简答

Question

我有兴趣将一些文字设置为UILabel，并取决于语言的方向性（例如，希伯来语 - 从右到左[RTL]，英语 - 从左到右[LTR] ]）设置UILabel的对齐方式。

请注意，使用iOS 6的NSTextAlignmentNatural无法解决问题，因为它根据当前区域设置选择对齐方式，实验显示。

Answer 1

根据建议given in this SO answer结束：编写一个简短的脚本来解析Unicode数据publicly available here，并生成代码以识别代码点是否具有强R或AL方向性属性。然后，在字符串中搜索第一个这样的字符。这正是ICU包中的ubidi_getBaseDirection。

由于NSString的内部表示是UTF16（可变长度编码），因此首先将其转换为UTF32以简化扫描代码。另一种方法是动态解码字符串，这需要处理BOM和Unicode代理。另一种方法是忽略一个unichar无法表示的字符。有关详细信息，请参阅Wikipedia's UTF16 article。

简答

@interface NSString (TextDirectionality)

/* Return 1 if the string is strongly LTR, -1 if strongly RTL, or 0 if neutral. */
/* See http://icu-project.org/apiref/icu4c/ubidi_8h.html#aeb1fd15743833278cc11906cd5a48aef */
-(int)getBaseDirection;

@end

@implementation NSString (TextDirectionality)

// Function takes UTF32 character, and not a unichar (=UTF16 character),
// because some Unicode characters need full 32 bits to represent.
BOOL isCodePointStrongRTL(UTF32Char c) {
  return ((c == 0x5BE) || (c == 0x5C0) || (c == 0x5C3) || (c == 0x5C6) || (c >= 0x5D0 && c <= 0x5EA) || (c >= 0x5F0 && c <= 0x5F4) || (c == 0x608) || (c == 0x60B) || (c == 0x60D) || (c == 0x61B) || (c >= 0x61E && c <= 0x64A) || (c >= 0x66D && c <= 0x66F) || (c >= 0x671 && c <= 0x6D5) || (c >= 0x6E5 && c <= 0x6E6) || (c >= 0x6EE && c <= 0x6EF) || (c >= 0x6FA && c <= 0x70D) || (c >= 0x70F && c <= 0x710) || (c >= 0x712 && c <= 0x72F) || (c >= 0x74D && c <= 0x7A5) || (c == 0x7B1) || (c >= 0x7C0 && c <= 0x7EA) || (c >= 0x7F4 && c <= 0x7F5) || (c == 0x7FA) || (c >= 0x800 && c <= 0x815) || (c == 0x81A) || (c == 0x824) || (c == 0x828) || (c >= 0x830 && c <= 0x83E) || (c >= 0x840 && c <= 0x858) || (c == 0x85E) || (c == 0x8A0) || (c >= 0x8A2 && c <= 0x8AC) || (c == 0x200F) || (c == 0xFB1D) || (c >= 0xFB1F && c <= 0xFB28) || (c >= 0xFB2A && c <= 0xFB36) || (c >= 0xFB38 && c <= 0xFB3C) || (c == 0xFB3E) || (c >= 0xFB40 && c <= 0xFB41) || (c >= 0xFB43 && c <= 0xFB44) || (c >= 0xFB46 && c <= 0xFBC1) || (c >= 0xFBD3 && c <= 0xFD3D) || (c >= 0xFD50 && c <= 0xFD8F) || (c >= 0xFD92 && c <= 0xFDC7) || (c >= 0xFDF0 && c <= 0xFDFC) || (c >= 0xFE70 && c <= 0xFE74) || (c >= 0xFE76 && c <= 0xFEFC) || (c >= 0x10800 && c <= 0x10805) || (c == 0x10808) || (c >= 0x1080A && c <= 0x10835) || (c >= 0x10837 && c <= 0x10838) || (c == 0x1083C) || (c >= 0x1083F && c <= 0x10855) || (c >= 0x10857 && c <= 0x1085F) || (c >= 0x10900 && c <= 0x1091B) || (c >= 0x10920 && c <= 0x10939) || (c == 0x1093F) || (c >= 0x10980 && c <= 0x109B7) || (c >= 0x109BE && c <= 0x109BF) || (c == 0x10A00) || (c >= 0x10A10 && c <= 0x10A13) || (c >= 0x10A15 && c <= 0x10A17) || (c >= 0x10A19 && c <= 0x10A33) || (c >= 0x10A40 && c <= 0x10A47) || (c >= 0x10A50 && c <= 0x10A58) || (c >= 0x10A60 && c <= 0x10A7F) || (c >= 0x10B00 && c <= 0x10B35) || (c >= 0x10B40 && c <= 0x10B55) || (c >= 0x10B58 && c <= 0x10B72) || (c >= 0x10B78 && c <= 0x10B7F) || (c >= 0x10C00 && c <= 0x10C48) || (c >= 0x1EE00 && c <= 0x1EE03) || (c >= 0x1EE05 && c <= 0x1EE1F) || (c >= 0x1EE21 && c <= 0x1EE22) || (c == 0x1EE24) || (c == 0x1EE27) || (c >= 0x1EE29 && c <= 0x1EE32) || (c >= 0x1EE34 && c <= 0x1EE37) || (c == 0x1EE39) || (c == 0x1EE3B) || (c == 0x1EE42) || (c == 0x1EE47) || (c == 0x1EE49) || (c == 0x1EE4B) || (c >= 0x1EE4D && c <= 0x1EE4F) || (c >= 0x1EE51 && c <= 0x1EE52) || (c == 0x1EE54) || (c == 0x1EE57) || (c == 0x1EE59) || (c == 0x1EE5B) || (c == 0x1EE5D) || (c == 0x1EE5F) || (c >= 0x1EE61 && c <= 0x1EE62) || (c == 0x1EE64) || (c >= 0x1EE67 && c <= 0x1EE6A) || (c >= 0x1EE6C && c <= 0x1EE72) || (c >= 0x1EE74 && c <= 0x1EE77) || (c >= 0x1EE79 && c <= 0x1EE7C) || (c == 0x1EE7E) || (c >= 0x1EE80 && c <= 0x1EE89) || (c >= 0x1EE8B && c <= 0x1EE9B) || (c >= 0x1EEA1 && c <= 0x1EEA3) || (c >= 0x1EEA5 && c <= 0x1EEA9) || (c >= 0x1EEAB && c <= 0x1EEBB));
}

