { 0xFB46, 0xFBB1, 1}, - { 0xFBD3, 0xFD3D, 1}, - { 0xFD50, 0xFD8F, 1}, - { 0xFD92, 0xFDC7, 1}, - { 0xFDF0, 0xFDFB, 1}, - { 0xFE70, 0xFE74, 1}, - { 0xFE76, 0xFEFC, 1}, - { 0xFF10, 0xFF19, 1}, - { 0xFF21, 0xFF3A, 1}, - { 0xFF41, 0xFF5A, 1}, - { 0xFF66, 0xFFBE, 1}, - { 0xFFC2, 0xFFC7, 1}, - { 0xFFCA, 0xFFCF, 1}, - { 0xFFD2, 0xFFD7, 1}, - { 0xFFDA, 0xFFDC, 1}, - {0x00010000, 0x0001000B, 1}, - {0x0001000D, 0x00010026, 1}, - {0x00010028, 0x0001003A, 1}, - {0x0001003C, 0x0001003D, 1}, - {0x0001003F, 0x0001004D, 1}, - {0x00010050, 0x0001005D, 1}, - {0x00010080, 0x000100FA, 1}, - {0x00010140, 0x00010174, 1}, - {0x00010280, 0x0001029C, 1}, - {0x000102A0, 0x000102D0, 1}, - {0x00010300, 0x0001031F, 1}, - {0x0001032D, 0x0001034A, 1}, - {0x00010350, 0x0001037A, 1}, - {0x00010380, 0x0001039D, 1}, - {0x000103A0, 0x000103C3, 1}, - {0x000103C8, 0x000103CF, 1}, - {0x000103D1, 0x000103D5, 1}, - {0x00010400, 0x0001049D, 1}, - {0x000104A0, 0x000104A9, 1}, - {0x000104B0, 0x000104D3, 1}, - {0x000104D8, 0x000104FB, 1}, - {0x00010500, 0x00010527, 1}, - {0x00010530, 0x00010563, 1}, - {0x00010600, 0x00010736, 1}, - {0x00010740, 0x00010755, 1}, - {0x00010760, 0x00010767, 1}, - {0x00010800, 0x00010805, 1}, - {0x00010808, 0, 0}, - {0x0001080A, 0x00010835, 1}, - {0x00010837, 0x00010838, 1}, - {0x0001083C, 0, 0}, - {0x0001083F, 0x00010855, 1}, - {0x00010860, 0x00010876, 1}, - {0x00010880, 0x0001089E, 1}, - {0x000108E0, 0x000108F2, 1}, - {0x000108F4, 0x000108F5, 1}, - {0x00010900, 0x00010915, 1}, - {0x00010920, 0x00010939, 1}, - {0x00010980, 0x000109B7, 1}, - {0x000109BE, 0x000109BF, 1}, - {0x00010A00, 0x00010A03, 1}, - {0x00010A05, 0x00010A06, 1}, - {0x00010A0C, 0x00010A13, 1}, - {0x00010A15, 0x00010A17, 1}, - {0x00010A19, 0x00010A33, 1}, - {0x00010A60, 0x00010A7C, 1}, - {0x00010A80, 0x00010A9C, 1}, - {0x00010AC0, 0x00010AC7, 1}, - {0x00010AC9, 0x00010AE4, 1}, - {0x00010B00, 0x00010B35, 1}, - {0x00010B40, 0x00010B55, 1}, - {0x00010B60, 0x00010B72, 1}, - {0x00010B80, 0x00010B91, 1}, - {0x00010C00, 0x00010C48, 1}, - {0x00010C80, 0x00010CB2, 1}, - {0x00010CC0, 0x00010CF2, 1}, - {0x00011000, 0x00011045, 1}, - {0x00011066, 0x0001106F, 1}, - {0x00011082, 0x000110B8, 1}, - {0x000110D0, 0x000110E8, 1}, - {0x000110F0, 0x000110F9, 1}, - {0x00011100, 0x00011132, 1}, - {0x00011136, 0x0001113F, 1}, - {0x00011150, 0x00011172, 1}, - {0x00011176, 0, 0}, - {0x00011180, 0x000111BF, 1}, - {0x000111C1, 0x000111C4, 1}, - {0x000111D0, 0x000111DA, 1}, - {0x000111DC, 0, 0}, - {0x00011200, 0x00011211, 1}, - {0x00011213, 0x00011234, 1}, - {0x00011237, 0, 0}, - {0x0001123E, 0, 0}, - {0x00011280, 0x00011286, 1}, - {0x00011288, 0, 0}, - {0x0001128A, 0x0001128D, 1}, - {0x0001128F, 0x0001129D, 1}, - {0x0001129F, 0x000112A8, 1}, - {0x000112B0, 0x000112E8, 1}, - {0x000112F0, 0x000112F9, 1}, - {0x00011300, 0x00011303, 1}, - {0x00011305, 0x0001130C, 1}, - {0x0001130F, 0x00011310, 1}, - {0x00011313, 0x00011328, 1}, - {0x0001132A, 0x00011330, 1}, - {0x00011332, 0x00011333, 1}, - {0x00011335, 0x00011339, 1}, - {0x0001133D, 0x00011344, 1}, - {0x00011347, 0x00011348, 1}, - {0x0001134B, 0x0001134C, 1}, - {0x00011350, 0, 0}, - {0x00011357, 0, 0}, - {0x0001135D, 0x00011363, 1}, - {0x00011400, 0x00011441, 1}, - {0x00011443, 0x00011445, 1}, - {0x00011447, 0x0001144A, 1}, - {0x00011450, 0x00011459, 