让我们假设我有一个UTF-8编码的std::string，其中包含以下内容：
óó
我想将它转换为以下内容：
ÓÓ
0xc3b3c3b3（每个字符两个字节，两个ó实例），我希望输出为0xc393c393（两个Ó实例）。StackOverflow上有一些示例，但它们使用宽字符字符串，而其他答案则表示您不应该使用宽字符字符串来处理UTF-8。此外，这个问题似乎非常“棘手”，因为输出可能取决于用户的语言环境。std::toupper()的东西，但是我对其使用感到非常不清楚，因为它似乎不仅仅转换一个字符，而是整个字符串。此外，我编写的Ideone example似乎表明，toupper()将0xc3b3转换为0xc3b3，这是一个意外的结果。无论是将setlocale设置为UTF-8还是ISO8859-1都没有改变结果。
如果你能指导我，让我知道我做错了什么或者我的问题/前提有什么问题，我会非常感激！
在C++中，没有标准的Unicode大小写转换方法。尽管有一些方法可用于某些C++实现，但标准并不要求它们。
如果您想保证Unicode大小写转换，则需要使用类似ICU或Boost.Locale（即具有更类似于C++界面的ICU）的库。
wstring 方法不起作用吗？ - aardvarkken_US.UTF-8，或者实现不使用Unicode格式的wchar_t，标准中并没有保证这两个条件。宽字符和窄字符一样是由实现定义的。另外，另一个答案也没有使用你要求的UTF-8编码。 - Nicol Bolastowupper/lower无法逐个字符地工作，因为有时一个字符的小写版本实际上是两个字符。因此，这些函数在Unicode中的API本质上是错误的。 - Nicol Bolas这段代码是经过仔细测试的 UTF8 大小写转换和大小写不敏感比较。
它应该是正确的（如果发现任何错误，请告诉我们）。
此函数涵盖了 UTF8 中区分大小写的字符集以及如何将其用于比较。
unsigned char* StrToUprExt(unsigned char* pString) (separate answer below, answer space)
unsigned char* StrToLwrExt(unsigned char* pString)
int StrnCiCmp(const char* s1, const char* s2, size_t ztCount)
int StrCiCmp(const char* s1, const char* s2)
char* StrCiStr(const char* s1, const char* s2)
ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞĀĂĄĆĈĊČĎĐĒĔĖĘĚĜĞĠĢĤĦĨĪĬĮİIJĴĶĹĻĽĿŁŃŅŇŊŌŎŐŒŔŖŘŚŜŞŠŢŤŦŨŪŬŮŰŲŴŶŸŹŻŽƁƂƄƆƇƊƋƎƏƐƑƓƔƖƗƘƜƝƠƢƤƧƩƬƮƯƱƲƳƵƷƸƼDŽDžLJLjNJNjǍǏǑǓǕǗǙǛǞǠǢǤǦǨǪǬǮDZDzǴǶǷǸǺǼǾȀȂȄȆȈȊȌȎȐȒȔȖȘȚȜȞȠȢȤȦȨȪȬȮȰȲȺȻȽȾɁɃɄɅɆɈɊɌɎͰͲͶͿΆΈΉΊΌΎΏΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΪΫϏϘϚϜϞϠϢϤϦϨϪϬϮϴϷϹϺϽϾϿЀЁЂЃЄЅІЇЈЉЊЋЌЍЎЏАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯѠѢѤѦѨѪѬѮѰѲѴѶѸѺѼѾҀҊҌҎҐҒҔҖҘҚҜҞҠҢҤҦҨҪҬҮҰҲҴҶҸҺҼҾӀӁӃӅӇӉӋӍӐӒӔӖӘӚӜӞӠӢӤӦӨӪӬӮӰӲӴӶӸӺӼӾԀԂԄԆԈԊԌԎԐԒԔԖԘԚԜԞԠԢԤԦԨԪԬԮԱԲԳԴԵԶԷԸԹԺԻԼԽԾԿՀՁՂՃՄՅՆՇՈՉՊՋՌՍՎՏՐՑՒՓՔՕՖႠႡႢႣႤႥႦႧႨႩႪႫႬႭႮႯႰႱႲႳႴႵႶႷႸႹႺႻႼႽႾႿჀჁჂჃჄჅჇჍᎠᎡᎢᎣᎤᎥᎦᎧᎨᎩᎪᎫᎬᎭᎮᎯᎰᎱᎲᎳᎴᎵᎶᎷᎸᎹᎺᎻᎼᎽᎾᎿᏀᏁᏂᏃᏄᏅᏆᏇᏈᏉᏊᏋᏌᏍᏎᏏᏐᏑᏒᏓᏔᏕᏖᏗᏘᏙᏚᏛᏜᏝᏞᏟᏠᏡᏢᏣᏤᏥᏦᏧᏨᏩᏪᏫᏬᏭᏮᏯᏰᏱᏲᏳᏴᏵᲐᲑᲒᲓᲔᲕᲖᲗᲘᲙᲚᲛᲜᲝᲞᲟᲠᲡᲢᲣᲤᲥᲦᲧᲨᲩᲪᲫᲬᲭᲮᲯᲰᲱᲲᲳᲴᲵᲶᲷᲸᲹᲺᲽᲾᲿḀḂḄḆḈḊḌḎḐḒḔḖḘḚḜḞḠḢḤḦḨḪḬḮḰḲḴḶḸḺḼḾṀṂṄṆṈṊṌṎṐṒṔṖṘṚṜṞṠṢṤṦṨṪṬṮṰṲṴṶṸṺṼṾẀẂẄẆẈẊẌẎẐẒẔẞẠẢẤẦẨẪẬẮẰẲẴẶẸẺẼẾỀỂỄỆỈỊỌỎỐỒỔỖỘỚỜỞỠỢỤỦỨỪỬỮỰỲỴỶỸỺỼỾἈἉἊἋἌἍἎἏἘἙἚἛἜἝἨἩἪἫἬἭἮἯἸἹἺἻἼἽἾἿὈὉὊὋὌὍὙὛὝὟὨὩὪὫὬὭὮὯᾈᾉᾊᾋᾌᾍᾎᾏᾘᾙᾚᾛᾜᾝᾞᾟᾨᾩᾪᾫᾬᾭᾮᾯᾸᾹᾺΆᾼῈΈῊΉῌῘῙῚΊῨῩῪΎῬῸΌῺΏῼⰀⰁⰂⰃⰄⰅⰆⰇⰈⰉⰊⰋⰌⰍⰎⰏⰐⰑⰒⰓⰔⰕⰖⰗⰘⰙⰚⰛⰜⰝⰞⰟⰠⰡⰢⰣⰤⰥⰦⰧⰨⰩⰪⰫⰬⰭⰮⱠⱢⱣⱤⱧⱩⱫⱭⱮⱯⱰⱲⱵⱾⱿⲀⲂⲄⲆⲈⲊⲌⲎⲐⲒⲔⲖⲘⲚⲜⲞⲠⲢⲤⲦⲨⲪⲬⲮⲰⲲⲴⲶⲸⲺⲼⲾⳀⳂⳄⳆⳈⳊⳌⳎⳐⳒⳔⳖⳘⳚⳜⳞⳠⳢⳫⳭⳲⴀⴁⴂⴃⴄⴅⴆⴇⴈⴉⴊⴋⴌⴍⴎⴏⴐⴑⴒⴓⴔⴕⴖⴗⴘⴙⴚⴛⴜⴝⴞⴟⴠⴡⴢⴣⴤⴥⴧⴭꙀꙂꙄꙆꙈꙊꙌꙎꙐꙒꙔꙖꙘꙚꙜꙞꙠꙢꙤꙦꙨꙪꙬꚀꚂꚄꚆꚈꚊꚌꚎꚐꚒꚔꚖꚘꚚꜢꜤꜦꜨꜪꜬꜮꜲꜴꜶꜸꜺꜼꜾꝀꝂꝄꝆꝈꝊꝌꝎꝐꝒꝔꝖꝘꝚꝜꝞꝠꝢꝤꝦꝨꝪꝬꝮꝹꝻꝽꝾꞀꞂꞄꞆꞋꞍꞐꞒꞖꞘꞚꞜꞞꞠꞢꞤꞦꞨꞪꞫꞬꞭꞮꞰꞱꞲꞳꞴꞶꞸꞺꞼꞾꟂꟄꟅꟆꟇꟉꟵＡＢＣＤＥＦＧＨＩＪＫＬＭＮＯＰＱＲＳＴＵＶＷＸＹＺ
备注
它将umlaut字母视为自己的一部分，因为a和á是不同的，要在比较情况下将它们处理为相同的将需要更加复杂的解决方案。有些umlaut字符仅存在于Lwr或Upr大小写中，并被忽略。
大写=小写
0xc8 0xba = 0xe2 0xb1 0xa5
0xc8 0xbe = 0xe2 0xb1 0xa6
0xe1 0xba 0x9e = 0xc3 0x9f
0xe2 0xb1 0xa2 = 0xc9 0xab
0xe2 0xb1 0xa4 = 0xc9 0xbd
0xe2 0xb1 0xad = 0xc9 0x91
0xe2 0xb1 0xae = 0xc9 0xb1
0xe2 0xb1 0xaf = 0xc9 0x90
0xe2 0xb1 0xb0 = 0xc9 0x92
0xe2 0xb1 0xbe = 0xc8 0xbf
0xe2 0xb1 0xbf = 0xc9 0x80
0xea 0x9e 0x8d = 0xc9 0xa5
0xea 0x9e 0xaa = 0xc9 0xa6
0xea 0x9e 0xab = 0xc9 0x9c
0xea 0x9e 0xac = 0xc9 0xa1
0xea 0x9e 0xad = 0xc9 0xac
0xea 0x9e 0xae = 0xc9 0xaa
0xea 0x9e 0xb0 = 0xca 0x9e
0xea 0x9e 0xb1 = 0xca 0x87。
0xea 0x9e 0xb2 = 0xca 0x9d。
0xea 0x9f 0x85 = 0xca 0x82。
代码不会处理字符串中的错误多字节字符的恢复（这是一个罕见的问题，区别于多字符字符串），它将重新同步。这不是本答案的主题。
运行时可能存在缓冲区溢出的风险（但极不可能）。当一个字符串以不完整的多字节字符结尾时，就会发生这种情况。如果在处理期间截断了字符串，就可能会发生这种情况，从而破坏了多字节字符。但是随着今天大量可用的存储器供应，是否要为完整的字符串分配内存呢？否则，如果您希望它具有缓冲区溢出安全性，您需要自己处理该问题。这不是本答案的主题。
unsigned char* StrToLwrExt(unsigned char* pString)
{
unsigned char* p = pString;
unsigned char* pExtChar = 0;
if (pString && *pString) {
while (*p) {
if ((*p >= 0x41) && (*p <= 0x5a)) /* US ASCII */
(*p) += 0x20;
else if (*p > 0xc0) {
pExtChar = p;
p++;
switch (*pExtChar) {
case 0xc3: /* Latin 1 */
if ((*p >= 0x80)
&& (*p <= 0x9e)
&& (*p != 0x97))
(*p) += 0x20; /* US ASCII shift */
break;
case 0xc4: /* Latin ext */
if (((*p >= 0x80)
&& (*p <= 0xb7)
&& (*p != 0xb0))
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
else if ((*p >= 0xb9)
&& (*p <= 0xbe)
&& (*p % 2)) /* Odd */
(*p)++; /* Next char is lwr */
else if (*p == 0xbf) {
*pExtChar = 0xc5;
(*p) = 0x80;
}
break;
case 0xc5: /* Latin ext */
if ((*p >= 0x81)
&& (*p <= 0x88)
&& (*p % 2)) /* Odd */
(*p)++; /* Next char is lwr */
else if ((*p >= 0x8a)
&& (*p <= 0xb7)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
else if (*p == 0xb8) {
*pExtChar = 0xc3;
(*p) = 0xbf;
}
else if ((*p >= 0xb9)
&& (*p <= 0xbe)
&& (*p % 2)) /* Odd */
(*p)++; /* Next char is lwr */
break;
case 0xc6: /* Latin ext */
switch (*p) {
case 0x81:
*pExtChar = 0xc9;
(*p) = 0x93;
break;
case 0x86:
*pExtChar = 0xc9;
(*p) = 0x94;
break;
case 0x89:
*pExtChar = 0xc9;
(*p) = 0x96;
break;
case 0x8a:
*pExtChar = 0xc9;
(*p) = 0x97;
break;
case 0x8e:
*pExtChar = 0xc9;
(*p) = 0x98;
break;
case 0x8f:
*pExtChar = 0xc9;
(*p) = 0x99;
break;
case 0x90:
*pExtChar = 0xc9;
(*p) = 0x9b;
break;
case 0x93:
*pExtChar = 0xc9;
(*p) = 0xa0;
break;
case 0x94:
*pExtChar = 0xc9;
(*p) = 0xa3;
break;
case 0x96:
*pExtChar = 0xc9;
(*p) = 0xa9;
break;
case 0x97:
*pExtChar = 0xc9;