BOOL isCodePointStrongLTR(UTF32Char c) {
  return (c >= 0x41 && c <= 0x5A) || (c >= 0x61 && c <= 0x7A) || (c == 0xAA) || (c == 0xB5) || (c == 0xBA) || (c >= 0xC0 && c <= 0xD6) || (c >= 0xD8 && c <= 0xF6) || (c >= 0xF8 && c <= 0x2B8) || (c >= 0x2BB && c <= 0x2C1) || (c >= 0x2D0 && c <= 0x2D1) || (c >= 0x2E0 && c <= 0x2E4) || (c == 0x2EE) || (c >= 0x370 && c <= 0x373) || (c >= 0x376 && c <= 0x377) || (c >= 0x37A && c <= 0x37D) || (c == 0x386) || (c >= 0x388 && c <= 0x38A) || (c == 0x38C) || (c >= 0x38E && c <= 0x3A1) || (c >= 0x3A3 && c <= 0x3F5) || (c >= 0x3F7 && c <= 0x482) || (c >= 0x48A && c <= 0x527) || (c >= 0x531 && c <= 0x556) || (c >= 0x559 && c <= 0x55F) || (c >= 0x561 && c <= 0x587) || (c == 0x589) || (c >= 0x903 && c <= 0x939) || (c == 0x93B) || (c >= 0x93D && c <= 0x940) || (c >= 0x949 && c <= 0x94C) || (c >= 0x94E && c <= 0x950) || (c >= 0x958 && c <= 0x961) || (c >= 0x964 && c <= 0x977) || (c >= 0x979 && c <= 0x97F) || (c >= 0x982 && c <= 0x983) || (c >= 0x985 && c <= 0x98C) || (c >= 0x98F && c <= 0x990) || (c >= 0x993 && c <= 0x9A8) || (c >= 0x9AA && c <= 0x9B0) || (c == 0x9B2) || (c >= 0x9B6 && c <= 0x9B9) || (c >= 0x9BD && c <= 0x9C0) || (c >= 0x9C7 && c <= 0x9C8) || (c >= 0x9CB && c <= 0x9CC) || (c == 0x9CE) || (c == 0x9D7) || (c >= 0x9DC && c <= 0x9DD) || (c >= 0x9DF && c <= 0x9E1) || (c >= 0x9E6 && c <= 0x9F1) || (c >= 0x9F4 && c <= 0x9FA) || (c == 0xA03) || (c >= 0xA05 && c <= 0xA0A) || (c >= 0xA0F && c <= 0xA10) || (c >= 0xA13 && c <= 0xA28) || (c >= 0xA2A && c <= 0xA30) || (c >= 0xA32 && c <= 0xA33) || (c >= 0xA35 && c <= 0xA36) || (c >= 0xA38 && c <= 0xA39) || (c >= 0xA3E && c <= 0xA40) || (c >= 0xA59 && c <= 0xA5C) || (c == 0xA5E) || (c >= 0xA66 && c <= 0xA6F) || (c >= 0xA72 && c <= 0xA74) || (c == 0xA83) || (c >= 0xA85 && c <= 0xA8D) || (c >= 0xA8F && c <= 0xA91) || (c >= 0xA93 && c <= 0xAA8) || (c >= 0xAAA && c <= 0xAB0) || (c >= 0xAB2 && c <= 0xAB3) || (c >= 0xAB5 && c <= 0xAB9) || (c >= 0xABD && c <= 0xAC0) || (c == 0xAC9) || (c >= 0xACB && c <= 0xACC) || (c == 0xAD0) || (c >= 0xAE0 && c <= 0xAE1) || (c >= 0xAE6 && c <= 0xAF0) || (c >= 0xB02 && c <= 0xB03) || (c >= 0xB05 && c <= 0xB0C) || (c >= 0xB0F && c <= 0xB10) || (c >= 0xB13 && c <= 0xB28) || (c >= 0xB2A && c <= 0xB30) || (c >= 0xB32 && c <= 0xB33) || (c >= 0xB35 && c <= 0xB39) || (c >= 0xB3D && c <= 0xB3E) || (c == 0xB40) || (c >= 0xB47 && c <= 0xB48) || (c >= 0xB4B && c <= 0xB4C) || (c == 0xB57) || (c >= 0xB5C && c <= 0xB5D) || (c >= 0xB5F && c <= 0xB61) || (c >= 0xB66 && c <= 0xB77) || (c == 0xB83) || (c >= 0xB85 && c <= 0xB8A) || (c >= 0xB8E && c <= 0xB90) || (c >= 0xB92 && c <= 0xB95) || (c >= 0xB99 && c <= 0xB9A) || (c == 0xB9C) || (c >= 0xB9E && c <= 0xB9F) || (c >= 0xBA3 && c <= 0xBA4) || (c >= 0xBA8 && c <= 0xBAA) || (c >= 0xBAE && c <= 0xBB9) || (c >= 0xBBE && c <= 0xBBF) || (c >= 0xBC1 && c <= 0xBC2) || (c >= 0xBC6 && c <= 0xBC8) || (c >= 0xBCA && c <= 0xBCC) || (c == 0xBD0) || (c == 0xBD7) || (c >= 0xBE6 && c <= 0xBF2) || (c >= 0xC01 && c <= 0xC03) || (c >= 0xC05 && c <= 0xC0C) || (c >= 0xC0E && c <= 0xC10) || (c >= 0xC12 && c <= 0xC28) || (c >= 0xC2A && c <= 0xC33) || (c >= 0xC35 && c <= 0xC39) || (c == 0xC3D) || (c >= 0xC41 && c <= 0xC44) || (c >= 