1}, - {0x00011480, 0x000114C1, 1}, - {0x000114C4, 0x000114C5, 1}, - {0x000114C7, 0, 0}, - {0x000114D0, 0x000114D9, 1}, - {0x00011580, 0x000115B5, 1}, - {0x000115B8, 0x000115BE, 1}, - {0x000115D8, 0x000115DD, 1}, - {0x00011600, 0x0001163E, 1}, - {0x00011640, 0, 0}, - {0x00011644, 0, 0}, - {0x00011650, 0x00011659, 1}, - {0x00011680, 0x000116B5, 1}, - {0x000116C0, 0x000116C9, 1}, - {0x00011700, 0x00011719, 1}, - {0x0001171D, 0x0001172A, 1}, - {0x00011730, 0x00011739, 1}, - {0x000118A0, 0x000118E9, 1}, - {0x000118FF, 0, 0}, - {0x00011A00, 0x00011A32, 1}, - {0x00011A35, 0x00011A3E, 1}, - {0x00011A50, 0x00011A83, 1}, - {0x00011A86, 0x00011A97, 1}, - {0x00011AC0, 0x00011AF8, 1}, - {0x00011C00, 0x00011C08, 1}, - {0x00011C0A, 0x00011C36, 1}, - {0x00011C38, 0x00011C3E, 1}, - {0x00011C40, 0, 0}, - {0x00011C50, 0x00011C59, 1}, - {0x00011C72, 0x00011C8F, 1}, - {0x00011C92, 0x00011CA7, 1}, - {0x00011CA9, 0x00011CB6, 1}, - {0x00011D00, 0x00011D06, 1}, - {0x00011D08, 0x00011D09, 1}, - {0x00011D0B, 0x00011D36, 1}, - {0x00011D3A, 0, 0}, - {0x00011D3C, 0x00011D3D, 1}, - {0x00011D3F, 0x00011D41, 1}, - {0x00011D43, 0, 0}, - {0x00011D46, 0x00011D47, 1}, - {0x00011D50, 0x00011D59, 1}, - {0x00012000, 0x00012399, 1}, - {0x00012400, 0x0001246E, 1}, - {0x00012480, 0x00012543, 1}, - {0x00013000, 0x0001342E, 1}, - {0x00014400, 0x00014646, 1}, - {0x00016800, 0x00016A38, 1}, - {0x00016A40, 0x00016A5E, 1}, - {0x00016A60, 0x00016A69, 1}, - {0x00016AD0, 0x00016AED, 1}, - {0x00016B00, 0x00016B36, 1}, - {0x00016B40, 0x00016B43, 1}, - {0x00016B50, 0x00016B59, 1}, - {0x00016B63, 0x00016B77, 1}, - {0x00016B7D, 0x00016B8F, 1}, - {0x00016F00, 0x00016F44, 1}, - {0x00016F50, 0x00016F7E, 1}, - {0x00016F93, 0x00016F9F, 1}, - {0x00016FE0, 0x00016FE1, 1}, - {0x00017000, 0x000187EC, 1}, - {0x00018800, 0x00018AF2, 1}, - {0x0001B000, 0x0001B11E, 1}, - {0x0001B170, 0x0001B2FB, 1}, - {0x0001BC00, 0x0001BC6A, 1}, - {0x0001BC70, 0x0001BC7C, 1}, - {0x0001BC80, 0x0001BC88, 1}, - {0x0001BC90, 0x0001BC99, 1}, - {0x0001BC9E, 0, 0}, - {0x0001D400, 0x0001D454, 1}, - {0x0001D456, 0x0001D49C, 1}, - {0x0001D49E, 0x0001D49F, 1}, - {0x0001D4A2, 0, 0}, - {0x0001D4A5, 0x0001D4A6, 1}, - {0x0001D4A9, 0x0001D4AC, 1}, - {0x0001D4AE, 0x0001D4B9, 1}, - {0x0001D4BB, 0, 0}, - {0x0001D4BD, 0x0001D4C3, 1}, - {0x0001D4C5, 0x0001D505, 1}, - {0x0001D507, 0x0001D50A, 1}, - {0x0001D50D, 0x0001D514, 1}, - {0x0001D516, 0x0001D51C, 1}, - {0x0001D51E, 0x0001D539, 1}, - {0x0001D53B, 0x0001D53E, 1}, - {0x0001D540, 0x0001D544, 1}, - {0x0001D546, 0, 0}, - {0x0001D54A, 0x0001D550, 1}, - {0x0001D552, 0x0001D6A5, 1}, - {0x0001D6A8, 0x0001D6C0, 1}, - {0x0001D6C2, 0x0001D6DA, 1}, - {0x0001D6DC, 0x0001D6FA, 1}, - {0x0001D6FC, 0x0001D714, 1}, - {0x0001D716, 0x0001D734, 1}, - {0x0001D736, 0x0001D74E, 1}, - {0x0001D750, 0x0001D76E, 1}, - {0x0001D770, 0x0001D788, 1}, - {0x0001D78A, 0x0001D7A8, 1}, - {0x0001D7AA, 0x0001D7C2, 1}, - {0x0001D7C4, 0x0001D7CB, 1}, - {0x0001D7CE, 0x0001D7FF, 1}, - {0x0001E000, 0x0001E006, 1}, - {0x0001E008, 0x0001E018, 1}, - {0x0001E01B, 0x0001E021, 1}, - {0x0001E023, 0x0001E024, 1}, - {0x0001E026, 0x0001E02A, 1}, - {0x0001E800, 0x0001E8C4, 1}, - {0x0001E900, 0x0001E943, 1}, - {0x0001E947, 0, 0}, - {0x0001E950, 0x0001E959, 1}, - {0x0001EE00, 0x0001EE03, 1}, - {0x0001EE05, 0x0001EE1F, 1}, - {0x0001EE21, 