[PHP] 中文转拼音首字母简易实现方案
发表于在某些情况下,为了简化查询,我们需要提取中文的拼音首字母,
比如”中华人民共和国” 是ZHRMGHG
最近在ALMRun程序就用到了这个方法,,顺便写了一下PHP版的.感觉PHP的更简单哈,
适用于要求不是很高的场合,因为这个没有处理多音字,只支持GB2312字符,不过优点就是足够简单,几行代码的问题.有需要的可以拿去用,欢迎报错.
源码: https://github.com/chenall/chenall/blob/master/php/tools/ZH-cn_TO_pinyin.php
<?php
/*
中文汉字转拼音首字母的PHP简易实现方法.
要求: 只能是GB2312码表里面中文字符
转换得到字符串对应的拼音首字母大写.
来源: http://chenall.net/
用法:
echo zh2py::conv('Chinese 中华人民共和国');//Chinese ZHRMGHG
或
$py = new zh2py;
echo $py->conv('Chinese 中华人民共和国');//Chinese ZHRMGHG
*/
class zh2py
{
//根据汉字区位表,(http://www.mytju.com/classcode/tools/QuWeiMa_FullList.asp)
//我们可以看到从16-55区之间是按拼音字母排序的,所以我们只需要判断某个汉字的区位码就可以得知它的拼音首字母.
//区位表第一部份,按拼音字母排序的.
//16区-55区
/*
'A'=>0xB0A1, 'B'=>0xB0C5, 'C'=>0xB2C1, 'D'=>0xB4EE, 'E'=>0xB6EA, 'F'=>0xB7A2, 'G'=>0xB8C1,'H'=>0xB9FE,
'J'=>0xBBF7, 'K'=>0xBFA6, 'L'=>0xC0AC, 'M'=>0xC2E8, 'N'=>0xC4C3, 'O'=>0xC5B6, 'P'=>0xC5BE,'Q'=>0xC6DA,
'R'=>0xC8BB, 'S'=>0xC8F6, 'T'=>0xCBFA, 'W'=>0xCDDA, 'X'=>0xCEF4, 'Y'=>0xD1B9, 'Z'=>0xD4D1
*/
private static $FirstTable = array(
0xB0C5, 0xB2C1, 0xB4EE, 0xB6EA, 0xB7A2, 0xB8C1, 0xB9FE, 0xBBF7, 0xBFA6, 0xC0AC, 0xC2E8,
0xC4C3, 0xC5B6, 0xC5BE, 0xC6DA, 0xC8BB, 0xC8F6, 0xCBFA, 0xCDDA, 0xCEF4, 0xD1B9, 0xD4D1,0xD7FA
);
private static $FirstLetter = "ABCDEFGHJKLMNOPQRSTWXYZ";
//区位表第二部份,不规则的,下面的字母是每个区里面对应字的拼音首字母.从网上查询整理出来的,可能会有部份错误.
