minibidi.c

putty

        {0x0ccc, 0x0ccd, NSM},
        {0x0cd5, 0x0cd6, L},
        {0x0cde, 0x0cde, L},
        {0x0ce0, 0x0ce1, L},
        {0x0ce6, 0x0cef, L},
        {0x0d02, 0x0d03, L},
        {0x0d05, 0x0d0c, L},
        {0x0d0e, 0x0d10, L},
        {0x0d12, 0x0d28, L},
        {0x0d2a, 0x0d39, L},
        {0x0d3e, 0x0d40, L},
        {0x0d41, 0x0d43, NSM},
        {0x0d46, 0x0d48, L},
        {0x0d4a, 0x0d4c, L},
        {0x0d4d, 0x0d4d, NSM},
        {0x0d57, 0x0d57, L},
        {0x0d60, 0x0d61, L},
        {0x0d66, 0x0d6f, L},
        {0x0d82, 0x0d83, L},
        {0x0d85, 0x0d96, L},
        {0x0d9a, 0x0db1, L},
        {0x0db3, 0x0dbb, L},
        {0x0dbd, 0x0dbd, L},
        {0x0dc0, 0x0dc6, L},
        {0x0dca, 0x0dca, NSM},
        {0x0dcf, 0x0dd1, L},
        {0x0dd2, 0x0dd4, NSM},
        {0x0dd6, 0x0dd6, NSM},
        {0x0dd8, 0x0ddf, L},
        {0x0df2, 0x0df4, L},
        {0x0e01, 0x0e30, L},
        {0x0e31, 0x0e31, NSM},
        {0x0e32, 0x0e33, L},
        {0x0e34, 0x0e3a, NSM},
        {0x0e3f, 0x0e3f, ET},
        {0x0e40, 0x0e46, L},
        {0x0e47, 0x0e4e, NSM},
        {0x0e4f, 0x0e5b, L},
        {0x0e81, 0x0e82, L},
        {0x0e84, 0x0e84, L},
        {0x0e87, 0x0e88, L},
        {0x0e8a, 0x0e8a, L},
        {0x0e8d, 0x0e8d, L},
        {0x0e94, 0x0e97, L},
        {0x0e99, 0x0e9f, L},
        {0x0ea1, 0x0ea3, L},
        {0x0ea5, 0x0ea5, L},
        {0x0ea7, 0x0ea7, L},
        {0x0eaa, 0x0eab, L},
        {0x0ead, 0x0eb0, L},
        {0x0eb1, 0x0eb1, NSM},
        {0x0eb2, 0x0eb3, L},
        {0x0eb4, 0x0eb9, NSM},
        {0x0ebb, 0x0ebc, NSM},
        {0x0ebd, 0x0ebd, L},
        {0x0ec0, 0x0ec4, L},
        {0x0ec6, 0x0ec6, L},
        {0x0ec8, 0x0ecd, NSM},
        {0x0ed0, 0x0ed9, L},
        {0x0edc, 0x0edd, L},
        {0x0f00, 0x0f17, L},
        {0x0f18, 0x0f19, NSM},
        {0x0f1a, 0x0f34, L},
        {0x0f35, 0x0f35, NSM},
        {0x0f36, 0x0f36, L},
        {0x0f37, 0x0f37, NSM},
        {0x0f38, 0x0f38, L},
        {0x0f39, 0x0f39, NSM},
        {0x0f3e, 0x0f47, L},
        {0x0f49, 0x0f6a, L},
        {0x0f71, 0x0f7e, NSM},
        {0x0f7f, 0x0f7f, L},
        {0x0f80, 0x0f84, NSM},
        {0x0f85, 0x0f85, L},
        {0x0f86, 0x0f87, NSM},
        {0x0f88, 0x0f8b, L},
        {0x0f90, 0x0f97, NSM},
        {0x0f99, 0x0fbc, NSM},
        {0x0fbe, 0x0fc5, L},
        {0x0fc6, 0x0fc6, NSM},
        {0x0fc7, 0x0fcc, L},
        {0x0fcf, 0x0fcf, L},
        {0x1000, 0x1021, L},
        {0x1023, 0x1027, L},
        {0x1029, 0x102a, L},
        {0x102c, 0x102c, L},
        {0x102d, 0x1030, NSM},
        {0x1031, 0x1031, L},
        {0x1032, 0x1032, NSM},
        {0x1036, 0x1037, NSM},
        {0x1038, 0x1038, L},
        {0x1039, 0x1039, NSM},
        {0x1040, 0x1057, L},
        {0x1058, 0x1059, NSM},