0xC58 && c <= 0xC59) || (c >= 0xC60 && c <= 0xC61) || (c >= 0xC66 && c <= 0xC6F) || (c == 0xC7F) || (c >= 0xC82 && c <= 0xC83) || (c >= 0xC85 && c <= 0xC8C) || (c >= 0xC8E && c <= 0xC90) || (c >= 0xC92 && c <= 0xCA8) || (c >= 0xCAA && c <= 0xCB3) || (c >= 0xCB5 && c <= 0xCB9) || (c >= 0xCBD && c <= 0xCC4) || (c >= 0xCC6 && c <= 0xCC8) || (c >= 0xCCA && c <= 0xCCB) || (c >= 0xCD5 && c <= 0xCD6) || (c == 0xCDE) || (c >= 0xCE0 && c <= 0xCE1) || (c >= 0xCE6 && c <= 0xCEF) || (c >= 0xCF1 && c <= 0xCF2) || (c >= 0xD02 && c <= 0xD03) || (c >= 0xD05 && c <= 0xD0C) || (c >= 0xD0E && c <= 0xD10) || (c >= 0xD12 && c <= 0xD3A) || (c >= 0xD3D && c <= 0xD40) || (c >= 0xD46 && c <= 0xD48) || (c >= 0xD4A && c <= 0xD4C) || (c == 0xD4E) || (c == 0xD57) || (c >= 0xD60 && c <= 0xD61) || (c >= 0xD66 && c <= 0xD75) || (c >= 0xD79 && c <= 0xD7F) || (c >= 0xD82 && c <= 0xD83) || (c >= 0xD85 && c <= 0xD96) || (c >= 0xD9A && c <= 0xDB1) || (c >= 0xDB3 && c <= 0xDBB) || (c == 0xDBD) || (c >= 0xDC0 && c <= 0xDC6) || (c >= 0xDCF && c <= 0xDD1) || (c >= 0xDD8 && c <= 0xDDF) || (c >= 0xDF2 && c <= 0xDF4) || (c >= 0xE01 && c <= 0xE30) || (c >= 0xE32 && c <= 0xE33) || (c >= 0xE40 && c <= 0xE46) || (c >= 0xE4F && c <= 0xE5B) || (c >= 0xE81 && c <= 0xE82) || (c == 0xE84) || (c >= 0xE87 && c <= 0xE88) || (c == 0xE8A) || (c == 0xE8D) || (c >= 0xE94 && c <= 0xE97) || (c >= 0xE99 && c <= 0xE9F) || (c >= 0xEA1 && c <= 0xEA3) || (c == 0xEA5) || (c == 0xEA7) || (c >= 0xEAA && c <= 0xEAB) || (c >= 0xEAD && c <= 0xEB0) || (c >= 0xEB2 && c <= 0xEB3) || (c == 0xEBD) || (c >= 0xEC0 && c <= 0xEC4) || (c == 0xEC6) || (c >= 0xED0 && c <= 0xED9) || (c >= 0xEDC && c <= 0xEDF) || (c >= 0xF00 && c <= 0xF17) || (c >= 0xF1A && c <= 0xF34) || (c == 0xF36) || (c == 0xF38) || (c >= 0xF3E && c <= 0xF47) || (c >= 0xF49 && c <= 0xF6C) || (c == 0xF7F) || (c == 0xF85) || (c >= 0xF88 && c <= 0xF8C) || (c >= 0xFBE && c <= 0xFC5) || (c >= 0xFC7 && c <= 0xFCC) || (c >= 0xFCE && c <= 0xFDA) || (c >= 0x1000 && c <= 0x102C) || (c == 0x1031) || (c == 0x1038) || (c >= 0x103B && c <= 0x103C) || (c >= 0x103F && c <= 0x1057) || (c >= 0x105A && c <= 0x105D) || (c >= 0x1061 && c <= 0x1070) || (c >= 0x1075 && c <= 0x1081) || (c >= 0x1083 && c <= 0x1084) || (c >= 0x1087 && c <= 0x108C) || (c >= 0x108E && c <= 0x109C) || (c >= 0x109E && c <= 0x10C5) || (c == 0x10C7) || (c == 0x10CD) || (c >= 0x10D0 && c <= 0x1248) || (c >= 0x124A && c <= 0x124D) || (c >= 0x1250 && c <= 0x1256) || (c == 0x1258) || (c >= 0x125A && c <= 0x125D) || (c >= 0x1260 && c <= 0x1288) || (c >= 0x128A && c <= 0x128D) || (c >= 0x1290 && c <= 0x12B0) || (c >= 0x12B2 && c <= 0x12B5) || (c >= 0x12B8 && c <= 0x12BE) || (c == 0x12C0) || (c >= 0x12C2 && c <= 0x12C5) || (c >= 0x12C8 && c <= 0x12D6) || (c >= 0x12D8 && c <= 0x1310) || (c >= 0x1312 && c <= 0x1315) || (c >= 0x1318 && c <= 0x135A) || (c >= 0x1360 && c <= 0x137C) || (c >= 0x1380 && c <= 0x138F) || (c >= 0x13A0 && c <= 0x13F4) || (c >= 0x1401 && c <= 0x167F) || (c >= 0x1681 && c <= 0x169A) || (c >= 0x16A0 && c <= 0x16F0) || (c >= 0x1700 && c <= 0x170C) || (c >= 0x170E && c <= 0x1711) || (c >= 0x1720 && c <= 0x1731) || (c >= 0x1735 && c <= 0x1736) || (c >= 0x1740 && c <= 0x1751) || (c >= 0x1760 && c <= 