(*p) = 0xa8;
break;
case 0x9c:
*pExtChar = 0xc9;
(*p) = 0xaf;
break;
case 0x9d:
*pExtChar = 0xc9;
(*p) = 0xb2;
break;
case 0x9f:
*pExtChar = 0xc9;
(*p) = 0xb5;
break;
case 0xa9:
*pExtChar = 0xca;
(*p) = 0x83;
break;
case 0xae:
*pExtChar = 0xca;
(*p) = 0x88;
break;
case 0xb1:
*pExtChar = 0xca;
(*p) = 0x8a;
break;
case 0xb2:
*pExtChar = 0xca;
(*p) = 0x8b;
break;
case 0xb7:
*pExtChar = 0xca;
(*p) = 0x92;
break;
case 0x82:
case 0x84:
case 0x87:
case 0x8b:
case 0x91:
case 0x98:
case 0xa0:
case 0xa2:
case 0xa4:
case 0xa7:
case 0xac:
case 0xaf:
case 0xb3:
case 0xb5:
case 0xb8:
case 0xbc:
(*p)++; /* Next char is lwr */
break;
default:
break;
}
break;
case 0xc7: /* Latin ext */
if (*p == 0x84)
(*p) = 0x86;
else if (*p == 0x85)
(*p)++; /* Next char is lwr */
else if (*p == 0x87)
(*p) = 0x89;
else if (*p == 0x88)
(*p)++; /* Next char is lwr */
else if (*p == 0x8a)
(*p) = 0x8c;
else if (*p == 0x8b)
(*p)++; /* Next char is lwr */
else if ((*p >= 0x8d)
&& (*p <= 0x9c)
&& (*p % 2)) /* Odd */
(*p)++; /* Next char is lwr */
else if ((*p >= 0x9e)
&& (*p <= 0xaf)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
else if (*p == 0xb1)
(*p) = 0xb3;
else if (*p == 0xb2)
(*p)++; /* Next char is lwr */
else if (*p == 0xb4)
(*p)++; /* Next char is lwr */
else if (*p == 0xb6) {
*pExtChar = 0xc6;
(*p) = 0x95;
}
else if (*p == 0xb7) {
*pExtChar = 0xc6;
(*p) = 0xbf;
}
else if ((*p >= 0xb8)
&& (*p <= 0xbf)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
break;
case 0xc8: /* Latin ext */
if ((*p >= 0x80)
&& (*p <= 0x9f)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
else if (*p == 0xa0) {
*pExtChar = 0xc6;
(*p) = 0x9e;
}
else if ((*p >= 0xa2)
&& (*p <= 0xb3)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
else if (*p == 0xbb)
(*p)++; /* Next char is lwr */
else if (*p == 0xbd) {
*pExtChar = 0xc6;
(*p) = 0x9a;
}
/* 0xba three byte small 0xe2 0xb1 0xa5 */
/* 0xbe three byte small 0xe2 0xb1 0xa6 */
break;
case 0xc9: /* Latin ext */
if (*p == 0x81)
(*p)++; /* Next char is lwr */
else if (*p == 0x83) {
*pExtChar = 0xc6;
(*p) = 0x80;
}
else if (*p == 0x84) {
*pExtChar = 0xca;
(*p) = 0x89;
}
else if (*p == 0x85) {
*pExtChar = 0xca;
(*p) = 0x8c;
}
else if ((*p >= 0x86)
&& (*p <= 0x8f)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
break;
case 0xcd: /* Greek & Coptic */
switch (*p) {
case 0xb0:
case 0xb2:
case 0xb6:
(*p)++; /* Next char is lwr */
break;
case 0xbf:
*pExtChar = 0xcf;
(*p) = 0xb3;
break;
default:
break;
}
break;
case 0xce: /* Greek & Coptic */
if (*p == 0x86)
(*p) = 0xac;
else if (*p == 0x88)
(*p) = 0xad;
else if (*p == 0x89)
(*p) = 0xae;
else if (*p == 0x8a)
(*p) = 0xaf;
else if (*p == 0x8c) {
*pExtChar = 0xcf;
(*p) = 0x8c;
}
else if (*p == 0x8e) {
*pExtChar = 0xcf;
(*p) = 0x8d;
}
else if (*p == 0x8f) {
*pExtChar = 0xcf;
(*p) = 0x8e;
}
else if ((*p >= 0x91)
&& (*p <= 0x9f))
(*p) += 0x20; /* US ASCII shift */
else if ((*p >= 0xa0)
&& (*p <= 0xab)
&& (*p != 0xa2)) {
*pExtChar = 0xcf;
(*p) -= 0x20;
}
break;
case 0xcf: /* Greek & Coptic */
if (*p == 0x8f)
(*p) = 0x97;
else if ((*p >= 0x98)
&& (*p <= 0xaf)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
else if (*p == 0xb4) {
(*p) = 0x91;
}
else if (*p == 0xb7)
(*p)++; /* Next char is lwr */
else if (*p == 0xb9)
(*p) = 0xb2;
else if (*p == 0xba)
(*p)++; /* Next char is lwr */
else if (*p == 0xbd) {
*pExtChar = 0xcd;
(*p) = 0xbb;
}
else if (*p == 0xbe) {
*pExtChar = 0xcd;
(*p) = 0xbc;
}
else if (*p == 0xbf) {
*pExtChar = 0xcd;
(*p) = 0xbd;
}
break;
case 0xd0: /* Cyrillic */
if ((*p >= 0x80)
&& (*p <= 0x8f)) {
*pExtChar = 0xd1;
(*p) += 0x10;
}
else if ((*p >= 0x90)
&& (*p <= 0x9f))
(*p) += 0x20; /* US ASCII shift */
else if ((*p >= 0xa0)
&& (*p <= 0xaf)) {
*pExtChar = 0xd1;
(*p) -= 0x20;
}
break;
case 0xd1: /* Cyrillic supplement */
if ((*p >= 0xa0)
&& (*p <= 0xbf)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
break;
case 0xd2: /* Cyrillic supplement */
if (*p == 0x80)
(*p)++; /* Next char is lwr */
else if ((*p >= 0x8a)
&& (*p <= 0xbf)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
break;
case 0xd3: /* Cyrillic supplement */
if (*p == 0x80)
(*p) = 0x8f;
else if ((*p >= 0x81)
&& (*p <= 0x8e)
&& (*p % 2)) /* Odd */
(*p)++; /* Next char is lwr */
else if ((*p >= 0x90)
&& (*p <= 0xbf)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
break;
case 0xd4: /* Cyrillic supplement & Armenian */
if ((*p >= 0x80)
&& (*p <= 0xaf)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
else if ((*p >= 0xb1)
&& (*p <= 0xbf)) {
*pExtChar = 0xd5;
(*p) -= 0x10;
}
break;
case 0xd5: /* Armenian */
if ((*p >= 0x80)
&& (*p <= 0x8f)) {
(*p) += 0x30;
}
else if ((*p >= 0x90)
&& (*p <= 0x96)) {
*pExtChar = 0xd6;
(*p) -= 0x10;
}
break;
case 0xe1: /* Three byte code */
pExtChar = p;
p++;
switch (*pExtChar) {
case 0x82: /* Georgian asomtavruli */
if ((*p >= 0xa0)
&& (*p <= 0xbf)) {
*pExtChar = 0x83;
(*p) -= 0x10;
}
break;