        {0x10a0, 0x10c5, L},
        {0x10d0, 0x10f8, L},
        {0x10fb, 0x10fb, L},
        {0x1100, 0x1159, L},
        {0x115f, 0x11a2, L},
        {0x11a8, 0x11f9, L},
        {0x1200, 0x1206, L},
        {0x1208, 0x1246, L},
        {0x1248, 0x1248, L},
        {0x124a, 0x124d, L},
        {0x1250, 0x1256, L},
        {0x1258, 0x1258, L},
        {0x125a, 0x125d, L},
        {0x1260, 0x1286, L},
        {0x1288, 0x1288, L},
        {0x128a, 0x128d, L},
        {0x1290, 0x12ae, L},
        {0x12b0, 0x12b0, L},
        {0x12b2, 0x12b5, L},
        {0x12b8, 0x12be, L},
        {0x12c0, 0x12c0, L},
        {0x12c2, 0x12c5, L},
        {0x12c8, 0x12ce, L},
        {0x12d0, 0x12d6, L},
        {0x12d8, 0x12ee, L},
        {0x12f0, 0x130e, L},
        {0x1310, 0x1310, L},
        {0x1312, 0x1315, L},
        {0x1318, 0x131e, L},
        {0x1320, 0x1346, L},
        {0x1348, 0x135a, L},
        {0x1361, 0x137c, L},
        {0x13a0, 0x13f4, L},
        {0x1401, 0x1676, L},
        {0x1680, 0x1680, WS},
        {0x1681, 0x169a, L},
        {0x16a0, 0x16f0, L},
        {0x1700, 0x170c, L},
        {0x170e, 0x1711, L},
        {0x1712, 0x1714, NSM},
        {0x1720, 0x1731, L},
        {0x1732, 0x1734, NSM},
        {0x1735, 0x1736, L},
        {0x1740, 0x1751, L},
        {0x1752, 0x1753, NSM},
        {0x1760, 0x176c, L},
        {0x176e, 0x1770, L},
        {0x1772, 0x1773, NSM},
        {0x1780, 0x17b6, L},
        {0x17b7, 0x17bd, NSM},
        {0x17be, 0x17c5, L},
        {0x17c6, 0x17c6, NSM},
        {0x17c7, 0x17c8, L},
        {0x17c9, 0x17d3, NSM},
        {0x17d4, 0x17da, L},
        {0x17db, 0x17db, ET},
        {0x17dc, 0x17dc, L},
        {0x17dd, 0x17dd, NSM},
        {0x17e0, 0x17e9, L},
        {0x180b, 0x180d, NSM},
        {0x180e, 0x180e, WS},
        {0x1810, 0x1819, L},
        {0x1820, 0x1877, L},
        {0x1880, 0x18a8, L},
        {0x18a9, 0x18a9, NSM},
        {0x1900, 0x191c, L},
        {0x1920, 0x1922, NSM},
        {0x1923, 0x1926, L},
        {0x1927, 0x192b, NSM},
        {0x1930, 0x1931, L},
        {0x1932, 0x1932, NSM},
        {0x1933, 0x1938, L},
        {0x1939, 0x193b, NSM},
        {0x1946, 0x196d, L},
        {0x1970, 0x1974, L},
        {0x1d00, 0x1d6b, L},
        {0x1e00, 0x1e9b, L},
        {0x1ea0, 0x1ef9, L},
        {0x1f00, 0x1f15, L},
        {0x1f18, 0x1f1d, L},
        {0x1f20, 0x1f45, L},
        {0x1f48, 0x1f4d, L},
        {0x1f50, 0x1f57, L},
        {0x1f59, 0x1f59, L},
        {0x1f5b, 0x1f5b, L},
        {0x1f5d, 0x1f5d, L},
        {0x1f5f, 0x1f7d, L},
        {0x1f80, 0x1fb4, L},
        {0x1fb6, 0x1fbc, L},
        {0x1fbe, 0x1fbe, L},
        {0x1fc2, 0x1fc4, L},
        {0x1fc6, 0x1fcc, L},
        {0x1fd0, 0x1fd3, L},
        {0x1fd6, 0x1fdb, L},
        {0x1fe0, 0x1fec, L},
        {0x1ff2, 0x1ff4, L},