0x176C) || (c >= 0x176E && c <= 0x1770) || (c >= 0x1780 && c <= 0x17B3) || (c == 0x17B6) || (c >= 0x17BE && c <= 0x17C5) || (c >= 0x17C7 && c <= 0x17C8) || (c >= 0x17D4 && c <= 0x17DA) || (c == 0x17DC) || (c >= 0x17E0 && c <= 0x17E9) || (c >= 0x1810 && c <= 0x1819) || (c >= 0x1820 && c <= 0x1877) || (c >= 0x1880 && c <= 0x18A8) || (c == 0x18AA) || (c >= 0x18B0 && c <= 0x18F5) || (c >= 0x1900 && c <= 0x191C) || (c >= 0x1923 && c <= 0x1926) || (c >= 0x1929 && c <= 0x192B) || (c >= 0x1930 && c <= 0x1931) || (c >= 0x1933 && c <= 0x1938) || (c >= 0x1946 && c <= 0x196D) || (c >= 0x1970 && c <= 0x1974) || (c >= 0x1980 && c <= 0x19AB) || (c >= 0x19B0 && c <= 0x19C9) || (c >= 0x19D0 && c <= 0x19DA) || (c >= 0x1A00 && c <= 0x1A16) || (c >= 0x1A19 && c <= 0x1A1B) || (c >= 0x1A1E && c <= 0x1A55) || (c == 0x1A57) || (c == 0x1A61) || (c >= 0x1A63 && c <= 0x1A64) || (c >= 0x1A6D && c <= 0x1A72) || (c >= 0x1A80 && c <= 0x1A89) || (c >= 0x1A90 && c <= 0x1A99) || (c >= 0x1AA0 && c <= 0x1AAD) || (c >= 0x1B04 && c <= 0x1B33) || (c == 0x1B35) || (c == 0x1B3B) || (c >= 0x1B3D && c <= 0x1B41) || (c >= 0x1B43 && c <= 0x1B4B) || (c >= 0x1B50 && c <= 0x1B6A) || (c >= 0x1B74 && c <= 0x1B7C) || (c >= 0x1B82 && c <= 0x1BA1) || (c >= 0x1BA6 && c <= 0x1BA7) || (c == 0x1BAA) || (c >= 0x1BAC && c <= 0x1BE5) || (c == 0x1BE7) || (c >= 0x1BEA && c <= 0x1BEC) || (c == 0x1BEE) || (c >= 0x1BF2 && c <= 0x1BF3) || (c >= 0x1BFC && c <= 0x1C2B) || (c >= 0x1C34 && c <= 0x1C35) || (c >= 0x1C3B && c <= 0x1C49) || (c >= 0x1C4D && c <= 0x1C7F) || (c >= 0x1CC0 && c <= 0x1CC7) || (c == 0x1CD3) || (c == 0x1CE1) || (c >= 0x1CE9 && c <= 0x1CEC) || (c >= 0x1CEE && c <= 0x1CF3) || (c >= 0x1CF5 && c <= 0x1CF6) || (c >= 0x1D00 && c <= 0x1DBF) || (c >= 0x1E00 && c <= 0x1F15) || (c >= 0x1F18 && c <= 0x1F1D) || (c >= 0x1F20 && c <= 0x1F45) || (c >= 0x1F48 && c <= 0x1F4D) || (c >= 0x1F50 && c <= 0x1F57) || (c == 0x1F59) || (c == 0x1F5B) || (c == 0x1F5D) || (c >= 0x1F5F && c <= 0x1F7D) || (c >= 0x1F80 && c <= 0x1FB4) || (c >= 0x1FB6 && c <= 0x1FBC) || (c == 0x1FBE) || (c >= 0x1FC2 && c <= 0x1FC4) || (c >= 0x1FC6 && c <= 0x1FCC) || (c >= 0x1FD0 && c <= 0x1FD3) || (c >= 0x1FD6 && c <= 0x1FDB) || (c >= 0x1FE0 && c <= 0x1FEC) || (c >= 0x1FF2 && c <= 0x1FF4) || (c >= 0x1FF6 && c <= 0x1FFC) || (c == 0x200E) || (c == 0x2071) || (c == 0x207F) || (c >= 0x2090 && c <= 0x209C) || (c == 0x2102) || (c == 0x2107) || (c >= 0x210A && c <= 0x2113) || (c == 0x2115) || (c >= 0x2119 && c <= 0x211D) || (c == 0x2124) || (c == 0x2126) || (c == 0x2128) || (c >= 0x212A && c <= 0x212D) || (c >= 0x212F && c <= 0x2139) || (c >= 0x213C && c <= 0x213F) || (c >= 0x2145 && c <= 0x2149) || (c >= 0x214E && c <= 0x214F) || (c >= 0x2160 && c <= 0x2188) || (c >= 0x2336 && c <= 0x237A) || (c == 0x2395) || (c >= 0x249C && c <= 0x24E9) || (c == 0x26AC) || (c >= 0x2800 && c <= 0x28FF) || (c >= 0x2C00 && c <= 0x2C2E) || (c >= 0x2C30 && c <= 0x2C5E) || (c >= 0x2C60 && c <= 0x2CE4) || (c >= 0x2CEB && c <= 0x2CEE) || (c >= 0x2CF2 && c <= 0x2CF3) || (c >= 0x2D00 && c <= 0x2D25) || (c == 0x2D27) || (c == 0x2D2D) || (c >= 0x2D30 && c <= 0x2D67) || (c >= 0x2D6F && c <= 0x2D70) || (c >= 0x2D80 && c <= 0x2D96) || (c >= 0x2DA0 && c <= 0x2DA6) || (c >= 0x2DA8 && c <= 0x2DAE) || (c >= 0x2DB0 && c <= 0x2DB6) || (c >= 0x2DB8 && c <= 0x2DBE) || (c >= 0x2DC0 && c <= 0x2DC6) || (c >= 0x2DC8 && c <= 0x2DCE) || (c >= 0x2DD0 && c <= 0x2DD6) || (c >= 0x2DD8 && c <= 0x2DDE) || (c >= 0x3005 && c <= 0x3007) || (c >= 0x3021 && c <= 0x3029) || (c >= 0x302E && c <= 0x302F) || (c >= 0x3031 && c <= 0x3035) || (c >= 0x3038 && c <= 0x303C) || (c >= 0x3041 && c <= 0x3096) || (c >= 0x309D && c <= 0x309F) || (c >= 0x30A1 && c <= 0x30FA) || (c >= 0x30FC && c <= 0x30FF) || (c >= 0x3105 && c <= 0x312D) || (c >= 0x3131 && c <= 0x318E) || (c >= 0x3190 && c <= 0x31BA) || (c >= 0x31F0 && c <= 0x321C) || (c >= 0x3220 && c <= 0x324F) || (c >= 0x3260 && c <= 0x327B) || (c >= 0x327F && c <= 0x32B0) || (c >= 0x32C0 && c <= 0x32CB) || (c >= 0x32D0 && c <= 0x32FE) || (c >= 0x3300 && c <= 0x3376) || (c >= 0x337B && c <= 0x33DD) || (c >= 0x33E0 && c <= 0x33FE) || (c == 0x3400) || (c == 0x4DB5) || (c == 0x4E00) || (c == 0x9FCC) || (c >= 0xA000 && c <= 0xA48C) || (c >= 0xA4D0 && c <= 0xA60C) || (c >= 0xA610 && c <= 0xA62B) || (c >= 0xA640 && c <= 0xA66E) || (c >= 0xA680 && c <= 0xA697) || (c >= 0xA6A0 && c <= 0xA6EF) || (c >= 0xA6F2 && c <= 0xA6F7) || (c >= 0xA722 && c <= 0xA787) || (c >= 0xA789 && c <= 0xA78E) || (c >= 0xA790 && c <= 0xA793) || (c >= 0xA7A0 && c <= 0xA7AA) || (c >= 0xA7F8 && c <= 0xA801) || (c >= 0xA803 && c <= 0xA805) || (c >= 0xA807 && c <= 0xA80A) || (c >= 0xA80C && c <= 0xA824) || (c == 0xA827) || (c >= 0xA830 && c <= 0xA837) || (c >= 0xA840 && c <= 0xA873) || (c >= 0xA880 && c <= 0xA8C3) || (c >= 0xA8CE && c <= 0xA8D9) || (c >= 0xA8F2 && c <= 0xA8FB) || (c >= 0xA900 && c <= 0xA925) || (c >= 0xA92E && c <= 0xA946) || (c >= 0xA952 && c <= 0xA953) || (c >= 0xA95F && c <= 0xA97C) || (c >= 0xA983 && c <= 0xA9B2) || (c >= 0xA9B4 && c <= 0xA9B5) || (c >= 0xA9BA && c <= 0xA9BB) || (c >= 0xA9BD && c <= 0xA9CD) || (c >= 0xA9CF && c <= 0xA9D9) || (c >= 0xA9DE && c <= 0xA9DF) || (c >= 0xAA00 && c <= 0xAA28) || (c >= 0xAA2F && c <= 0xAA30) || (c >= 0xAA33 && c <= 0xAA34) || (c >= 0xAA40 && c <= 0xAA42) || (c >= 0xAA44 && c <= 0xAA4B) || (c == 0xAA4D) || (c >= 0xAA50 && c <= 0xAA59) || (c >= 0xAA5C && c <= 0xAA7B) || (c >= 0xAA80 && c <= 0xAAAF) || (c == 0xAAB1) || (c >= 0xAAB5 && c <= 0xAAB6) || (c >= 0xAAB9 && c <= 0xAABD) || (c == 0xAAC0) || (c == 0xAAC2) || (c >= 0xAADB && c <= 0xAAEB) || (c >= 0xAAEE && c <= 0xAAF5) || (c >= 0xAB01 && c <= 0xAB06) || (c >= 0xAB09 && c <= 0xAB0E) || (c >= 0xAB11 && c <= 0xAB16) || (c >= 0xAB20 && c <= 0xAB26) || (c >= 0xAB28 && c <= 0xAB2E) || (c >= 0xABC0 && c <= 0xABE4) || (c >= 0xABE6 && c <= 0xABE7) || (c >= 0xABE9 && c <= 0xABEC) || (c >= 0xABF0 && c <= 0xABF9) || (c == 0xAC00) || (c == 0xD7A3) || (c >= 0xD7B0 && c <= 0xD7C6) || (c >= 0xD7CB && c <= 0xD7FB) || (c == 0xD800) || (c >= 0xDB7F && c <= 0xDB80) || (c >= 0xDBFF && c <= 0xDC00) || (c >= 0xDFFF && c <= 0xE000) || (c >= 0xF8FF && c <= 0xFA6D) || (c >= 0xFA70 && c <= 0xFAD9) || (c >= 0xFB00 && c <= 0xFB06) || (c >= 0xFB13 && c <= 0xFB17) || (c >= 0xFF21 && c <= 0xFF3A) || (c >= 0xFF41 && c <= 0xFF5A) || (c >= 0xFF66 && c <= 0xFFBE) || (c >= 0xFFC2 && c <= 0xFFC7) || (c >= 0xFFCA && c <= 0xFFCF) || (c >= 0xFFD2 && c <= 0xFFD7) || (c >= 0xFFDA && c <= 0xFFDC) || (c >= 0x10000 && c <= 0x1000B) || (c >= 0x1000D && c <= 0x10026) || (c >= 0x10028 && c <= 0x1003A) || (c >= 0x1003C && c <= 0x1003D) || (c >= 0x1003F && c <= 0x1004D) || (c >= 0x10050 && c <= 0x1005D) || (c >= 0x10080 && c <= 0x100FA) || (c == 0x10100) || (c == 0x10102) || (c >= 0x10107 && c <= 0x10133) || (c >= 0x10137 && c <= 0x1013F) || (c >= 0x101D0 && c <= 0x101FC) || (c >= 0x10280 && c <= 0x1029C) || (c >= 0x102A0 && c <= 0x102D0) || (c >= 0x10300 && c <= 0x1031E) || (c >= 0x10320 && c <= 0x10323) || (c >= 0x10330 && c <= 0x1034A) || (c >= 0x10380 && c <= 0x1039D) || (c >= 0x1039F && c <= 0x103C3) || (c >= 0x103C8 && c <= 0x103D5) || (c >= 0x10400 && c <= 0x1049D) || (c >= 0x104A0 && c <= 0x104A9) || (c == 0x11000) || (c >= 0x11002 && c <= 0x11037) || (c >= 0x11047 && c <= 0x1104D) || (c >= 0x11066 && c <= 0x1106F) || (c >= 0x11082 && c <= 0x110B2) || (c >= 0x110B7 && c <= 0x110B8) || (c >= 0x110BB && c <= 0x110C1) || (c >= 0x110D0 && c <= 0x110E8) || (c >= 0x110F0 && c <= 0x110F9) || (c >= 0x11103 && c <= 0x11126) || (c == 0x1112C) || (c >= 0x11136 && c <= 0x11143) || (c >= 0x11182 && c <= 0x111B5) || (c >= 0x111BF && c <= 0x111C8) || (c >= 0x111D0 && c <= 0x111D9) || (c >= 0x11680 && c <= 0x116AA) || (c == 0x116AC) || (c >= 0x116AE && c <= 0x116AF) || (c == 0x116B6) || (c >= 0x116C0 && c <= 0x116C9) || (c >= 0x12000 && c <= 0x1236E) || (c >= 0x12400 && c <= 0x12462) || (c >= 0x12470 && c <= 0x12473) || (c >= 0x13000 && c <= 0x1342E) || (c >= 0x16800 && c <= 0x16A38) || (c >= 0x16F00 && c <= 0x16F44) || (c >= 0x16F50 && c <= 0x16F7E) || (c >= 0x16F93 && c <= 0x16F9F) || (c >= 0x1B000 && c <= 0x1B001) || (c >= 0x1D000 && c <= 0x1D0F5) || (c >= 0x1D100 && c <= 0x1D126) || (c >= 0x1D129 && c <= 0x1D166) || (c >= 0x1D16A && c <= 0x1D172) || (c >= 0x1D183 && c <= 0x1D184) || (c >= 0x1D18C && c <= 0x1D1A9) || (c >= 0x1D1AE && c <= 0x1D1DD) || (c >= 0x1D360 && c <= 0x1D371) || (c >= 0x1D400 && c <= 0x1D454) || (c >= 0x1D456 && c <= 0x1D49C) || (c >= 0x1D49E && c <= 0x1D49F) || (c == 0x1D4A2) || (c >= 0x1D4A5 && c <= 0x1D4A6) || (c >= 0x1D4A9 && c <= 0x1D4AC) || (c >= 0x1D4AE && c <= 0x1D4B9) || (c == 0x1D4BB) || (c >= 0x1D4BD && c <= 0x1D4C3) || (c >= 0x1D4C5 && c <= 0x1D505) || (c >= 0x1D507 && c <= 0x1D50A) || (c >= 0x1D50D && c <= 0x1D514) || (c >= 0x1D516 && c <= 0x1D51C) || (c >= 0x1D51E && c <= 0x1D539) || (c >= 0x1D53B && c <= 0x1D53E) || (c >= 0x1D540 && c <= 0x1D544) || (c == 0x1D546) || (c >= 0x1D54A && c <= 0x1D550) || (c >= 0x1D552 && c <= 0x1D6A5) || (c >= 0x1D6A8 && c <= 0x1D6DA) || (c >= 0x1D6DC && c <= 0x1D714) || (c >= 0x1D716 && c <= 0x1D74E) || (c >= 0x1D750 && c <= 0x1D788) || (c >= 0x1D78A && c <= 0x1D7C2) || (c >= 0x1D7C4 && c <= 0x1D7CB) || (c >= 0x1F110 && c <= 0x1F12E) || (c >= 0x1F130 && c <= 0x1F169) || (c >= 0x1F170 && c <= 0x1F19A) || (c >= 0x1F1E6 && c <= 0x1F202) || (c >= 0x1F210 && c <= 0x1F23A) || (c >= 0x1F240 && c <= 0x1F248) || (c >= 0x1F250 && c <= 0x1F251) || (c == 0x20000) || (c == 0x2A6D6) || (c == 0x2A700) || (c == 0x2B734) || (c == 0x2B740) || (c == 0x2B81D) || (c >= 0x2F800 && c <= 0x2FA1D) || (c == 0xF0000) || (c == 0xFFFFD) || (c == 0x100000) || (c == 0x10FFFD);
}   