case 0x83: /* Georgian asomtavruli */
if (((*p >= 0x80)
&& (*p <= 0x85))
|| (*p == 0x87)
|| (*p == 0x8d))
(*p) += 0x30;
break;
case 0x8e: /* Cherokee */
if ((*p >= 0xa0)
&& (*p <= 0xaf)) {
*(p - 2) = 0xea;
*pExtChar = 0xad;
(*p) += 0x10;
}
else if ((*p >= 0xb0)
&& (*p <= 0xbf)) {
*(p - 2) = 0xea;
*pExtChar = 0xae;
(*p) -= 0x30;
}
break;
case 0x8f: /* Cherokee */
if ((*p >= 0x80)
&& (*p <= 0xaf)) {
*(p - 2) = 0xea;
*pExtChar = 0xae;
(*p) += 0x10;
}
else if ((*p >= 0xb0)
&& (*p <= 0xb5)) {
(*p) += 0x08;
}
/* 0xbe three byte small 0xe2 0xb1 0xa6 */
break;
case 0xb2: /* Georgian mtavruli */
if (((*p >= 0x90)
&& (*p <= 0xba))
|| (*p == 0xbd)
|| (*p == 0xbe)
|| (*p == 0xbf))
*pExtChar = 0x83;
break;
case 0xb8: /* Latin ext */
if ((*p >= 0x80)
&& (*p <= 0xbf)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
break;
case 0xb9: /* Latin ext */
if ((*p >= 0x80)
&& (*p <= 0xbf)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
break;
case 0xba: /* Latin ext */
if ((*p >= 0x80)
&& (*p <= 0x94)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
else if ((*p >= 0xa0)
&& (*p <= 0xbf)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
/* 0x9e Two byte small 0xc3 0x9f */
break;
case 0xbb: /* Latin ext */
if ((*p >= 0x80)
&& (*p <= 0xbf)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
break;
case 0xbc: /* Greek ex */
if ((*p >= 0x88)
&& (*p <= 0x8f))
(*p) -= 0x08;
else if ((*p >= 0x98)
&& (*p <= 0x9d))
(*p) -= 0x08;
else if ((*p >= 0xa8)
&& (*p <= 0xaf))
(*p) -= 0x08;
else if ((*p >= 0xb8)
&& (*p <= 0xbf))
(*p) -= 0x08;
break;
case 0xbd: /* Greek ex */
if ((*p >= 0x88)
&& (*p <= 0x8d))
(*p) -= 0x08;
else if ((*p == 0x99)
|| (*p == 0x9b)
|| (*p == 0x9d)
|| (*p == 0x9f))
(*p) -= 0x08;
else if ((*p >= 0xa8)
&& (*p <= 0xaf))
(*p) -= 0x08;
break;
case 0xbe: /* Greek ex */
if ((*p >= 0x88)
&& (*p <= 0x8f))
(*p) -= 0x08;
else if ((*p >= 0x98)
&& (*p <= 0x9f))
(*p) -= 0x08;
else if ((*p >= 0xa8)
&& (*p <= 0xaf))
(*p) -= 0x08;
else if ((*p >= 0xb8)
&& (*p <= 0xb9))
(*p) -= 0x08;
else if ((*p >= 0xba)
&& (*p <= 0xbb)) {
*(p - 1) = 0xbd;
(*p) -= 0x0a;
}
else if (*p == 0xbc)
(*p) -= 0x09;
break;
case 0xbf: /* Greek ex */
if ((*p >= 0x88)
&& (*p <= 0x8b)) {
*(p - 1) = 0xbd;
(*p) += 0x2a;
}
else if (*p == 0x8c)
(*p) -= 0x09;
else if ((*p >= 0x98)
&& (*p <= 0x99))
(*p) -= 0x08;
else if ((*p >= 0x9a)
&& (*p <= 0x9b)) {
*(p - 1) = 0xbd;
(*p) += 0x1c;
}
else if ((*p >= 0xa8)
&& (*p <= 0xa9))
(*p) -= 0x08;
else if ((*p >= 0xaa)
&& (*p <= 0xab)) {
*(p - 1) = 0xbd;
(*p) += 0x10;
}
else if (*p == 0xac)
(*p) -= 0x07;
else if ((*p >= 0xb8)
&& (*p <= 0xb9)) {
*(p - 1) = 0xbd;
}
else if ((*p >= 0xba)
&& (*p <= 0xbb)) {
*(p - 1) = 0xbd;
(*p) += 0x02;
}
else if (*p == 0xbc)
(*p) -= 0x09;
break;
default:
break;
}
break;
case 0xe2: /* Three byte code */
pExtChar = p;
p++;
switch (*pExtChar) {
case 0xb0: /* Glagolitic */
if ((*p >= 0x80)
&& (*p <= 0x8f)) {
(*p) += 0x30;
}
else if ((*p >= 0x90)
&& (*p <= 0xae)) {
*pExtChar = 0xb1;
(*p) -= 0x10;
}
break;
case 0xb1: /* Latin ext */
switch (*p) {
case 0xa0:
case 0xa7:
case 0xa9:
case 0xab:
case 0xb2:
case 0xb5:
(*p)++; /* Next char is lwr */
break;
case 0xa2: /* Two byte small 0xc9 0xab */
case 0xa4: /* Two byte small 0xc9 0xbd */
case 0xad: /* Two byte small 0xc9 0x91 */
case 0xae: /* Two byte small 0xc9 0xb1 */
case 0xaf: /* Two byte small 0xc9 0x90 */
case 0xb0: /* Two byte small 0xc9 0x92 */
case 0xbe: /* Two byte small 0xc8 0xbf */
case 0xbf: /* Two byte small 0xc9 0x80 */
break;
case 0xa3:
*(p - 2) = 0xe1;
*(p - 1) = 0xb5;
*(p) = 0xbd;
break;
default:
break;
}
break;
case 0xb2: /* Coptic */
if ((*p >= 0x80)
&& (*p <= 0xbf)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
break;
case 0xb3: /* Coptic */
if (((*p >= 0x80)
&& (*p <= 0xa3)
&& (!(*p % 2))) /* Even */
|| (*p == 0xab)
|| (*p == 0xad)
|| (*p == 0xb2))
(*p)++; /* Next char is lwr */
break;
case 0xb4: /* Georgian nuskhuri */
if (((*p >= 0x80)
&& (*p <= 0xa5))
|| (*p == 0xa7)
|| (*p == 0xad)) {
*(p - 2) = 0xe1;
*(p - 1) = 0x83;
(*p) += 0x10;
}
break;
default:
break;
}
break;
case 0xea: /* Three byte code */
pExtChar = p;
p++;
switch (*pExtChar) {
case 0x99: /* Cyrillic */
if ((*p >= 0x80)
&& (*p <= 0xad)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
break;
case 0x9a: /* Cyrillic */
if ((*p >= 0x80)
&& (*p <= 0x9b)
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
break;
case 0x9c: /* Latin ext */
if ((((*p >= 0xa2)
&& (*p <= 0xaf))
|| ((*p >= 0xb2)
&& (*p <= 0xbf)))
&& (!(*p % 2))) /* Even */
(*p)++; /* Next char is lwr */
break;
case 0x9d: /* Latin ext */
if ((((*p >= 0x80)
&& (*p <= 0xaf))
&& (!(*p % 2))) /* Even */
|| (*p == 0xb9)
|| (*p == 0xbb)
|| (*p == 0xbe))
(*p)++; /* Next char is lwr */
else if (*p == 0xbd) {
*(p - 2) = 0xe1;
*(p - 1) = 0xb5;
*(p) = 0xb9;
}
break;
case 0x9e: /* Latin ext */
if (((((*p >= 0x80)
&& (*p <= 0x87))
|| ((*p >= 0x96)
&& (*p <= 0xa9))