        {0x1ff6, 0x1ffc, L},
        {0x2000, 0x200a, WS},
        {0x200b, 0x200d, BN},
        {0x200e, 0x200e, L},
        {0x200f, 0x200f, R},
        {0x2028, 0x2028, WS},
        {0x2029, 0x2029, B},
        {0x202a, 0x202a, LRE},
        {0x202b, 0x202b, RLE},
        {0x202c, 0x202c, PDF},
        {0x202d, 0x202d, LRO},
        {0x202e, 0x202e, RLO},
        {0x202f, 0x202f, WS},
        {0x2030, 0x2034, ET},
        {0x2044, 0x2044, CS},
        {0x205f, 0x205f, WS},
        {0x2060, 0x2063, BN},
        {0x206a, 0x206f, BN},
        {0x2070, 0x2070, EN},
        {0x2071, 0x2071, L},
        {0x2074, 0x2079, EN},
        {0x207a, 0x207b, ET},
        {0x207f, 0x207f, L},
        {0x2080, 0x2089, EN},
        {0x208a, 0x208b, ET},
        {0x20a0, 0x20b1, ET},
        {0x20d0, 0x20ea, NSM},
        {0x2102, 0x2102, L},
        {0x2107, 0x2107, L},
        {0x210a, 0x2113, L},
        {0x2115, 0x2115, L},
        {0x2119, 0x211d, L},
        {0x2124, 0x2124, L},
        {0x2126, 0x2126, L},
        {0x2128, 0x2128, L},
        {0x212a, 0x212d, L},
        {0x212e, 0x212e, ET},
        {0x212f, 0x2131, L},
        {0x2133, 0x2139, L},
        {0x213d, 0x213f, L},
        {0x2145, 0x2149, L},
        {0x2160, 0x2183, L},
        {0x2212, 0x2213, ET},
        {0x2336, 0x237a, L},
        {0x2395, 0x2395, L},
        {0x2488, 0x249b, EN},
        {0x249c, 0x24e9, L},
        {0x2800, 0x28ff, L},
        {0x3000, 0x3000, WS},
        {0x3005, 0x3007, L},
        {0x3021, 0x3029, L},
        {0x302a, 0x302f, NSM},
        {0x3031, 0x3035, L},
        {0x3038, 0x303c, L},
        {0x3041, 0x3096, L},
        {0x3099, 0x309a, NSM},
        {0x309d, 0x309f, L},
        {0x30a1, 0x30fa, L},
        {0x30fc, 0x30ff, L},
        {0x3105, 0x312c, L},
        {0x3131, 0x318e, L},
        {0x3190, 0x31b7, L},
        {0x31f0, 0x321c, L},
        {0x3220, 0x3243, L},
        {0x3260, 0x327b, L},
        {0x327f, 0x32b0, L},
        {0x32c0, 0x32cb, L},
        {0x32d0, 0x32fe, L},
        {0x3300, 0x3376, L},
        {0x337b, 0x33dd, L},
        {0x33e0, 0x33fe, L},
        {0x3400, 0x4db5, L},
        {0x4e00, 0x9fa5, L},
        {0xa000, 0xa48c, L},
        {0xac00, 0xd7a3, L},
        {0xd800, 0xfa2d, L},
        {0xfa30, 0xfa6a, L},
        {0xfb00, 0xfb06, L},
        {0xfb13, 0xfb17, L},
        {0xfb1d, 0xfb1d, R},
        {0xfb1e, 0xfb1e, NSM},
        {0xfb1f, 0xfb28, R},
        {0xfb29, 0xfb29, ET},
        {0xfb2a, 0xfb36, R},
        {0xfb38, 0xfb3c, R},
        {0xfb3e, 0xfb3e, R},
        {0xfb40, 0xfb41, R},
        {0xfb43, 0xfb44, R},
        {0xfb46, 0xfb4f, R},
        {0xfb50, 0xfbb1, AL},
        {0xfbd3, 0xfd3d, AL},
        {0xfd50, 0xfd8f, AL},
        {0xfd92, 0xfdc7, AL},
        {0xfdf0, 0xfdfc, AL},
        {0xfe00, 0xfe0f, NSM},