//56区-87区
private static $SecondTable = array(
"CJWGNSPGCGNEGYPBTYYZDXYKYGTZJNMJQMBSGZSCYJSYYFPGKBZGYDYWJKGKLJSWKPJQHYJWRDZLSYMRYPYWWCCKZNKYYG",
"TTNGJEYKKZYTCJNMCYLQLYPYSFQRPZSLWBTGKJFYXJWZLTBNCXJJJJTXDTTSQZYCDXXHGCKBPHFFSSTYBGMXLPBYLLBHLX",
"SMZMYJHSOJNGHDZQYKLGJHSGQZHXQGKXZZWYSCSCJXYEYXADZPMDSSMZJZQJYZCJJFWQJBDZBXGZNZCPWHWXHQKMWFBPBY",
"DTJZZKXHYLYGXFPTYJYYZPSZLFCHMQSHGMXXSXJYQDCSBBQBEFSJYHWWGZKPYLQBGLDLCDTNMAYDDKSSNGYCSGXLYZAYPN",
"PTSDKDYLHGYMYLCXPYCJNDQJWXQXFYYFJLEJPZRXCCQWQQSBZKYMGPLBMJRQCFLNYMYQMSQYRBCJTHZTQFRXQHXMQJCJLY",
"QGJMSHZKBSWYEMYLTXFSYDXWLYCJQXSJNQBSCTYHBFTDCYZDJWYGHQFRXWCKQKXEBPTLPXJZSRMEBWHJLBJSLYYSMDXLCL",
"QKXLHXJRZJMFQHXHWYWSBHTRXXGLHQHFNMGYKLDYXZPYLGGSMTCFBAJJZYLJTYANJGBJPLQGSZYQYAXBKYSECJSZNSLYZH",
"ZXLZCGHPXZHZNYTDSBCJKDLZAYFFYDLEBBGQYZKXGLDNDNYSKJSHDLYXBCGHXYPKDJMMZNGMMCLGWZSZXZJFZNMLZZTHCS",
"YDBDLLSCDDNLKJYKJSYCJLKWHQASDKNHCSGAGHDAASHTCPLCPQYBSZMPJLPCJOQLCDHJJYSPRCHNWJNLHLYYQYYWZPTCZG",
"WWMZFFJQQQQYXACLBHKDJXDGMMYDJXZLLSYGXGKJRYWZWYCLZMSSJZLDBYDCFCXYHLXCHYZJQSQQAGMNYXPFRKSSBJLYXY",
"SYGLNSCMHCWWMNZJJLXXHCHSYZSTTXRYCYXBYHCSMXJSZNPWGPXXTAYBGAJCXLYXDCCWZOCWKCCSBNHCPDYZNFCYYTYCKX",
"KYBSQKKYTQQXFCMCHCYKELZQBSQYJQCCLMTHSYWHMKTLKJLYCXWHEQQHTQKZPQSQSCFYMMDMGBWHWLGSLLYSDLMLXPTHMJ",
"HWLJZYHZJXKTXJLHXRSWLWZJCBXMHZQXSDZPSGFCSGLSXYMJSHXPJXWMYQKSMYPLRTHBXFTPMHYXLCHLHLZYLXGSSSSTCL",
"SLDCLRPBHZHXYYFHBMGDMYCNQQWLQHJJCYWJZYEJJDHPBLQXTQKWHLCHQXAGTLXLJXMSLJHTZKZJECXJCJNMFBYCSFYWYB",
"JZGNYSDZSQYRSLJPCLPWXSDWEJBJCBCNAYTWGMPAPCLYQPCLZXSBNMSGGFNZJJBZSFZYNTXHPLQKZCZWALSBCZJXSYZGWK",
"YPSGXFZFCDKHJGXTLQFSGDSLQWZKXTMHSBGZMJZRGLYJBPMLMSXLZJQQHZYJCZYDJWFMJKLDDPMJEGXYHYLXHLQYQHKYCW",
"CJMYYXNATJHYCCXZPCQLBZWWYTWBQCMLPMYRJCCCXFPZNZZLJPLXXYZTZLGDLTCKLYRZZGQTTJHHHJLJAXFGFJZSLCFDQZ",
"LCLGJDJZSNZLLJPJQDCCLCJXMYZFTSXGCGSBRZXJQQCTZHGYQTJQQLZXJYLYLBCYAMCSTYLPDJBYREGKLZYZHLYSZQLZNW",
"CZCLLWJQJJJKDGJZOLBBZPPGLGHTGZXYGHZMYCNQSYCYHBHGXKAMTXYXNBSKYZZGJZLQJTFCJXDYGJQJJPMGWGJJJPKQSB",
"GBMMCJSSCLPQPDXCDYYKYPCJDDYYGYWRHJRTGZNYQLDKLJSZZGZQZJGDYKSHPZMTLCPWNJYFYZDJCNMWESCYGLBTZZGMSS",