|| ((*p >= 0xb4)
&& (*p <= 0xbf)))
&& (!(*p % 2))) /* Even */
|| (*p == 0x8b)
|| (*p == 0x90)
|| (*p == 0x92))
(*p)++; /* Next char is lwr */
else if (*p == 0xb3) {
*(p - 2) = 0xea;
*(p - 1) = 0xad;
*(p) = 0x93;
}
/* case 0x8d: // Two byte small 0xc9 0xa5 */
/* case 0xaa: // Two byte small 0xc9 0xa6 */
/* case 0xab: // Two byte small 0xc9 0x9c */
/* case 0xac: // Two byte small 0xc9 0xa1 */
/* case 0xad: // Two byte small 0xc9 0xac */
/* case 0xae: // Two byte small 0xc9 0xaa */
/* case 0xb0: // Two byte small 0xca 0x9e */
/* case 0xb1: // Two byte small 0xca 0x87 */
/* case 0xb2: // Two byte small 0xca 0x9d */
break;
case 0x9f: /* Latin ext */
if ((*p == 0x82)
|| (*p == 0x87)
|| (*p == 0x89)
|| (*p == 0xb5))
(*p)++; /* Next char is lwr */
else if (*p == 0x84) {
*(p - 2) = 0xea;
*(p - 1) = 0x9e;
*(p) = 0x94;
}
else if (*p == 0x86) {
*(p - 2) = 0xe1;
*(p - 1) = 0xb6;
*(p) = 0x8e;
}
/* case 0x85: // Two byte small 0xca 0x82 */
break;
default:
break;
}
break;
case 0xef: /* Three byte code */
pExtChar = p;
p++;
switch (*pExtChar) {
case 0xbc: /* Latin fullwidth */
if ((*p >= 0xa1)
&& (*p <= 0xba)) {
*pExtChar = 0xbd;
(*p) -= 0x20;
}
break;
default:
break;
}
break;
case 0xf0: /* Four byte code */
pExtChar = p;
p++;
switch (*pExtChar) {
case 0x90:
pExtChar = p;
p++;
switch (*pExtChar) {
case 0x90: /* Deseret */
if ((*p >= 0x80)
&& (*p <= 0x97)) {
(*p) += 0x28;
}
else if ((*p >= 0x98)
&& (*p <= 0xa7)) {
*pExtChar = 0x91;
(*p) -= 0x18;
}
break;
case 0x92: /* Osage */
if ((*p >= 0xb0)
&& (*p <= 0xbf)) {
*pExtChar = 0x93;
(*p) -= 0x18;
}
break;
case 0x93: /* Osage */
if ((*p >= 0x80)
&& (*p <= 0x93))
(*p) += 0x28;
break;
case 0xb2: /* Old hungarian */
if ((*p >= 0x80)
&& (*p <= 0xb2))
*pExtChar = 0xb3;
break;
default:
break;
}
break;
case 0x91:
pExtChar = p;
p++;
switch (*pExtChar) {
case 0xa2: /* Warang citi */
if ((*p >= 0xa0)
&& (*p <= 0xbf)) {
*pExtChar = 0xa3;
(*p) -= 0x20;
}
break;
default:
break;
}
break;
case 0x96:
pExtChar = p;
p++;
switch (*pExtChar) {
case 0xb9: /* Medefaidrin */
if ((*p >= 0x80)
&& (*p <= 0x9f)) {
(*p) += 0x20;
}
break;
default:
break;
}
break;
case 0x9E:
pExtChar = p;
p++;
switch (*pExtChar) {
case 0xA4: /* Adlam */
if ((*p >= 0x80)
&& (*p <= 0x9d))
(*p) += 0x22;
else if ((*p >= 0x9e)
&& (*p <= 0xa1)) {
*(pExtChar) = 0xa5;
(*p) -= 0x1e;
}
break;
default:
break;
}
break;
default:
break;
}
break;
default:
break;
}
pExtChar = 0;
}
p++;
}
}
return pString;
}
int StrnCiCmp(const char* s1, const char* s2, size_t ztCount)
{
unsigned char* pStr1Low = 0;
unsigned char* pStr2Low = 0;
unsigned char* p1 = 0;
unsigned char* p2 = 0;
if (s1 && *s1 && s2 && *s2) {
char cExtChar = 0;
pStr1Low = (unsigned char*)calloc(strlen(s1) + 1, sizeof(unsigned char));
if (pStr1Low) {
pStr2Low = (unsigned char*)calloc(strlen(s2) + 1, sizeof(unsigned char));
if (pStr2Low) {
p1 = pStr1Low;
p2 = pStr2Low;
strcpy((char*)pStr1Low, s1);
strcpy((char*)pStr2Low, s2);
StrToLwrExt(pStr1Low);
StrToLwrExt(pStr2Low);
for (; ztCount--; p1++, p2++) {
int iDiff = *p1 - *p2;
if (iDiff != 0 || !*p1 || !*p2) {
free(pStr1Low);
free(pStr2Low);
return iDiff;
}
}
free(pStr1Low);
free(pStr2Low);
return 0;
}
free(pStr1Low);
return (-1);
}
return (-1);
}
return (-1);
}
int StrCiCmp(const char* s1, const char* s2)
{
return StrnCiCmp(s1, s2, (size_t)(-1));
}
char* StrCiStr(const char* s1, const char* s2)
{
char* p = (char*)s1;
size_t len = 0;
if (s1 && *s1 && s2 && *s2) {
len = strlen(s2);
while (*p) {
if (StrnCiCmp(p, s2, len) == 0)
return (char*)p;
p++;
}
}
return (0);
}
switch落空的警告（它们在嵌套的switch语句中），这是有意为之吗？ - Cygonu8"ÂÊÎÔÛ ÁÉÍÓÚ ÀÈÌÒÙ AÖU" 测试这段代码片段，但结果是 ÂÊÎÔÛ ÁÉÍÓÚ ÀÈÌÒÙ aÖU（16个字符仍为大写，有两个错误）。 - Cygon这些不区分大小写的特性在搜索功能中绝对是必需的。
嗯，我和上面描述的需要一样，并且UTF8在大多数方面都很顺畅，但大小写情况并不太好。看起来它是被搁置在待办事项清单上完成时？因为在这种情况下它过去是待办事项清单中的主要话题之一。在IBM发货之前，我一直在打补丁IBM键盘驱动程序1984年，但是副本是可用的。在IBM想要在欧洲发货之前，也修补了Displaywrite 1和3（PC-DOS文字处理器）。在IBM 3270主机终端系统中，完成了大量PC-DOS（CP850）和CP1252（Windows）与国家EBCDIC代码页之间的交换。所有国家ASCII版本和CP1252 Windows表都在0x40-0x5F和0x60-0x7F之间有一个转换，以便在小写和大写之间切换（但不是PCDOS CP850），通过0x20。
该怎么办呢？
tolower（）和toupper（）在UTF8多字符字符串中不起作用，除了US-ASCII外。它们只适用于一个字节。但是，字符串解决方案将起作用，并且几乎有关于其他所有问题的解决方案。
西欧人很幸运
好吧，UTF8将CP1252（Windows 8位/ Latin1）作为第一个附加表，Latin-1 Supplement（Unicode块），正如它是的。这意味着可以像常规US ASCII一样移动字母（C3XX）。下面是代码示例。
希腊人、俄罗斯人、冰岛人和东欧人就没那么幸运了
对于冰岛人，Đ / đ-D with stroke（与单词“the”的th音相同）只是从CP1252中打出来的。
希腊人、俄罗斯人和东欧国家的ISO8字符集（CP1253、CP1251和CP1257）本应该被使用（因为拉丁CP1252直接被使用）。然后只需进行移位即可工作。但是，某人只是相当随意地填充了表格（就像在PC-DOC 8位ASCII中一样）。
只有一种有效的解决方案，与PC_DOS ASCII相同，制作翻译表。当我需要时，我会在下一个圣诞节做到这一点，但是如果有人急需，我会提示如何做到这一点。
如何为希腊人、俄罗斯人、冰岛人和东欧人提供解决方案
在编程代码中制作与UTF8表的不同第一个字节相关的不同表格，用其UTF8第二字节位置中的字母的第二个字节填充表格，并用匹配小写字母的第二字节交换大写字母，并制作另一个反向执行相反的操作的表格。
然后，确定每个表所关联的第一个字节。这样，编程代码就可以选择正确的表格，并只需读取正确的位置并获取所需的大写或小写字符。然后修改以下字母大小写函数（我为Latin1创建的那些），以使用表格而不是移动0x20，对于一些必须使用表格的第一个UTF8字符。它将运行顺畅，新计算机在内存和功率方面都没有问题。unsigned char *StrToLwrUft8Latin1(unsigned char *pString)
{
