获取汉字拼音
1、获取汉字拼音的首字母
string GetFirstLetter(const char* strChs) { static int li_SecPosValue[] = { 1601, 1637, 1833, 2078, 2274, 2302, 2433, 2594, 2787, 3106, 3212, 3472, 3635, 3722, 3730, 3858, 4027, 4086, 4390, 4558, 4684, 4925, 5249 }; static char* lc_FirstLetter[] = { "A", "B", "C", "D", "E", "F", "G", "H", "J", "K", "L", "M", "N", "O", "P", "Q", "R", "S", "T", "W", "X", "Y", "Z" }; static char* ls_SecondSecTable = "CJWGNSPGCGNE[Y[BTYYZDXYKYGT[JNNJQMBSGZSCYJSYY[PGKBZGY[YWJKGKLJYWKPJQHY[W[DZLSGMRYPYWWCCKZNKYYGTTNJJNYKKZYTCJNMCYLQLYPYQFQRPZSLWBTGKJFYXJWZLTBNCXJJJJTXDTTSQZYCDXXHGCK[PHFFSS[YBGXLPPBYLL[HLXS[ZM[JHSOJNGHDZQYKLGJHSGQZHXQGKEZZWYSCSCJXYEYXADZPMDSSMZJZQJYZC[J[WQJBYZPXGZNZCPWHKXHQKMWFBPBYDTJZZKQHY" "LYGXFPTYJYYZPSZLFCHMQSHGMXXSXJ[[DCSBBQBEFSJYHXWGZKPYLQBGLDLCCTNMAYDDKSSNGYCSGXLYZAYBNPTSDKDYLHGYMYLCXPY[JNDQJWXQXFYYFJLEJPZRXCCQWQQSBNKYMGPLBMJRQCFLNYMYQMSQYRBCJTHZTQFRXQHXMJJCJLXQGJMSHZKBSWYEMYLTXFSYDSWLYCJQXSJNQBSCTYHBFTDCYZDJWYGHQFRXWCKQKXEBPTLPXJZSRMEBWHJLBJSLYYSMDXLCLQKXLHXJRZJMFQHXHWY" "WSBHTRXXGLHQHFNM[YKLDYXZPYLGG[MTCFPAJJZYLJTYANJGBJPLQGDZYQYAXBKYSECJSZNSLYZHSXLZCGHPXZHZNYTDSBCJKDLZAYFMYDLEBBGQYZKXGLDNDNYSKJSHDLYXBCGHXYPKDJMMZNGMMCLGWZSZXZJFZNMLZZTHCSYDBDLLSCDDNLKJYKJSYCJLKWHQASDKNHCSGANHDAASHTCPLCPQYBSDMPJLPZJOQLCDHJJYSPRCHN[NNLHLYYQYHWZPTCZGWWMZFFJQQQQYXACLBHKDJXDGMMY" "DJXZLLSYGXGKJRYWZWYCLZMSSJZLDBYD[FCXYHLXCHYZJQ[[QAGMNYXPFRKSSBJLYXYSYGLNSCMHZWWMNZJJLXXHCHSY[[TTXRYCYXBYHCSMXJSZNPWGPXXTAYBGAJCXLY[DCCWZOCWKCCSBNHCPDYZNFCYYTYCKXKYBSQKKYTQQXFCWCHCYKELZQBSQYJQCCLMTHSYWHMKTLKJLYCXWHEQQHTQH[PQ[QSCFYMNDMGBWHWLGSLLYSDLMLXPTHMJHWLJZYHZJXHTXJLHXRSWLWZJCBXMHZQXSDZP" "MGFCSGLSXYMJSHXPJXWMYQKSMYPLRTHBXFTPMHYXLCHLHLZYLXGSSSSTCLSLDCLRPBHZHXYYFHB[GDMYCNQQWLQHJJ[YWJZYEJJDHPBLQXTQKWHLCHQXAGTLXLJXMSL[HTZKZJECXJCJNMFBY[SFYWYBJZGNYSDZSQYRSLJPCLPWXSDWEJBJCBCNAYTWGMPAPCLYQPCLZXSBNMSGGFNZJJBZSFZYNDXHPLQKZCZWALSBCCJX[YZGWKYPSGXFZFCDKHJGXDLQFSGDSLQWZKXTMHSBGZMJZRGLYJB" "PMLMSXLZJQQHZYJCZYDJWBMYKLDDPMJEGXYHYLXHLQYQHKYCWCJMYYXNATJHYCCXZPCQLBZWWYTWBQCMLPMYRJCCCXFPZNZZLJPLXXYZTZLGDLDCKLYRZZGQTGJHHGJLJAXFGFJZSLCFDQZLCLGJDJCSNZLLJPJQDCCLCJXMYZFTSXGCGSBRZXJQQCTZHGYQTJQQLZXJYLYLBCYAMCSTYLPDJBYREGKLZYZHLYSZQLZNWCZCLLWJQJJJKDGJZOLBBZPPGLGHTGZXYGHZMYCNQSYCYHBHGXKAMTX" "YXNBSKYZZGJZLQJDFCJXDYGJQJJPMGWGJJJPKQSBGBMMCJSSCLPQPDXCDYYKY[CJDDYYGYWRHJRTGZNYQLDKLJSZZGZQZJGDYKSHPZMTLCPWNJAFYZDJCNMWESCYGLBTZCGMSSLLYXQSXSBSJSBBSGGHFJLYPMZJNLYYWDQSHZXTYYWHMZYHYWDBXBTLMSYYYFSXJC[DXXLHJHF[SXZQHFZMZCZTQCXZXRTTDJHNNYZQQMNQDMMG[YDXMJGDHCDYZBFFALLZTDLTFXMXQZDNGWQDBDCZJDXBZGS" "QQDDJCMBKZFFXMKDMDSYYSZCMLJDSYNSBRSKMKMPCKLGDBQTFZSWTFGGLYPLLJZHGJ[GYPZLTCSMCNBTJBQFKTHBYZGKPBBYMTDSSXTBNPDKLEYCJNYDDYKZDDHQHSDZSCTARLLTKZLGECLLKJLQJAQNBDKKGHPJTZQKSECSHALQFMMGJNLYJBBTMLYZXDCJPLDLPCQDHZYCBZSCZBZMSLJFLKRZJSNFRGJHXPDHYJYBZGDLQCSEZGXLBLGYXTWMABCHECMWYJYZLLJJYHLG[DJLSLYGKDZPZXJ" "YYZLWCXSZFGWYYDLYHCLJSCMBJHBLYZLYCBLYDPDQYSXQZBYTDKYXJY[CNRJMPDJGKLCLJBCTBJDDBBLBLCZQRPPXJCJLZCSHLTOLJNMDDDLNGKAQHQHJGYKHEZNMSHRP[QQJCHGMFPRXHJGDYCHGHLYRZQLCYQJNZSQTKQJYMSZSWLCFQQQXYFGGYPTQWLMCRNFKKFSYYLQBMQAMMMYXCTPSHCPTXXZZSMPHPSHMCLMLDQFYQXSZYYDYJZZHQPDSZGLSTJBCKBXYQZJSGPSXQZQZRQTBDKYXZK" "HHGFLBCSMDLDGDZDBLZYYCXNNCSYBZBFGLZZXSWMSCCMQNJQSBDQSJTXXMBLTXZCLZSHZCXRQJGJYLXZFJPHYMZQQYDFQJJLZZNZJCDGZYGCTXMZYSCTLKPHTXHTLBJXJLXSCDQXCBBTJFQZFSLTJBTKQBXXJJLJCHCZDBZJDCZJDCPRNPQCJPFCZLCLZXZDMXMPHJSGZGSZZQLYLWTJPFSYASMCJBTZKYCWMYTCSJJLJCQLWZMALBXYFBPNLSFHTGJWEJJXXGLLJSTGSHJQLZFKCGNNNSZFDEQ" "FHBSAQTGYLBXMMYGSZLDYDQMJJRGBJTKGDHGKBLQKBDMBYLXWCXYTTYBKMRTJZXQJBHLMHMJJZMQASLDCYXYQDLQCAFYWYXQHZ"; std::string result; int H = 0; int L = 0; int W = 0; UINT stringlen = strlen(strChs); for (UINT i = 0; i < stringlen; i++) { H = (UCHAR)(strChs[i + 0]); L = (UCHAR)(strChs[i + 1]); if (H < 0xA1 || L < 0xA1) { result += strChs[i]; continue; } else { W = (H - 160) * 100 + L - 160; } if (W > 1600 && W < 5590) { for (int j = 22; j >= 0; j--) { if (W >= li_SecPosValue[j]) { result += lc_FirstLetter[j]; i++; break; } } continue; } else { i++; W = (H - 160 - 56) * 94 + L - 161; if (W >= 0 && W <= 3007) result += ls_SecondSecTable[W]; else { result += (char)H; result += (char)L; } } } return result; } string str = GetFirstLetter("测试数据"); //str为CSSJ
常见多音字:
行,H,X
长,Z,C
藏,Z,C
重,Z,C
盛,S,C
奇,Q,j
阿,E,A
畜,X,C
单,D,S
系,J,X
校,X,J
省,S,X
宿,X,S
2、获取汉字拼音
#include <iostream> #include <vector> #include <algorithm> #include <locale> int main(int argc, char** argv) { // 设置中文 locale(需系统支持) std::locale loc("Chinese_China.936"); //Windows 可用 "Chinese_China.936" 或 "zh-CN" //std::locale loc("zh_CN.UTF-8"); // Linux/macOS 常见 // 若失败可尝试 std::locale("") 使用系统默认,但需确保系统区域为中文 std::vector<std::string> words = { "张三", "李四", "王五", "赵六", "安琪" }; // 使用 collate 进行字符串比较 const std::collate<char>& coll = std::use_facet<std::collate<char>>(loc); std::sort(words.begin(), words.end(), [&](const std::string& a, const std::string& b) { return coll.compare(a.data(), a.data() + a.size(), b.data(), b.data() + b.size()) < 0; }); for (const auto& s : words) std::cout << s << std::endl; return 0; }
3、其它方法
使用轻量级的开源库pinyin4cpp,或者功能丰富的cpp-pinyin(支持多音字处理)。
浙公网安备 33010602011771号