-(int)getBaseDirection {
  // Decode string into UTF32.
  NSData *utf32data = [self dataUsingEncoding:NSUTF32StringEncoding];
  // NSUTF32StringEncoding has the platform's byte-order, which should
  // be the same as UTF32Char's.
  UTF32Char *utf32chars = (UTF32Char *)[utf32data bytes];

  for (NSUInteger i = 0; i < self.length; i++) {
    // UTF32 is a fixed-length encoding, so utf32chars[i] will
    // always give us the i'th character.
    if (isCodePointStrongRTL(utf32chars[i]))
      return -1;
    if (isCodePointStrongLTR(utf32chars[i]))
      return 1;
  }
  return 0;
}

@end

更长的答案：生成函数`isCodePointStrong{RTL,LTR}`

创建脚本hex_numbers_to_dec_ranges_py，

import sys
from itertools import groupby, count

numberlist = []
for line in sys.stdin:
    numberlist.append(int(line, 16));

def as_range(iterable): # not sure how to do this part elegantly
    l = list(iterable)
    if len(l) > 1:
        return '(c >= 0x{0:X} && c <= 0x{1:X})'.format(l[0], l[-1])
    else:
        return '(c == 0x{0:X})'.format(l[0])

print ' || '.join(as_range(g) for _, g in groupby(numberlist, lambda n, c=count(): n-next(c)))

（从this excellent answer at StackExhange's Code Review无耻地窃取的代码。）

从终端运行：

curl http://www.unicode.org/Public/UNIDATA/UnicodeData.txt > /tmp/UnicodeData.txt
cat /tmp/UnicodeData.txt | awk -F';' '$5 == "R" || $5 == "AL"' | cut -d';' -f1 | python hex_numbers_to_dec_ranges.py > rtl.m
cat /tmp/UnicodeData.txt | awk -F';' '$5 == "L"' | cut -d';' -f1 | python hex_numbers_to_dec_ranges.py > ltr.m
rm /tmp/UnicodeData.txt