char cExtChar = 0;
if (pString && *pString) {
unsigned char *p = pString;
while (*p) {
if (((cExtChar && ((*p >= 0x80) && (*p <= 0xbf)))
|| ((!cExtChar) && (*p <= 0x7f)))
&& ((((*p & 0x7f) + cExtChar) >= 0x40)
&& (((*p & 0x7f) + cExtChar) <= 0x5f)))
*p += 0x20;
if (cExtChar)
cExtChar = 0;
else if (*p == 0xc3)
cExtChar = 0x40;
p++;
}
}
return pString;
}
unsigned char *StrToUprUft8Latin1(unsigned char *pString)
{
char cExtChar = 0;
if (pString && *pString) {
unsigned char *p = pString;
while (*p) {
if (((cExtChar && ((*p >= 0x80) && (*p <= 0xbf)))
|| ((!cExtChar) && (*p <= 0x7f)))
&& ((((*p & 0x7f) + cExtChar) >= 0x60)
&& (((*p & 0x7f) + cExtChar) <= 0x7e)))
*p -= 0x20;
if (cExtChar)
cExtChar = 0;
else if (*p == 0xc3)
cExtChar = 0x40;
p++;
}
}
return pString;
}
int StrnCiCmpLatin1(const char *s1, const char *s2, size_t ztCount)
{
unsigned char cExtChar = 0;
if (s1 && *s1 && s2 && *s2) {
for (; ztCount--; s1++, s2++) {
int iDiff = tolower((unsigned char)(*s1 & 0x7f)
+ cExtChar) - tolower((unsigned char)(*s2 & 0x7f) + cExtChar);
if (iDiff != 0 || !*s1 || !*s2)
return iDiff;
if (cExtChar)
cExtChar = 0;
else if (((unsigned char )*s2) == ((unsigned char)0xc3))
cExtChar = 0x40;
}
}
return 0;
}
int StrCiCmpLatin1(const char *s1, const char *s2)
{
return StrnCiCmpLatin1(s1, s2, (size_t)(-1));
}
char *StrCiStrLatin1(const char *s1, const char *s2)
{
if (s1 && *s1 && s2 && *s2) {
char *p = (char *)s1;
size_t len = strlen(s2);
while (*p) {
if (StrnCiCmpLatin1(p, s2, len) == 0)
return p;
p++;
}
}
return (0);
}
wchar_t 要足够宽以容纳所有支持的代码单元（32位宽），但在处理UTF-8时完全正常。 在Windows上，wchar_t 是UTF-16，但说实话，如果您在Windows上，那您会有更多问题（即可怕的API）。sort）无法正常工作，因此用户需要负责。unsigned char 的范围为 255。 0xc3b3 远远超过了这个范围。#include <iostream>
#include <string>
#include <locale>
int main()
{
std::setlocale(LC_CTYPE, "en_US.UTF-8"); // the locale will be the UTF-8 enabled English
std::wstring str = L"óó";
std::wcout << str << std::endl;
for (std::wstring::iterator it = str.begin(); it != str.end(); ++it)
*it = towupper(*it);
std::wcout << str << std::endl;
}
输出结果：OO
toupper 的使用让我感到困惑的原因是，我读到通常情况下将单个字节映射转换为多字节字符。因此，如果在原地转换字符，则简单的迭代器将无法工作。wstring 类型吗？ - aardvarkksetlocale设置为UTF-8时，返回值为NULL。 - aardvarkkstring（而不是wstring），那么将string转换为wstring是否很简单？我认为这个过程也需要了解UTF-8编码。 - aardvarkkstd::string转换，因此并没有真正回答这个问题。 - Thomaswchar_t 支持 UTF-32 码元（或 Unicode）。 - 一二三这段代码是一个功能集，包括验证过的UTF（UTF8，UTF16和UTF32）Lwr/Upr转换，不区分大小写的Cmp、strstr，以及使用UTF代码点引用ID进行处理。
下载地址：https://www.alphabet.se/download/UtfConv.c
该功能集包括：
// Utf 8
size_t StrLenUtf8(const Utf8Char* str);
int StrnCmpUtf8(const Utf8Char* Utf8s1, const Utf8Char* Utf8s2, size_t ztCount);
int StrCmpUtf8(const Utf8Char* Utf8s1, const Utf8Char* Utf8s2);
size_t CharLenUtf8(const Utf8Char* pUtf8);
Utf8Char* ForwardUtf8Chars(const Utf8Char* pUtf8, size_t ztForwardUtf8Chars);
size_t StrLenUtf32AsUtf8(const Utf32Char* pUtf32);
Utf8Char* Utf32ToUtf8(const Utf32Char* pUtf32);
Utf32Char* Utf8ToUtf32(const Utf8Char* pUtf8);
Utf16Char* Utf8ToUtf16(const Utf8Char* pUtf8);
Utf8Char* Utf8StrMakeUprUtf8Str(const Utf8Char* pUtf8);
Utf8Char* Utf8StrMakeLwrUtf8Str(const Utf8Char* pUtf8);
int StrnCiCmpUtf8(const Utf8Char* pUtf8s1, const Utf8Char* pUtf8s2, size_t ztCount);
int StrCiCmpUtf8(const Utf8Char* pUtf8s1, const Utf8Char* pUtf8s2);
Utf8Char* StrCiStrUtf8(const Utf8Char* pUtf8s1, const Utf8Char* pUtf8s2);
// Utf 16
size_t StrLenUtf16(const Utf16Char* str);
Utf16Char* StrCpyUtf16(Utf16Char* dest, const Utf16Char* src);
Utf16Char* StrCatUtf16(Utf16Char* dest, const Utf16Char* src);
int StrnCmpUtf16(const Utf16Char* Utf16s1, const Utf16Char* Utf16s2, size_t ztCount);
int StrCmpUtf16(const Utf16Char* Utf16s1, const Utf16Char* Utf16s2);
size_t CharLenUtf16(const Utf16Char* pUtf16);
Utf16Char* ForwardUtf16Chars(const Utf16Char* pUtf16, size_t ztForwardUtf16Chars);
size_t StrLenUtf32AsUtf16(const Utf32Char* pUtf32);
Utf16Char* Utf32ToUtf16(const Utf32Char* pUtf32);
Utf32Char* Utf16ToUtf32(const Utf16Char* pUtf16);
Utf8Char* Utf16ToUtf8(const Utf16Char* pUtf16);
Utf16Char* Utf16StrMakeUprUtf16Str(const Utf16Char* pUtf16);
Utf16Char* Utf16StrMakeLwrUtf16Str(const Utf16Char* pUtf16);
int StrnCiCmpUtf16(const Utf16Char* pUtf16s1, const Utf16Char* pUtf16s2, size_t ztCount);
int StrCiCmpUtf16(const Utf16Char* pUtf16s1, const Utf16Char* pUtf16s2);
Utf16Char* StrCiStrUtf16(const Utf16Char* pUtf16s1, const Utf16Char* pUtf16s2);
// Utf 32
size_t StrLenUtf32(const Utf32Char* str);
Utf32Char* StrCpyUtf32(Utf32Char* dest, const Utf32Char* src);
Utf32Char* StrCatUtf32(Utf32Char* dest, const Utf32Char* src);
int StrnCmpUtf32(const Utf32Char* Utf32s1, const Utf32Char* Utf32s2, size_t ztCount);
int StrCmpUtf32(const Utf32Char* Utf32s1, const Utf32Char* Utf32s2);
Utf32Char* StrToUprUtf32(Utf32Char* pUtf32);
Utf32Char* StrToLwrUtf32(Utf32Char* pUtf32);
int StrnCiCmpUtf32(const Utf32Char* Utf32s1, const Utf32Char* Utf32s2, size_t ztCount);