0x0001EE22, 1}, - {0x0001EE24, 0, 0}, - {0x0001EE27, 0, 0}, - {0x0001EE29, 0x0001EE32, 1}, - {0x0001EE34, 0x0001EE37, 1}, - {0x0001EE39, 0, 0}, - {0x0001EE3B, 0, 0}, - {0x0001EE42, 0, 0}, - {0x0001EE47, 0, 0}, - {0x0001EE49, 0, 0}, - {0x0001EE4B, 0, 0}, - {0x0001EE4D, 0x0001EE4F, 1}, - {0x0001EE51, 0x0001EE52, 1}, - {0x0001EE54, 0, 0}, - {0x0001EE57, 0, 0}, - {0x0001EE59, 0, 0}, - {0x0001EE5B, 0, 0}, - {0x0001EE5D, 0, 0}, - {0x0001EE5F, 0, 0}, - {0x0001EE61, 0x0001EE62, 1}, - {0x0001EE64, 0, 0}, - {0x0001EE67, 0x0001EE6A, 1}, - {0x0001EE6C, 0x0001EE72, 1}, - {0x0001EE74, 0x0001EE77, 1}, - {0x0001EE79, 0x0001EE7C, 1}, - {0x0001EE7E, 0, 0}, - {0x0001EE80, 0x0001EE89, 1}, - {0x0001EE8B, 0x0001EE9B, 1}, - {0x0001EEA1, 0x0001EEA3, 1}, - {0x0001EEA5, 0x0001EEA9, 1}, - {0x0001EEAB, 0x0001EEBB, 1}, - {0x0001F130, 0x0001F149, 1}, - {0x0001F150, 0x0001F169, 1}, - {0x0001F170, 0x0001F189, 1}, - {0x00020000, 0x0002A6D6, 1}, - {0x0002A700, 0x0002B734, 1}, - {0x0002B740, 0x0002B81D, 1}, - {0x0002B820, 0x0002CEA1, 1}, - {0x0002CEB0, 0x0002EBE0, 1}, - {0x0002F800, 0x0002FA1D, 1}, +static const utf8_range_t utf8_ranges[] = { + {0x00000041, 0x0000005A}, {0x00000061, 0x0000007A}, {0x000000C0, 0x000000D6}, + {0x000000D8, 0x000000F6}, {0x000000F8, 0x000002C1}, {0x000002C6, 0x000002D1}, + {0x000002E0, 0x000002E4}, {0x00000370, 0x00000374}, {0x00000376, 0x00000377}, + {0x0000037A, 0x0000037D}, {0x00000388, 0x0000038A}, {0x0000038E, 0x000003A1}, + {0x000003A3, 0x000003F5}, {0x000003F7, 0x00000481}, {0x0000048A, 0x0000052F}, + {0x00000531, 0x00000556}, {0x00000561, 0x00000587}, {0x000005B0, 0x000005BD}, + {0x000005C1, 0x000005C2}, {0x000005C4, 0x000005C5}, {0x000005D0, 0x000005EA}, + {0x000005F0, 0x000005F2}, {0x00000610, 0x0000061A}, {0x00000620, 0x00000657}, + {0x00000659, 0x00000669}, {0x0000066E, 0x000006D3}, {0x000006D5, 0x000006DC}, + {0x000006E1, 0x000006E8}, {0x000006ED, 0x000006FC}, {0x00000710, 0x0000073F}, + {0x0000074D, 0x000007B1}, {0x000007C0, 0x000007EA}, {0x000007F4, 0x000007F5}, + {0x00000800, 0x00000817}, {0x0000081A, 0x0000082C}, {0x00000840, 0x00000858}, + {0x00000860, 0x0000086A}, {0x000008A0, 0x000008B4}, {0x000008B6, 0x000008BD}, + {0x000008D4, 0x000008DF}, {0x000008E3, 0x000008E9}, {0x000008F0, 0x0000093B}, + {0x0000093D, 0x0000094C}, {0x0000094E, 0x00000950}, {0x00000955, 0x00000963}, + {0x00000966, 0x0000096F}, {0x00000971, 0x00000983}, {0x00000985, 0x0000098C}, + {0x0000098F, 0x00000990}, {0x00000993, 0x000009A8}, {0x000009AA, 0x000009B0}, + {0x000009B6, 0x000009B9}, {0x000009BD, 0x000009C4}, {0x000009C7, 0x000009C8}, + {0x000009CB, 0x000009CC}, {0x000009DC, 0x000009DD}, {0x000009DF, 0x000009E3}, + {0x000009E6, 0x000009F1}, {0x00000A01, 0x00000A03}, {0x00000A05, 0x00000A0A}, + {0x00000A0F, 0x00000A10}, {0x00000A13, 0x00000A28}, {0x00000A2A, 0x00000A30}, + {0x00000A32, 0x00000A33}, {0x00000A35, 0x00000A36}, {0x00000A38, 0x00000A39}, + {0x00000A3E, 0x00000A42}, {0x00000A47, 0x00000A48}, {0x00000A4B, 0x00000A4C}, + {0x00000A59, 0x00000A5C}, {0x00000A66, 0x00000A75}, {0x00000A81, 0x00000A83}, + {0x00000A85, 0x00000A8D}, {0x00000A8F, 0x00000A91}, {0x00000A93, 0x00000AA8}, + {0x00000AAA, 0x00000AB0}, {0x00000AB2, 0x00000AB3}, {0x00000AB5, 0x00000AB9}, + {0x00000ABD, 0x00000AC5}, {0x00000AC7, 0x00000AC9}, {0x00000ACB, 0x00000ACC}, + {0x00000AE0, 