        {0xfe20, 0xfe23, NSM},
        {0xfe50, 0xfe50, CS},
        {0xfe52, 0xfe52, CS},
        {0xfe55, 0xfe55, CS},
        {0xfe5f, 0xfe5f, ET},
        {0xfe62, 0xfe63, ET},
        {0xfe69, 0xfe6a, ET},
        {0xfe70, 0xfe74, AL},
        {0xfe76, 0xfefc, AL},
        {0xfeff, 0xfeff, BN},
        {0xff03, 0xff05, ET},
        {0xff0b, 0xff0b, ET},
        {0xff0c, 0xff0c, CS},
        {0xff0d, 0xff0d, ET},
        {0xff0e, 0xff0e, CS},
        {0xff0f, 0xff0f, ES},
        {0xff10, 0xff19, EN},
        {0xff1a, 0xff1a, CS},
        {0xff21, 0xff3a, L},
        {0xff41, 0xff5a, L},
        {0xff66, 0xffbe, L},
        {0xffc2, 0xffc7, L},
        {0xffca, 0xffcf, L},
        {0xffd2, 0xffd7, L},
        {0xffda, 0xffdc, L},
        {0xffe0, 0xffe1, ET},
        {0xffe5, 0xffe6, ET},
        {0x10000, 0x1000b, L},
        {0x1000d, 0x10026, L},
        {0x10028, 0x1003a, L},
        {0x1003c, 0x1003d, L},
        {0x1003f, 0x1004d, L},
        {0x10050, 0x1005d, L},
        {0x10080, 0x100fa, L},
        {0x10100, 0x10100, L},
        {0x10102, 0x10102, L},
        {0x10107, 0x10133, L},
        {0x10137, 0x1013f, L},
        {0x10300, 0x1031e, L},
        {0x10320, 0x10323, L},
        {0x10330, 0x1034a, L},
        {0x10380, 0x1039d, L},
        {0x1039f, 0x1039f, L},
        {0x10400, 0x1049d, L},
        {0x104a0, 0x104a9, L},
        {0x10800, 0x10805, R},
        {0x10808, 0x10808, R},
        {0x1080a, 0x10835, R},
        {0x10837, 0x10838, R},
        {0x1083c, 0x1083c, R},
        {0x1083f, 0x1083f, R},
        {0x1d000, 0x1d0f5, L},
        {0x1d100, 0x1d126, L},
        {0x1d12a, 0x1d166, L},
        {0x1d167, 0x1d169, NSM},
        {0x1d16a, 0x1d172, L},
        {0x1d173, 0x1d17a, BN},
        {0x1d17b, 0x1d182, NSM},
        {0x1d183, 0x1d184, L},
        {0x1d185, 0x1d18b, NSM},
        {0x1d18c, 0x1d1a9, L},
        {0x1d1aa, 0x1d1ad, NSM},
        {0x1d1ae, 0x1d1dd, L},
        {0x1d400, 0x1d454, L},
        {0x1d456, 0x1d49c, L},
        {0x1d49e, 0x1d49f, L},
        {0x1d4a2, 0x1d4a2, L},
        {0x1d4a5, 0x1d4a6, L},
        {0x1d4a9, 0x1d4ac, L},
        {0x1d4ae, 0x1d4b9, L},
        {0x1d4bb, 0x1d4bb, L},
        {0x1d4bd, 0x1d4c3, L},
        {0x1d4c5, 0x1d505, L},
        {0x1d507, 0x1d50a, L},
        {0x1d50d, 0x1d514, L},
        {0x1d516, 0x1d51c, L},
        {0x1d51e, 0x1d539, L},
        {0x1d53b, 0x1d53e, L},
        {0x1d540, 0x1d544, L},
        {0x1d546, 0x1d546, L},
        {0x1d54a, 0x1d550, L},
        {0x1d552, 0x1d6a3, L},
        {0x1d6a8, 0x1d7c9, L},
        {0x1d7ce, 0x1d7ff, EN},
        {0x20000, 0x2a6d6, L},
        {0x2f800, 0x2fa1d, L},
        {0xe0001, 0xe0001, BN},
        {0xe0020, 0xe007f, BN},
        {0xe0100, 0xe01ef, NSM},
        {0xf0000, 0xffffd, L},
        {0x100000, 0x10fffd, L}
    };