"LLYXYSXXBSJSBBSGGHFJLYPMZJNLYYWDQSHZXTYYWHMCYHYWDBXBTLMSYYYFSXJCBDXXLHJHFSSXZQHFZMZCZTQCXZXRTT",
"DJHNRYZQQMTQDMMGNYDXMJGDXCDYZBFFALLZTDLTFXMXQZDNGWQDBDCZJDXBZGSQQDDJCMBKZFFXMKDMDSYYSZCMLJDSYN",
"SPRSKMKMPCKLGTBQTFZSWTFGGLYPLLJZHGJJGYPZLTCSMCNBTJBQFKDHBYZGKPBBYMTDSSXTBNPDKLEYCJNYCDYKZTDHQH",
"SYZSCTARLLTKZLGECLLKJLQJAQNBDKKGHPJTZQKSECSHALQFMMGJNLYJBBTMLYZXDXJPLDLPCQDHZYCBZSCZBZMSLJFLKR",
"ZJSNFRGJHXPDHYJYBZGDLQCSEZGXLBLGYXTWMABCHECMWYJYZLLJJYHLGNDJLSLYGKDZPZXJYYZLWCXSZFGWYYDLYHCLJS",
"CMBJHBLYZLYCBLYDPDQYSXQZBYTDKYXJYYCNRJMPDJGKLCLJBCTBJDDBBLBLCZQRPYXJCJLZCSHLTOLJNMDDDLNGKATHQH",
"JHYKHEZNMSHRPHQQJCHGMFPRXHJGDYCHGHLYRZQLCYQJNZSQTKQJYMSZSWLCFQQQXYFGGYPTQWLMCRNFKKFSYYLQBMQAMM",
"MYXCTPSHCPTXXZZSMPHPSHMCLMLDQFYQXSZYJDJJZZHQPDSZGLSTJBCKBXYQZJSGPSXQZQZRQTBDKYXZKHHGFLBCSMDLDG",
"DZDBLZYYCXNNCSYBZBFGLZZXSWMSCCMQNJQSBDQSJTXXMBLTXZCLZSHZCXRQJGJYLXZFJPHYMZQQYDFQJJLZZNZJCDGZYG",
"CTXMZYSCTLKPHTXHTLBJXJLXSCDQXCBBTJFQZFSLTJBTKQBXXJJLJCHCZDBZJDCZJDCPRNPQCJPFCZLCLZXZDMXMPHJSGZ",
"GSZZQLYLWTJPFSYASMCJBTZYYCWMYTZSJJLJCQLWZMALBXYFBPNLSFHTGJWEJJXXGLLJSTGSHJQLZFKCGNNNSZFDEQFHBS",
"AQTGYLBXMMYGSZLDYDQMJJRGBJTKGDHGKBLQKBDMBYLXWCXYTTYBKMRTJZXQJBHLMHMJJZMQASLDCYXYQDLQCAFYWYXQHZ",
);
function utf8_to_gbk($string)//编码转换,必须转换成GB2312字符,这里只是简单的判断并不是很准确,可以自己写一个.
{
if (mb_check_encoding($string,'gb2312'))
return $string;
if (function_exists('iconv'))
return iconv("utf-8","gb2312//IGNORE",$string);
return mb_convert_encoding($string,'gb2312','utf-8');
}
function conv($str)
{
$str = self::utf8_to_gbk($str);
$len = strlen($str);
$newStr = '';
for($i=0; $i<$len ; ++$i)
{
$H = ord($str[$i]);
$L = ord($str[$i+1]);
//字符集非法
if ($H < 0xB0 || $L < 0xA1 || $H > 0xF7 || $L == 0xFF)
{
$newStr .= $str[$i];
continue;
}
if ($H < 0xD8)//($H >= 0xB0 && $H <=0xD7)//查询文字在一级汉字区(16-55)
{
$W = ($H << 8) | $L;
foreach(self::$FirstTable as $key=>$value)
{
if ($W < $value)
{
$newStr .= self::$FirstLetter[$key];
break;
}
}
}
else// if (H >= 0xD8 && H <= 0xF7)//查询中文在二级汉字区(56-87)
$newStr .=self::$SecondTable[$H - 0xD8][$L-0xA1];
++$i;
}
return $newStr;
}
}
echo zh2py::conv('Chinese 中华人民共和国');//Chinese ZHRMGHG