0x00000AE3}, {0x00000AE6, 0x00000AEF}, {0x00000AF9, 0x00000AFC}, + {0x00000B01, 0x00000B03}, {0x00000B05, 0x00000B0C}, {0x00000B0F, 0x00000B10}, + {0x00000B13, 0x00000B28}, {0x00000B2A, 0x00000B30}, {0x00000B32, 0x00000B33}, + {0x00000B35, 0x00000B39}, {0x00000B3D, 0x00000B44}, {0x00000B47, 0x00000B48}, + {0x00000B4B, 0x00000B4C}, {0x00000B56, 0x00000B57}, {0x00000B5C, 0x00000B5D}, + {0x00000B5F, 0x00000B63}, {0x00000B66, 0x00000B6F}, {0x00000B82, 0x00000B83}, + {0x00000B85, 0x00000B8A}, {0x00000B8E, 0x00000B90}, {0x00000B92, 0x00000B95}, + {0x00000B99, 0x00000B9A}, {0x00000B9E, 0x00000B9F}, {0x00000BA3, 0x00000BA4}, + {0x00000BA8, 0x00000BAA}, {0x00000BAE, 0x00000BB9}, {0x00000BBE, 0x00000BC2}, + {0x00000BC6, 0x00000BC8}, {0x00000BCA, 0x00000BCC}, {0x00000BE6, 0x00000BEF}, + {0x00000C00, 0x00000C03}, {0x00000C05, 0x00000C0C}, {0x00000C0E, 0x00000C10}, + {0x00000C12, 0x00000C28}, {0x00000C2A, 0x00000C39}, {0x00000C3D, 0x00000C44}, + {0x00000C46, 0x00000C48}, {0x00000C4A, 0x00000C4C}, {0x00000C55, 0x00000C56}, + {0x00000C58, 0x00000C5A}, {0x00000C60, 0x00000C63}, {0x00000C66, 0x00000C6F}, + {0x00000C80, 0x00000C83}, {0x00000C85, 0x00000C8C}, {0x00000C8E, 0x00000C90}, + {0x00000C92, 0x00000CA8}, {0x00000CAA, 0x00000CB3}, {0x00000CB5, 0x00000CB9}, + {0x00000CBD, 0x00000CC4}, {0x00000CC6, 0x00000CC8}, {0x00000CCA, 0x00000CCC}, + {0x00000CD5, 0x00000CD6}, {0x00000CE0, 0x00000CE3}, {0x00000CE6, 0x00000CEF}, + {0x00000CF1, 0x00000CF2}, {0x00000D00, 0x00000D03}, {0x00000D05, 0x00000D0C}, + {0x00000D0E, 0x00000D10}, {0x00000D12, 0x00000D3A}, {0x00000D3D, 0x00000D44}, + {0x00000D46, 0x00000D48}, {0x00000D4A, 0x00000D4C}, {0x00000D54, 0x00000D57}, + {0x00000D5F, 0x00000D63}, {0x00000D66, 0x00000D6F}, {0x00000D7A, 0x00000D7F}, + {0x00000D82, 0x00000D83}, {0x00000D85, 0x00000D96}, {0x00000D9A, 0x00000DB1}, + {0x00000DB3, 0x00000DBB}, {0x00000DC0, 0x00000DC6}, {0x00000DCF, 0x00000DD4}, + {0x00000DD8, 0x00000DDF}, {0x00000DE6, 0x00000DEF}, {0x00000DF2, 0x00000DF3}, + {0x00000E01, 0x00000E3A}, {0x00000E40, 0x00000E46}, {0x00000E50, 0x00000E59}, + {0x00000E81, 0x00000E82}, {0x00000E87, 0x00000E88}, {0x00000E94, 0x00000E97}, + {0x00000E99, 0x00000E9F}, {0x00000EA1, 0x00000EA3}, {0x00000EAA, 0x00000EAB}, + {0x00000EAD, 0x00000EB9}, {0x00000EBB, 0x00000EBD}, {0x00000EC0, 0x00000EC4}, + {0x00000ED0, 0x00000ED9}, {0x00000EDC, 0x00000EDF}, {0x00000F20, 0x00000F29}, + {0x00000F40, 0x00000F47}, {0x00000F49, 0x00000F6C}, {0x00000F71, 0x00000F81}, + {0x00000F88, 0x00000F97}, {0x00000F99, 0x00000FBC}, {0x00001000, 0x00001036}, + {0x0000103B, 0x00001049}, {0x00001050, 0x00001062}, {0x00001065, 0x00001068}, + {0x0000106E, 0x00001086}, {0x00001090, 0x00001099}, {0x0000109C, 0x0000109D}, + {0x000010A0, 0x000010C5}, {0x000010D0, 0x000010FA}, {0x000010FC, 0x00001248}, + {0x0000124A, 0x0000124D}, {0x00001250, 0x00001256}, {0x0000125A, 0x0000125D}, + {0x00001260, 0x00001288}, {0x0000128A, 0x0000128D}, {0x00001290, 0x000012B0}, + {0x000012B2, 0x000012B5}, {0x000012B8, 0x000012BE}, {0x000012C2, 0x000012C5}, + {0x000012C8, 0x000012D6}, {0x000012D8, 0x00001310}, {0x00001312, 0x00001315}, + {0x00001318, 0x0000135A}, {0x00001380, 0x0000138F}, {0x000013A0, 0x000013F5}, + {0x000013F8, 0x000013FD}, {0x00001401, 0x0000166C}, {0x0000166F, 0x0000167F}, + {0x00001681, 