    int i, j, k;

    i = -1;
    j = lenof(lookup);

    while (j - i > 1) {
	k = (i + j) / 2;
	if (ch < lookup[k].first)
	    j = k;
	else if (ch > lookup[k].last)
	    i = k;
	else
	    return lookup[k].type;
    }

    /*
     * If we reach here, the character was not in any of the
     * intervals listed in the lookup table. This means we return
     * ON (`Other Neutrals'). This is the appropriate code for any
     * character genuinely not listed in the Unicode table, and
     * also the table above has deliberately left out any
     * characters _explicitly_ listed as ON (to save space!).
     */
    return ON;
}

/*
 * Function exported to front ends to allow them to identify
 * bidi-active characters (in case, for example, the platform's
 * text display function can't conveniently be prevented from doing
 * its own bidi and so special treatment is required for characters
 * that would cause the bidi algorithm to activate).
 * 
 * This function is passed a single Unicode code point, and returns
 * nonzero if the presence of this code point can possibly cause
 * the bidi algorithm to do any reordering. Thus, any string
 * composed entirely of characters for which is_rtl() returns zero
 * should be safe to pass to a bidi-active platform display
 * function without fear.
 * 
 * (is_rtl() must therefore also return true for any character
 * which would be affected by Arabic shaping, but this isn't
 * important because all such characters are right-to-left so it
 * would have flagged them anyway.)
 */
int is_rtl(int c)
{
    /*
     * After careful reading of the Unicode bidi algorithm (URL as
     * given at the top of this file) I believe that the only
     * character classes which can possibly cause trouble are R,
     * AL, RLE and RLO. I think that any string containing no
     * character in any of those classes will be displayed
     * uniformly left-to-right by the Unicode bidi algorithm.
     */
    const int mask = (1<<R) | (1<<AL) | (1<<RLE) | (1<<RLO);

    return mask & (1 << (getType(c)));
}

/*
 * The most significant 2 bits of each level are used to store
 * Override status of each character
 * This function sets the override bits of level according
 * to the value in override, and reurns the new byte.
 */
unsigned char setOverrideBits(unsigned char level, unsigned char override)
{
    if (override == ON)
	return level;
    else if (override == R)
	return level | OISR;
    else if (override == L)
	return level | OISL;
    return level;
}

/*
 * Find the most recent run of the same value in `level', and
 * return the value _before_ it. Used to process U+202C POP
 * DIRECTIONAL FORMATTING.
 */
int getPreviousLevel(unsigned char* level, int from)
{
    if (from > 0) {
        unsigned char current = level[--from];

        while (from >= 0 && level[from] == current)
            from--;

        if (from >= 0)
            return level[from];

        return -1;
    } else
        return -1;
}