int StrCiCmpUtf32(const Utf32Char* Utf32s1, const Utf32Char* Utf32s2);
Utf32Char* StrCiStrUtf32(const Utf32Char* Utf32s1, const Utf32Char* Utf32s2);
与”This code is a carefully tested UTF8 case conversion/case insensitive cmp.”答案相关的优点是：
劣势：
StrToUprExt()
这个答案是对“该代码是经过仔细测试的UTF8大小写转换/不区分大小写的cmp。”答案的扩展。尽管它没有用于strcmp()或strstr()函数，但根据需求，它也可以拥有一个大写函数。
它与主要答案同时制作，获取了所有具有两种情况的UTF8表（我认为我找到了它们所有），并在编程辅助下编写了代码，应该覆盖所有内容。它已经仔细检查过错误。
它在另一个答案中，因为答案有空间限制，而且代码无法适应其他答案。
unsigned char* StrToUprExt(unsigned char* pString)
{
unsigned char* p = pString;
unsigned char* pExtChar = 0;
if (pString && *pString) {
while (*p) {
if ((*p >= 0x61) && (*p <= 0x7a)) /* US ASCII */
(*p) -= 0x20;
else if (*p > 0xc0) {
pExtChar = p;
p++;
switch (*pExtChar) {
case 0xc3: /* Latin 1 */
/* 0x9f Three byte capital 0xe1 0xba 0x9e */
if ((*p >= 0xa0)
&& (*p <= 0xbe)
&& (*p != 0xb7))
(*p) -= 0x20; /* US ASCII shift */
else if (*p == 0xbf) {
*pExtChar = 0xc5;
(*p) = 0xb8;
}
break;
case 0xc4: /* Latin ext */
if (((*p >= 0x80)
&& (*p <= 0xb7)
&& (*p != 0xb1))
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
else if ((*p >= 0xb9)
&& (*p <= 0xbe)
&& (!(*p % 2))) /* Even */
(*p)--; /* Prev char is upr */
break;
case 0xc5: /* Latin ext */
if (*p == 0x80) {
*pExtChar = 0xc4;
(*p) = 0xbf;
}
else if ((*p >= 0x81)
&& (*p <= 0x88)
&& (!(*p % 2))) /* Even */
(*p)--; /* Prev char is upr */
else if ((*p >= 0x8a)
&& (*p <= 0xb7)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
else if (*p == 0xb8) {
*pExtChar = 0xc5;
(*p) = 0xb8;
}
else if ((*p >= 0xb9)
&& (*p <= 0xbe)
&& (!(*p % 2))) /* Even */
(*p)--; /* Prev char is upr */
break;
case 0xc6: /* Latin ext */
switch (*p) {
case 0x83:
case 0x85:
case 0x88:
case 0x8c:
case 0x92:
case 0x99:
case 0xa1:
case 0xa3:
case 0xa5:
case 0xa8:
case 0xad:
case 0xb0:
case 0xb4:
case 0xb6:
case 0xb9:
case 0xbd:
(*p)--; /* Prev char is upr */
break;
case 0x80:
*pExtChar = 0xc9;
(*p) = 0x83;
break;
case 0x95:
*pExtChar = 0xc7;
(*p) = 0xb6;
break;
case 0x9a:
*pExtChar = 0xc8;
(*p) = 0xbd;
break;
case 0x9e:
*pExtChar = 0xc8;
(*p) = 0xa0;
break;
case 0xbf:
*pExtChar = 0xc7;
(*p) = 0xb7;
break;
default:
break;
}
break;
case 0xc7: /* Latin ext */
if (*p == 0x85)
(*p)--; /* Prev char is upr */
else if (*p == 0x86)
(*p) = 0x84;
else if (*p == 0x88)
(*p)--; /* Prev char is upr */
else if (*p == 0x89)
(*p) = 0x87;
else if (*p == 0x8b)
(*p)--; /* Prev char is upr */
else if (*p == 0x8c)
(*p) = 0x8a;
else if ((*p >= 0x8d)
&& (*p <= 0x9c)
&& (!(*p % 2))) /* Even */
(*p)--; /* Prev char is upr */
else if ((*p >= 0x9e)
&& (*p <= 0xaf)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
else if (*p == 0xb2)
(*p)--; /* Prev char is upr */
else if (*p == 0xb3)
(*p) = 0xb1;
else if (*p == 0xb5)
(*p)--; /* Prev char is upr */
else if ((*p >= 0xb9)
&& (*p <= 0xbf)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
break;
case 0xc8: /* Latin ext */
if ((*p >= 0x80)
&& (*p <= 0x9f)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
else if ((*p >= 0xa2)
&& (*p <= 0xb3)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
else if (*p == 0xbc)
(*p)--; /* Prev char is upr */
/* 0xbf Three byte capital 0xe2 0xb1 0xbe */
break;
case 0xc9: /* Latin ext */
switch (*p) {
case 0x80: /* Three byte capital 0xe2 0xb1 0xbf */
case 0x90: /* Three byte capital 0xe2 0xb1 0xaf */
case 0x91: /* Three byte capital 0xe2 0xb1 0xad */
case 0x92: /* Three byte capital 0xe2 0xb1 0xb0 */
case 0x9c: /* Three byte capital 0xea 0x9e 0xab */
case 0xa1: /* Three byte capital 0xea 0x9e 0xac */
case 0xa5: /* Three byte capital 0xea 0x9e 0x8d */
case 0xa6: /* Three byte capital 0xea 0x9e 0xaa */
case 0xab: /* Three byte capital 0xe2 0xb1 0xa2 */
case 0xac: /* Three byte capital 0xea 0x9e 0xad */
case 0xb1: /* Three byte capital 0xe2 0xb1 0xae */
case 0xbd: /* Three byte capital 0xe2 0xb1 0xa4 */
break;
case 0x82:
(*p)--; /* Prev char is upr */
break;
case 0x93:
*pExtChar = 0xc6;
(*p) = 0x81;
break;
case 0x94:
*pExtChar = 0xc6;
(*p) = 0x86;
break;
case 0x96:
*pExtChar = 0xc6;
(*p) = 0x89;
break;
case 0x97:
*pExtChar = 0xc6;
(*p) = 0x8a;
break;
case 0x98:
*pExtChar = 0xc6;
(*p) = 0x8e;
break;
case 0x99:
*pExtChar = 0xc6;
(*p) = 0x8f;
break;
case 0x9b:
*pExtChar = 0xc6;
(*p) = 0x90;
break;
case 0xa0:
*pExtChar = 0xc6;
(*p) = 0x93;
break;
case 0xa3:
*pExtChar = 0xc6;
(*p) = 0x94;
break;
case 0xa8:
*pExtChar = 0xc6;
(*p) = 0x97;
break;
case 0xa9:
*pExtChar = 0xc6;
(*p) = 0x96;
break;
case 0xaf:
*pExtChar = 0xc6;
(*p) = 0x9c;
break;
case 0xb2:
*pExtChar = 0xc6;
(*p) = 0x9d;
break;
case 0xb5:
*pExtChar = 0xc6;
(*p) = 0x9f;
break;
default:
if ((*p >= 0x87)
&& (*p <= 0x8f)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
break;
}
break;
case 0xca: /* Latin ext */
switch (*p) {
case 0x82: /* Three byte capital 0xea 0x9f 0x85 */
case 0x87: /* Three byte capital 0xea 0x9e 0xb1 */
case 0x9d: /* Three byte capital 0xea 0x9e 0xb2 */