0x0000169A}, {0x000016A0, 0x000016EA}, {0x000016EE, 0x000016F8}, + {0x00001700, 0x0000170C}, {0x0000170E, 0x00001713}, {0x00001720, 0x00001733}, + {0x00001740, 0x00001753}, {0x00001760, 0x0000176C}, {0x0000176E, 0x00001770}, + {0x00001772, 0x00001773}, {0x00001780, 0x000017B3}, {0x000017B6, 0x000017C8}, + {0x000017E0, 0x000017E9}, {0x00001810, 0x00001819}, {0x00001820, 0x00001877}, + {0x00001880, 0x000018AA}, {0x000018B0, 0x000018F5}, {0x00001900, 0x0000191E}, + {0x00001920, 0x0000192B}, {0x00001930, 0x00001938}, {0x00001946, 0x0000196D}, + {0x00001970, 0x00001974}, {0x00001980, 0x000019AB}, {0x000019B0, 0x000019C9}, + {0x000019D0, 0x000019D9}, {0x00001A00, 0x00001A1B}, {0x00001A20, 0x00001A5E}, + {0x00001A61, 0x00001A74}, {0x00001A80, 0x00001A89}, {0x00001A90, 0x00001A99}, + {0x00001B00, 0x00001B33}, {0x00001B35, 0x00001B43}, {0x00001B45, 0x00001B4B}, + {0x00001B50, 0x00001B59}, {0x00001B80, 0x00001BA9}, {0x00001BAC, 0x00001BE5}, + {0x00001BE7, 0x00001BF1}, {0x00001C00, 0x00001C35}, {0x00001C40, 0x00001C49}, + {0x00001C4D, 0x00001C7D}, {0x00001C80, 0x00001C88}, {0x00001CE9, 0x00001CEC}, + {0x00001CEE, 0x00001CF3}, {0x00001CF5, 0x00001CF6}, {0x00001D00, 0x00001DBF}, + {0x00001DE7, 0x00001DF4}, {0x00001E00, 0x00001F15}, {0x00001F18, 0x00001F1D}, + {0x00001F20, 0x00001F45}, {0x00001F48, 0x00001F4D}, {0x00001F50, 0x00001F57}, + {0x00001F5F, 0x00001F7D}, {0x00001F80, 0x00001FB4}, {0x00001FB6, 0x00001FBC}, + {0x00001FC2, 0x00001FC4}, {0x00001FC6, 0x00001FCC}, {0x00001FD0, 0x00001FD3}, + {0x00001FD6, 0x00001FDB}, {0x00001FE0, 0x00001FEC}, {0x00001FF2, 0x00001FF4}, + {0x00001FF6, 0x00001FFC}, {0x00002090, 0x0000209C}, {0x0000210A, 0x00002113}, + {0x00002119, 0x0000211D}, {0x0000212A, 0x0000212D}, {0x0000212F, 0x00002139}, + {0x0000213C, 0x0000213F}, {0x00002145, 0x00002149}, {0x00002160, 0x00002188}, + {0x000024B6, 0x000024E9}, {0x00002C00, 0x00002C2E}, {0x00002C30, 0x00002C5E}, + {0x00002C60, 0x00002CE4}, {0x00002CEB, 0x00002CEE}, {0x00002CF2, 0x00002CF3}, + {0x00002D00, 0x00002D25}, {0x00002D30, 0x00002D67}, {0x00002D80, 0x00002D96}, + {0x00002DA0, 0x00002DA6}, {0x00002DA8, 0x00002DAE}, {0x00002DB0, 0x00002DB6}, + {0x00002DB8, 0x00002DBE}, {0x00002DC0, 0x00002DC6}, {0x00002DC8, 0x00002DCE}, + {0x00002DD0, 0x00002DD6}, {0x00002DD8, 0x00002DDE}, {0x00002DE0, 0x00002DFF}, + {0x00003005, 0x00003007}, {0x00003021, 0x00003029}, {0x00003031, 0x00003035}, + {0x00003038, 0x0000303C}, {0x00003041, 0x00003096}, {0x0000309D, 0x0000309F}, + {0x000030A1, 0x000030FA}, {0x000030FC, 0x000030FF}, {0x00003105, 0x0000312E}, + {0x00003131, 0x0000318E}, {0x000031A0, 0x000031BA}, {0x000031F0, 0x000031FF}, + {0x00003400, 0x00004DB5}, {0x00004E00, 0x00009FEA}, {0x0000A000, 0x0000A48C}, + {0x0000A4D0, 0x0000A4FD}, {0x0000A500, 0x0000A60C}, {0x0000A610, 0x0000A62B}, + {0x0000A640, 0x0000A66E}, {0x0000A674, 0x0000A67B}, {0x0000A67F, 0x0000A6EF}, + {0x0000A717, 0x0000A71F}, {0x0000A722, 0x0000A788}, {0x0000A78B, 0x0000A7AE}, + {0x0000A7B0, 0x0000A7B7}, {0x0000A7F7, 0x0000A801}, {0x0000A803, 0x0000A805}, + {0x0000A807, 0x0000A80A}, {0x0000A80C, 0x0000A827}, {0x0000A840, 0x0000A873}, + {0x0000A880, 0x0000A8C3}, {0x0000A8D0, 0x0000A8D9}, {0x0000A8F2, 0x0000A8F7}, + {0x0000A900, 0x0000A92A}, {0x0000A930, 0x0000A952}, {0x0000A960, 0x0000A97C}, + {0x0000A980, 