编辑：正如@masmor正确指出的那样，for中的getBaseDirection循环会扫描字符，而不是字节。因此，它应该在“字符”迭代次数之后终止，而不是“字节”迭代次数。换句话说，self.length次，而不是utf32data.length次。代码现已更正。

Answer 2

我认为-getBaseDirection中的扫描循环应该在接受的答案中为self.length次，而不是utf32data.length。

utf32data.length是sizeof(UTF32Char) == 4的大小（以字节为单位），这会导致超支。

在行动中，当前代码偶尔会返回相同输入的误报，具体取决于它超出的范围（也许它会在足够糟糕的一天发生段错误）。其他所有东西似乎都与修复完美配合。

Answer 3

在HTML5中，可以通过将dir =“auto”应用于元素来完成。它是在WebKit中实现的，虽然我不完全确定它在iOS中可用。

dir =“auto”非常简单，您可以自己实现它 - 只需搜索具有强方向性的第一个角色，并将其方向性应用于整个角色。

如果您在iOS中找不到任何内容，可以尝试从StatusNet实现它的方式中获取一些更聪明的想法：http://status.net/sites/default/files/issues/1346_jquery.directionDetector.js

Answer 4

有一种基于language detection of the string的解决方案。

如果无法确定方向，则方法返回NSTextAlignmentNatural。

@implementation NSString (StringAlignmentDetection)

- (NSTextAlignment)naturalTextAligment
{
    NSArray *tagschemes = [NSArray arrayWithObjects:NSLinguisticTagSchemeLanguage, nil];
    NSLinguisticTagger *tagger = [[NSLinguisticTagger alloc] initWithTagSchemes:tagschemes options:0];
    [tagger setString:self];
    NSString *language = [tagger tagAtIndex:0 scheme:NSLinguisticTagSchemeLanguage tokenRange:NULL sentenceRange:NULL];

    NSTextAlignment alignment = NSTextAlignmentNatural;

    if(!language)
    {
        return alignment;
    }

    NSLocaleLanguageDirection direction = [NSLocale characterDirectionForLanguage: language];

    switch (direction)
    {
        case NSLocaleLanguageDirectionLeftToRight:
            alignment = NSTextAlignmentLeft;
            break;

        case NSLocaleLanguageDirectionRightToLeft:
            alignment = NSTextAlignmentRight;
            break;

        default:
            alignment = NSTextAlignmentNatural;
            break;
    }

    return alignment;
}

@end

Answer 5

ICU Project提供了您要实现的目标的方法，在Xcode 11上，可以将ICU库链接到iOS应用程序或iOS框架目标中。为此，请打开目标，然后在“框架和库”下的“常规”选项卡上添加libicucore.tbd。

如果这样做，Xcode可能会选择该库的macOS变体，在这种情况下，您会在项目文件中看到类似的内容。

ABCDEFGHIJKLMNOPQRSTUVWX /* libicucore.tbd */ = {isa = PBXFileReference; lastKnownFileType = "sourcecode.text-based-dylib-definition"; name = libicucore.tbd; path = Platforms/MacOSX.platform/Developer/SDKs/MacOSX10.15.sdk/usr/lib/libicucore.tbd; sourceTree = DEVELOPER_DIR; };

要强制使用iOS版本，只需使用文本编辑器编辑项目文件，使该行看起来像这样

ABCDEFGHIJKLMNOPQRSTUVWX /* libicucore.tbd */ = {isa = PBXFileReference; lastKnownFileType = "sourcecode.text-based-dylib-definition"; name = libicucore.tbd; path = usr/lib/libicucore.tbd; sourceTree = SDKROOT; };

不幸的是，iOS附带的库版本较旧，并且不包含ubidi_getBaseDirection。但是，有一种方法u_charDirection可用于重建ubidi_getBaseDirection。只需在字符串中移动字符，并以强烈的方向性返回第一个字符的方向。下面是一个如何在Swift中执行此操作的示例（Objective-C端口应该很简单）。

enum Direction {
    case leftToRight
    case rightToLeft
    case neutral
}

func ubidi_getBaseDirection(of string: String) -> Direction {
    guard let data = string.data(using: .utf32) else {
        return .leftToRight
    }
    let chars = data.withUnsafeBytes { $0.bindMemory(to: UChar32.self) }
    for c in chars {
        let direction = u_charDirection(c)
        if direction == U_RIGHT_TO_LEFT || direction == U_RIGHT_TO_LEFT_ARABIC {
            return .rightToLeft
        } else if direction == U_LEFT_TO_RIGHT {
            return .leftToRight
        }
    }
    return .neutral
}

请注意，由于libicucore是纯C库，因此如果您在Swift中工作，则需要将其添加到桥接标头/伞形标头中。我发现以下内容已足够。

#include "unicode/utypes.h"

根据文本语言自动对齐UILabel中的文本

5 个答案:

简答

更长的答案：生成函数`isCodePointStrong{RTL,LTR}`

根据文本语言自动对齐UILabel中的文本

5 个答案:

简答

更长的答案：生成函数isCodePointStrong{RTL,LTR}

更长的答案：生成函数`isCodePointStrong{RTL,LTR}`