case 0x9e: /* Three byte capital 0xea 0x9e 0xb0 */
break;
case 0x83:
*pExtChar = 0xc6;
(*p) = 0xa9;
break;
case 0x88:
*pExtChar = 0xc6;
(*p) = 0xae;
break;
case 0x89:
*pExtChar = 0xc9;
(*p) = 0x84;
break;
case 0x8a:
*pExtChar = 0xc6;
(*p) = 0xb1;
break;
case 0x8b:
*pExtChar = 0xc6;
(*p) = 0xb2;
break;
case 0x8c:
*pExtChar = 0xc9;
(*p) = 0x85;
break;
case 0x92:
*pExtChar = 0xc6;
(*p) = 0xb7;
break;
default:
break;
}
break;
case 0xcd: /* Greek & Coptic */
switch (*p) {
case 0xb1:
case 0xb3:
case 0xb7:
(*p)--; /* Prev char is upr */
break;
case 0xbb:
*pExtChar = 0xcf;
(*p) = 0xbd;
break;
case 0xbc:
*pExtChar = 0xcf;
(*p) = 0xbe;
break;
case 0xbd:
*pExtChar = 0xcf;
(*p) = 0xbf;
break;
default:
break;
}
break;
case 0xce: /* Greek & Coptic */
if (*p == 0xac)
(*p) = 0x86;
else if (*p == 0xad)
(*p) = 0x88;
else if (*p == 0xae)
(*p) = 0x89;
else if (*p == 0xaf)
(*p) = 0x8a;
else if ((*p >= 0xb1)
&& (*p <= 0xbf))
(*p) -= 0x20; /* US ASCII shift */
break;
case 0xcf: /* Greek & Coptic */
if (*p == 0x82) {
*pExtChar = 0xce;
(*p) = 0xa3;
}
else if ((*p >= 0x80)
&& (*p <= 0x8b)) {
*pExtChar = 0xce;
(*p) += 0x20;
}
else if (*p == 0x8c) {
*pExtChar = 0xce;
(*p) = 0x8c;
}
else if (*p == 0x8d) {
*pExtChar = 0xce;
(*p) = 0x8e;
}
else if (*p == 0x8e) {
*pExtChar = 0xce;
(*p) = 0x8f;
}
else if (*p == 0x91)
(*p) = 0xb4;
else if (*p == 0x97)
(*p) = 0x8f;
else if ((*p >= 0x98)
&& (*p <= 0xaf)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
else if (*p == 0xb2)
(*p) = 0xb9;
else if (*p == 0xb3) {
*pExtChar = 0xcd;
(*p) = 0xbf;
}
else if (*p == 0xb8)
(*p)--; /* Prev char is upr */
else if (*p == 0xbb)
(*p)--; /* Prev char is upr */
break;
case 0xd0: /* Cyrillic */
if ((*p >= 0xb0)
&& (*p <= 0xbf))
(*p) -= 0x20; /* US ASCII shift */
break;
case 0xd1: /* Cyrillic supplement */
if ((*p >= 0x80)
&& (*p <= 0x8f)) {
*pExtChar = 0xd0;
(*p) += 0x20;
}
else if ((*p >= 0x90)
&& (*p <= 0x9f)) {
*pExtChar = 0xd0;
(*p) -= 0x10;
}
else if ((*p >= 0xa0)
&& (*p <= 0xbf)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
break;
case 0xd2: /* Cyrillic supplement */
if (*p == 0x81)
(*p)--; /* Prev char is upr */
else if ((*p >= 0x8a)
&& (*p <= 0xbf)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
break;
case 0xd3: /* Cyrillic supplement */
if ((*p >= 0x81)
&& (*p <= 0x8e)
&& (!(*p % 2))) /* Even */
(*p)--; /* Prev char is upr */
else if (*p == 0x8f)
(*p) = 0x80;
else if ((*p >= 0x90)
&& (*p <= 0xbf)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
break;
case 0xd4: /* Cyrillic supplement & Armenian */
if ((*p >= 0x80)
&& (*p <= 0xaf)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
break;
case 0xd5: /* Armenian */
if ((*p >= 0xa1)
&& (*p <= 0xaf)) {
*pExtChar = 0xd4;
(*p) += 0x10;
}
else if ((*p >= 0xb0)
&& (*p <= 0xbf)) {
(*p) -= 0x30;
}
break;
case 0xd6: /* Armenian */
if ((*p >= 0x80)
&& (*p <= 0x86)) {
*pExtChar = 0xd5;
(*p) += 0x10;
}
break;
case 0xe1: /* Three byte code */
pExtChar = p;
p++;
switch (*pExtChar) {
case 0x82: /* Georgian Asomtavruli */
if ((*p >= 0xa0)
&& (*p <= 0xbf)) {
*pExtChar = 0xb2;
(*p) -= 0x10;
}
break;
case 0x83: /* Georgian */
/* Georgian Asomtavruli */
if (((*p >= 0x80)
&& (*p <= 0x85))
|| (*p == 0x87)
|| (*p == 0x8d)) {
*pExtChar = 0xb2;
(*p) += 0x30;
}
/* Georgian mkhedruli */
else if (((*p >= 0x90)
&& (*p <= 0xba))
|| (*p == 0xbd)
|| (*p == 0xbe)
|| (*p == 0xbf)) {
*pExtChar = 0xb2;
}
break;
case 0x8f: /* Cherokee */
if ((*p >= 0xb8)
&& (*p <= 0xbd)) {
(*p) -= 0x08;
}
break;
case 0xb5: /* Latin ext */
if (*p == 0xb9) {
*(p - 2) = 0xea;
*(p - 1) = 0x9d;
(*p) = 0xbd;
}
else if (*p == 0xbd) {
*(p - 2) = 0xe2;
*(p - 1) = 0xb1;
(*p) = 0xa3;
}
break;
case 0xb6: /* Latin ext */
if (*p == 0x8e) {
*(p - 2) = 0xea;
*(p - 1) = 0x9f;
(*p) = 0x86;
}
break;
case 0xb8: /* Latin ext */
if ((*p >= 0x80)
&& (*p <= 0xbf)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
break;
case 0xb9: /* Latin ext */
if ((*p >= 0x80)
&& (*p <= 0xbf)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
break;
case 0xba: /* Latin ext */
if ((*p >= 0x80)
&& (*p <= 0x95)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
else if ((*p >= 0xa0)
&& (*p <= 0xbf)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
break;
case 0xbb: /* Latin ext */
if ((*p >= 0x80)
&& (*p <= 0xbf)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
break;
case 0xbc: /* Greek ext */
if ((*p >= 0x80)
&& (*p <= 0x87))
(*p) += 0x08;
else if ((*p >= 0x90)
&& (*p <= 0x95))
(*p) += 0x08;
else if ((*p >= 0xa0)
&& (*p <= 0xa7))
(*p) += 0x08;
else if ((*p >= 0xb0)
&& (*p <= 0xb7))
(*p) += 0x08;
break;
case 0xbd: /* Greek ext */
if ((*p >= 0x80)
&& (*p <= 0x85))
(*p) += 0x08;
else if ((*p == 0x91)
|| (*p == 0x93)
|| (*p == 0x95)
|| (*p == 0x97))
(*p) += 0x08;
else if ((*p >= 0xa0)
&& (*p <= 0xa7))
(*p) += 0x08;
else if ((*p >= 0xb0)
&& (*p <= 0xb1)) {
*(p - 1) = 0xbe;
(*p) += 0x0a;
}
else if ((*p >= 0xb2)