0x0000A9B2}, {0x0000A9B4, 0x0000A9BF}, {0x0000A9CF, 0x0000A9D9}, + {0x0000A9E0, 0x0000A9E4}, {0x0000A9E6, 0x0000A9FE}, {0x0000AA00, 0x0000AA36}, + {0x0000AA40, 0x0000AA4D}, {0x0000AA50, 0x0000AA59}, {0x0000AA60, 0x0000AA76}, + {0x0000AA7E, 0x0000AABE}, {0x0000AADB, 0x0000AADD}, {0x0000AAE0, 0x0000AAEF}, + {0x0000AAF2, 0x0000AAF5}, {0x0000AB01, 0x0000AB06}, {0x0000AB09, 0x0000AB0E}, + {0x0000AB11, 0x0000AB16}, {0x0000AB20, 0x0000AB26}, {0x0000AB28, 0x0000AB2E}, + {0x0000AB30, 0x0000AB5A}, {0x0000AB5C, 0x0000AB65}, {0x0000AB70, 0x0000ABEA}, + {0x0000ABF0, 0x0000ABF9}, {0x0000AC00, 0x0000D7A3}, {0x0000D7B0, 0x0000D7C6}, + {0x0000D7CB, 0x0000D7FB}, {0x0000F900, 0x0000FA6D}, {0x0000FA70, 0x0000FAD9}, + {0x0000FB00, 0x0000FB06}, {0x0000FB13, 0x0000FB17}, {0x0000FB1D, 0x0000FB28}, + {0x0000FB2A, 0x0000FB36}, {0x0000FB38, 0x0000FB3C}, {0x0000FB40, 0x0000FB41}, + {0x0000FB43, 0x0000FB44}, {0x0000FB46, 0x0000FBB1}, {0x0000FBD3, 0x0000FD3D}, + {0x0000FD50, 0x0000FD8F}, {0x0000FD92, 0x0000FDC7}, {0x0000FDF0, 0x0000FDFB}, + {0x0000FE70, 0x0000FE74}, {0x0000FE76, 0x0000FEFC}, {0x0000FF10, 0x0000FF19}, + {0x0000FF21, 0x0000FF3A}, {0x0000FF41, 0x0000FF5A}, {0x0000FF66, 0x0000FFBE}, + {0x0000FFC2, 0x0000FFC7}, {0x0000FFCA, 0x0000FFCF}, {0x0000FFD2, 0x0000FFD7}, + {0x0000FFDA, 0x0000FFDC}, {0x00010000, 0x0001000B}, {0x0001000D, 0x00010026}, + {0x00010028, 0x0001003A}, {0x0001003C, 0x0001003D}, {0x0001003F, 0x0001004D}, + {0x00010050, 0x0001005D}, {0x00010080, 0x000100FA}, {0x00010140, 0x00010174}, + {0x00010280, 0x0001029C}, {0x000102A0, 0x000102D0}, {0x00010300, 0x0001031F}, + {0x0001032D, 0x0001034A}, {0x00010350, 0x0001037A}, {0x00010380, 0x0001039D}, + {0x000103A0, 0x000103C3}, {0x000103C8, 0x000103CF}, {0x000103D1, 0x000103D5}, + {0x00010400, 0x0001049D}, {0x000104A0, 0x000104A9}, {0x000104B0, 0x000104D3}, + {0x000104D8, 0x000104FB}, {0x00010500, 0x00010527}, {0x00010530, 0x00010563}, + {0x00010600, 0x00010736}, {0x00010740, 0x00010755}, {0x00010760, 0x00010767}, + {0x00010800, 0x00010805}, {0x0001080A, 0x00010835}, {0x00010837, 0x00010838}, + {0x0001083F, 0x00010855}, {0x00010860, 0x00010876}, {0x00010880, 0x0001089E}, + {0x000108E0, 0x000108F2}, {0x000108F4, 0x000108F5}, {0x00010900, 0x00010915}, + {0x00010920, 0x00010939}, {0x00010980, 0x000109B7}, {0x000109BE, 0x000109BF}, + {0x00010A00, 0x00010A03}, {0x00010A05, 0x00010A06}, {0x00010A0C, 0x00010A13}, + {0x00010A15, 0x00010A17}, {0x00010A19, 0x00010A33}, {0x00010A60, 0x00010A7C}, + {0x00010A80, 0x00010A9C}, {0x00010AC0, 0x00010AC7}, {0x00010AC9, 0x00010AE4}, + {0x00010B00, 0x00010B35}, {0x00010B40, 0x00010B55}, {0x00010B60, 0x00010B72}, + {0x00010B80, 0x00010B91}, {0x00010C00, 0x00010C48}, {0x00010C80, 0x00010CB2}, + {0x00010CC0, 0x00010CF2}, {0x00011000, 0x00011045}, {0x00011066, 0x0001106F}, + {0x00011082, 0x000110B8}, {0x000110D0, 0x000110E8}, {0x000110F0, 0x000110F9}, + {0x00011100, 0x00011132}, {0x00011136, 0x0001113F}, {0x00011150, 0x00011172}, + {0x00011180, 0x000111BF}, {0x000111C1, 0x000111C4}, {0x000111D0, 0x000111DA}, + {0x00011200, 0x00011211}, {0x00011213, 0x00011234}, {0x00011280, 0x00011286}, + {0x0001128A, 0x0001128D}, {0x0001128F, 0x0001129D}, {0x0001129F, 0x000112A8}, + {0x000112B0, 0x000112E8}, {0x000112F0, 0x000112F9}, {0x00011300, 0x00011303}, + {0x00011305, 