&& (*p <= 0xb5)) {
*(p - 1) = 0xbf;
(*p) -= 0x2a;
}
else if ((*p >= 0xb6)
&& (*p <= 0xb7)) {
*(p - 1) = 0xbf;
(*p) -= 0x1c;
}
else if ((*p >= 0xb8)
&& (*p <= 0xb9)) {
*(p - 1) = 0xbf;
}
else if ((*p >= 0xba)
&& (*p <= 0xbb)) {
*(p - 1) = 0xbf;
(*p) -= 0x10;
}
else if ((*p >= 0xbc)
&& (*p <= 0xbd)) {
*(p - 1) = 0xbf;
(*p) -= 0x02;
}
break;
case 0xbe: /* Greek ext */
if ((*p >= 0x80)
&& (*p <= 0x87))
(*p) += 0x08;
else if ((*p >= 0x90)
&& (*p <= 0x97))
(*p) += 0x08;
else if ((*p >= 0xa0)
&& (*p <= 0xa7))
(*p) += 0x08;
else if ((*p >= 0xb0)
&& (*p <= 0xb1))
(*p) += 0x08;
else if (*p == 0xb3)
(*p) += 0x09;
break;
case 0xbf: /* Greek ext */
if (*p == 0x83)
(*p) += 0x09;
else if ((*p >= 0x90)
&& (*p <= 0x91))
*p += 0x08;
else if ((*p >= 0xa0)
&& (*p <= 0xa1))
(*p) += 0x08;
else if (*p == 0xa5)
(*p) += 0x07;
else if (*p == 0xb3)
(*p) += 0x09;
break;
default:
break;
}
break;
case 0xe2: /* Three byte code */
pExtChar = p;
p++;
switch (*pExtChar) {
case 0xb0: /* Glagolitic */
if ((*p >= 0xb0)
&& (*p <= 0xbf)) {
(*p) -= 0x30;
}
break;
case 0xb1: /* Glagolitic */
if ((*p >= 0x80)
&& (*p <= 0x9e)) {
*pExtChar = 0xb0;
(*p) += 0x10;
}
else { /* Latin ext */
switch (*p) {
case 0xa1:
case 0xa8:
case 0xaa:
case 0xac:
case 0xb3:
case 0xb6:
(*p)--; /* Prev char is upr */
break;
case 0xa5: /* Two byte capital 0xc8 0xba */
case 0xa6: /* Two byte capital 0xc8 0xbe */
break;
default:
break;
}
}
break;
case 0xb2: /* Coptic */
if ((*p >= 0x80)
&& (*p <= 0xbf)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
break;
case 0xb3: /* Coptic */
if (((*p >= 0x80)
&& (*p <= 0xa3)
&& (*p % 2)) /* Odd */
|| (*p == 0xac)
|| (*p == 0xae)
|| (*p == 0xb3))
(*p)--; /* Prev char is upr */
break;
case 0xb4: /* Georgian */
if (((*p >= 0x80)
&& (*p <= 0xa5))
|| (*p == 0xa7)
|| (*p == 0xad)) {
*(p - 2) = 0xe1;
*(p - 1) = 0xb2;
*(p) += 0x10;
}
break;
default:
break;
}
break;
case 0xea: /* Three byte code */
pExtChar = p;
p++;
switch (*pExtChar) {
case 0x99: /* Cyrillic */
if ((*p >= 0x80)
&& (*p <= 0xad)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
break;
case 0x9a: /* Cyrillic */
if ((*p >= 0x80)
&& (*p <= 0x9b)
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
break;
case 0x9c: /* Latin ext */
if ((((*p >= 0xa2)
&& (*p <= 0xaf))
|| ((*p >= 0xb2)
&& (*p <= 0xbf)))
&& (*p % 2)) /* Odd */
(*p)--; /* Prev char is upr */
break;
case 0x9d: /* Latin ext */
if (((*p >= 0x80)
&& (*p <= 0xaf)
&& (*p % 2)) /* Odd */
|| (*p == 0xba)
|| (*p == 0xbc)
|| (*p == 0xbf))
(*p)--; /* Prev char is upr */
break;
case 0x9e: /* Latin ext */
if (((((*p >= 0x80)
&& (*p <= 0x87))
|| ((*p >= 0x96)
&& (*p <= 0xa9))
|| ((*p >= 0xb4)
&& (*p <= 0xbf)))
&& (*p % 2)) /* Odd */
|| (*p == 0x8c)
|| (*p == 0x91)
|| (*p == 0x93))
(*p)--; /* Prev char is upr */
else if (*p == 0x94) {
*(p - 2) = 0xea;
*(p - 1) = 0x9f;
*(p) = 0x84;
}
break;
case 0x9f: /* Latin ext */
if ((*p == 0x83)
|| (*p == 0x88)
|| (*p == 0x8a)
|| (*p == 0xb6))
(*p)--; /* Prev char is upr */
break;
case 0xad:
/* Latin ext */
if (*p == 0x93) {
*pExtChar = 0x9e;
(*p) = 0xb3;
}
/* Cherokee */
else if ((*p >= 0xb0)
&& (*p <= 0xbf)) {
*(p - 2) = 0xe1;
*pExtChar = 0x8e;
(*p) -= 0x10;
}
break;
case 0xae: /* Cherokee */
if ((*p >= 0x80)
&& (*p <= 0x8f)) {
*(p - 2) = 0xe1;
*pExtChar = 0x8e;
(*p) += 0x30;
}
else if ((*p >= 0x90)
&& (*p <= 0xbf)) {
*(p - 2) = 0xe1;
*pExtChar = 0x8f;
(*p) -= 0x10;
}
break;
default:
break;
}
break;
case 0xef: /* Three byte code */
pExtChar = p;
p++;
switch (*pExtChar) {
case 0xbd: /* Latin fullwidth */
if ((*p >= 0x81)
&& (*p <= 0x9a)) {
*pExtChar = 0xbc;
(*p) += 0x20;
}
break;
default:
break;
}
break;
case 0xf0: /* Four byte code */
pExtChar = p;
p++;
switch (*pExtChar) {
case 0x90:
pExtChar = p;
p++;
switch (*pExtChar) {
case 0x90: /* Deseret */
if ((*p >= 0xa8)
&& (*p <= 0xbf)) {
(*p) -= 0x28;
}
break;
case 0x91: /* Deseret */
if ((*p >= 0x80)
&& (*p <= 0x8f)) {
*pExtChar = 0x90;
(*p) += 0x18;
}
break;
case 0x93: /* Osage */
if ((*p >= 0x98)
&& (*p <= 0xa7)) {
*pExtChar = 0x92;
(*p) += 0x18;
}
else if ((*p >= 0xa8)
&& (*p <= 0xbb))
(*p) -= 0x28;
break;
case 0xb3: /* Old hungarian */
if ((*p >= 0x80)
&& (*p <= 0xb2))
*pExtChar = 0xb2;
break;
default:
break;
}
break;
case 0x91:
pExtChar = p;
p++;
switch (*pExtChar) {
case 0xa3: /* Warang citi */
if ((*p >= 0x80)
&& (*p <= 0x9f)) {
*pExtChar = 0xa2;
(*p) += 0x20;
}
break;
default:
break;
}
break;
case 0x96:
pExtChar = p;
p++;
switch (*pExtChar) {
case 0xb9: /* Medefaidrin */
if ((*p >= 0xa0)
&& (*p <= 0xbf))
(*p) -= 0x20;
break;
default:
break;
}
break;
case 0x9E:
pExtChar = p;
p++;
switch (*pExtChar) {
case 0xA4: /* Adlam */
if ((*p >= 0xa2)
&& (*p <= 0xbf))
(*p) -= 0x22;
break;
case 0xA5: /* Adlam */
if ((*p >= 0x80)
&& (*p <= 0x83)) {
*(pExtChar) = 0xa4;
(*p) += 0x1e;
}
break;
default:
break;
}
break;
}
break;
default:
break;
}
pExtChar = 0;
}
p++;
}
}
return pString;
}