0x0001130C}, {0x0001130F, 0x00011310}, {0x00011313, 0x00011328}, + {0x0001132A, 0x00011330}, {0x00011332, 0x00011333}, {0x00011335, 0x00011339}, + {0x0001133D, 0x00011344}, {0x00011347, 0x00011348}, {0x0001134B, 0x0001134C}, + {0x0001135D, 0x00011363}, {0x00011400, 0x00011441}, {0x00011443, 0x00011445}, + {0x00011447, 0x0001144A}, {0x00011450, 0x00011459}, {0x00011480, 0x000114C1}, + {0x000114C4, 0x000114C5}, {0x000114D0, 0x000114D9}, {0x00011580, 0x000115B5}, + {0x000115B8, 0x000115BE}, {0x000115D8, 0x000115DD}, {0x00011600, 0x0001163E}, + {0x00011650, 0x00011659}, {0x00011680, 0x000116B5}, {0x000116C0, 0x000116C9}, + {0x00011700, 0x00011719}, {0x0001171D, 0x0001172A}, {0x00011730, 0x00011739}, + {0x000118A0, 0x000118E9}, {0x00011A00, 0x00011A32}, {0x00011A35, 0x00011A3E}, + {0x00011A50, 0x00011A83}, {0x00011A86, 0x00011A97}, {0x00011AC0, 0x00011AF8}, + {0x00011C00, 0x00011C08}, {0x00011C0A, 0x00011C36}, {0x00011C38, 0x00011C3E}, + {0x00011C50, 0x00011C59}, {0x00011C72, 0x00011C8F}, {0x00011C92, 0x00011CA7}, + {0x00011CA9, 0x00011CB6}, {0x00011D00, 0x00011D06}, {0x00011D08, 0x00011D09}, + {0x00011D0B, 0x00011D36}, {0x00011D3C, 0x00011D3D}, {0x00011D3F, 0x00011D41}, + {0x00011D46, 0x00011D47}, {0x00011D50, 0x00011D59}, {0x00012000, 0x00012399}, + {0x00012400, 0x0001246E}, {0x00012480, 0x00012543}, {0x00013000, 0x0001342E}, + {0x00014400, 0x00014646}, {0x00016800, 0x00016A38}, {0x00016A40, 0x00016A5E}, + {0x00016A60, 0x00016A69}, {0x00016AD0, 0x00016AED}, {0x00016B00, 0x00016B36}, + {0x00016B40, 0x00016B43}, {0x00016B50, 0x00016B59}, {0x00016B63, 0x00016B77}, + {0x00016B7D, 0x00016B8F}, {0x00016F00, 0x00016F44}, {0x00016F50, 0x00016F7E}, + {0x00016F93, 0x00016F9F}, {0x00016FE0, 0x00016FE1}, {0x00017000, 0x000187EC}, + {0x00018800, 0x00018AF2}, {0x0001B000, 0x0001B11E}, {0x0001B170, 0x0001B2FB}, + {0x0001BC00, 0x0001BC6A}, {0x0001BC70, 0x0001BC7C}, {0x0001BC80, 0x0001BC88}, + {0x0001BC90, 0x0001BC99}, {0x0001D400, 0x0001D454}, {0x0001D456, 0x0001D49C}, + {0x0001D49E, 0x0001D49F}, {0x0001D4A5, 0x0001D4A6}, {0x0001D4A9, 0x0001D4AC}, + {0x0001D4AE, 0x0001D4B9}, {0x0001D4BD, 0x0001D4C3}, {0x0001D4C5, 0x0001D505}, + {0x0001D507, 0x0001D50A}, {0x0001D50D, 0x0001D514}, {0x0001D516, 0x0001D51C}, + {0x0001D51E, 0x0001D539}, {0x0001D53B, 0x0001D53E}, {0x0001D540, 0x0001D544}, + {0x0001D54A, 0x0001D550}, {0x0001D552, 0x0001D6A5}, {0x0001D6A8, 0x0001D6C0}, + {0x0001D6C2, 0x0001D6DA}, {0x0001D6DC, 0x0001D6FA}, {0x0001D6FC, 0x0001D714}, + {0x0001D716, 0x0001D734}, {0x0001D736, 0x0001D74E}, {0x0001D750, 0x0001D76E}, + {0x0001D770, 0x0001D788}, {0x0001D78A, 0x0001D7A8}, {0x0001D7AA, 0x0001D7C2}, + {0x0001D7C4, 0x0001D7CB}, {0x0001D7CE, 0x0001D7FF}, {0x0001E000, 0x0001E006}, + {0x0001E008, 0x0001E018}, {0x0001E01B, 0x0001E021}, {0x0001E023, 0x0001E024}, + {0x0001E026, 0x0001E02A}, {0x0001E800, 0x0001E8C4}, {0x0001E900, 0x0001E943}, + {0x0001E950, 0x0001E959}, {0x0001EE00, 0x0001EE03}, {0x0001EE05, 0x0001EE1F}, + {0x0001EE21, 0x0001EE22}, {0x0001EE29, 0x0001EE32}, {0x0001EE34, 0x0001EE37}, + {0x0001EE4D, 0x0001EE4F}, {0x0001EE51, 0x0001EE52}, {0x0001EE61, 0x0001EE62}, + {0x0001EE67, 0x0001EE6A}, {0x0001EE6C, 0x0001EE72}, {0x0001EE74, 0x0001EE77}, + {0x0001EE79, 0x0001EE7C}, {0x0001EE80, 0x0001EE89}, {0x0001EE8B, 0x0001EE9B}, + {0x0001EEA1, 0x0001EEA3}, {0x0001EEA5, 0x0001EEA9}, {0x0001EEAB, 0x0001EEBB}, + {0x0001F130, 0x0001F149}, {0x0001F150, 0x0001F169}, {0x0001F170, 0x0001F189}, + {0x00020000, 0x0002A6D6}, {0x0002A700, 0x0002B734}, {0x0002B740, 0x0002B81D}, + {0x0002B820, 0x0002CEA1}, {0x0002CEB0, 0x0002EBE0}, {0x0002F800, 0x0002FA1D} +}; -/* END::UTF8TABLE */ +static const unsigned utf8_chars[] = { + 0x000000AA, 0x000000B5, 0x000000BA, 0x000002EC, 0x000002EE, 0x00000345, + 0x0000037F, 0x00000386, 0x0000038C, 0x00000559, 0x000005BF, 0x000005C7, + 0x000006FF, 0x000007FA, 0x000009B2, 0x000009CE, 0x000009D7, 0x000009FC, + 0x00000A51, 0x00000A5E, 0x00000AD0, 0x00000B71, 0x00000B9C, 0x00000BD0, + 0x00000BD7, 0x00000CDE, 0x00000D4E, 0x00000DBD, 0x00000DD6, 0x00000E4D, + 0x00000E84, 0x00000E8A, 0x00000E8D, 0x00000EA5, 0x00000EA7, 0x00000EC6, + 0x00000ECD, 0x00000F00, 0x00001038, 0x0000108E, 0x000010C7, 0x000010CD, + 0x00001258, 0x000012C0, 0x0000135F, 0x000017D7, 0x000017DC, 0x00001AA7, + 0x00001F59, 0x00001F5B, 0x00001F5D, 0x00001FBE, 0x00002071, 0x0000207F, + 0x00002102, 0x00002107, 0x00002115, 0x00002124, 0x00002126, 0x00002128, + 0x0000214E, 0x00002D27, 0x00002D2D, 0x00002D6F, 0x00002E2F, 0x0000A8C5, + 0x0000A8FB, 0x0000A8FD, 0x0000AA7A, 0x0000AAC0, 0x0000AAC2, 0x0000FB3E, + 0x00010808, 0x0001083C, 0x00011176, 0x000111DC, 0x00011237, 0x0001123E, + 0x00011288, 0x00011350, 0x00011357, 0x000114C7, 0x00011640, 0x00011644, + 0x000118FF, 0x00011C40, 0x00011D3A, 0x00011D43, 0x0001BC9E, 0x0001D4A2, + 0x0001D4BB, 0x0001D546, 0x0001E947, 0x0001EE24, 0x0001EE27, 0x0001EE39, + 0x0001EE3B, 0x0001EE42, 0x0001EE47, 0x0001EE49, 0x0001EE4B, 0x0001EE54, + 0x0001EE57, 0x0001EE59, 0x0001EE5B, 0x0001EE5D, 0x0001EE5F, 0x0001EE64, + 0x0001EE7E }; +/* END::UTF8TABLE */ + static inline size_t utf8towc(unsigned *wc, const unsigned char *uc, size_t len) { unsigned char ub = utf8_mblen[*uc]; @@ -786,11 +308,8 @@ static inline size_t utf8towc(unsigned *wc, const unsigned char *uc, size_t len) static inline zend_bool isualpha(unsigned ch) { - unsigned count = sizeof(utf8_ranges)/sizeof(utf8_range_t), - lo = 0, - hi = count-1, - cur = (count-1)/2, - prev; + unsigned hi = sizeof(utf8_ranges)/sizeof(utf8_ranges[0])-1, + cur = hi/2, lo = 0, prev; #undef u #define u (utf8_ranges[cur]) @@ -799,20 +318,8 @@ static inline zend_bool isualpha(unsigned ch) #if 0 fprintf(stderr, "=> cur=%u lo=%u hi=%u (%u in %u-%u)\n", cur, lo, hi, ch, u.start, u.end); #endif - if (u.start == ch) { + if (u.start <= ch && u.end >= ch) { return 1; - } else if (u.start <= ch && u.end >= ch) { - unsigned j; - - if (u.step == 1) { - return 1; - } - for (j = u.start; j <= u.end; j+= u.step) { - if (ch == j) { - return 1; - } - } - return 0; } prev = cur; @@ -824,13 +331,38 @@ static inline zend_bool isualpha(unsigned ch) lo = cur; cur += (hi - cur) / 2; } else { - return 0; + break; } } while (cur != prev); #undef u -#undef check +#define u (utf8_chars[cur]) + + hi = sizeof(utf8_chars)/sizeof(utf8_chars[0]); + cur = hi/2; + lo = 0; + + do { +#if 0 + fprintf(stderr, "=> cur=%u lo=%u hi=%u (%u is %u)\n", cur, lo, hi, ch, u); +#endif + if (u == ch) { + return 1; + } + + prev = cur; + + if (u > ch) { + hi = cur; + cur -= (cur - lo) / 2; + } else { + lo = cur; + cur += (hi - cur) / 2; + } + } while (cur != prev); + +#undef u return 0; } -- 2.30.2