转载: 实测可用的php中文转拼音的程序

2014年05月03日 01:22 by:佚名作者

导读: 老吧博客实测可以用的中文转拼音php程序, 有的时候要经常用到, 保存以便以后查询. 这段中文转换成拼音的php类支持gb2312和utf-8模式输出.

最近在把中文关键词转换文件名的时候用到php中文转拼音的函数(支持gb2312和utf-8), 百度了一下, 找到下面的这段代码, 经老修测试高效可用. 保存以便日后再次查找. 
  1. header("Content-Type:text/html;charset=utf-8");
  2. function Pinyin($_String, $_Code='gb2312'){
  3. $_DataKey = "a|ai|an|ang|ao|ba|bai|ban|bang|bao|bei|ben|beng|bi|bian|biao|bie|bin|bing|bo|bu|ca|cai|can|cang|cao|ce|ceng|cha".
  4. "|chai|chan|chang|chao|che|chen|cheng|chi|chong|chou|chu|chuai|chuan|chuang|chui|chun|chuo|ci|cong|cou|cu|".
  5. "cuan|cui|cun|cuo|da|dai|dan|dang|dao|de|deng|di|dian|diao|die|ding|diu|dong|dou|du|duan|dui|dun|duo|e|en|er".
  6. "|fa|fan|fang|fei|fen|feng|fo|fou|fu|ga|gai|gan|gang|gao|ge|gei|gen|geng|gong|gou|gu|gua|guai|guan|guang|gui".
  7. "|gun|guo|ha|hai|han|hang|hao|he|hei|hen|heng|hong|hou|hu|hua|huai|huan|huang|hui|hun|huo|ji|jia|jian|jiang".
  8. "|jiao|jie|jin|jing|jiong|jiu|ju|juan|jue|jun|ka|kai|kan|kang|kao|ke|ken|keng|kong|kou|ku|kua|kuai|kuan|kuang".
  9. "|kui|kun|kuo|la|lai|lan|lang|lao|le|lei|leng|li|lia|lian|liang|liao|lie|lin|ling|liu|long|lou|lu|lv|luan|lue".
  10. "|lun|luo|ma|mai|man|mang|mao|me|mei|men|meng|mi|mian|miao|mie|min|ming|miu|mo|mou|mu|na|nai|nan|nang|nao|ne".
  11. "|nei|nen|neng|ni|nian|niang|niao|nie|nin|ning|niu|nong|nu|nv|nuan|nue|nuo|o|ou|pa|pai|pan|pang|pao|pei|pen".
  12. "|peng|pi|pian|piao|pie|pin|ping|po|pu|qi|qia|qian|qiang|qiao|qie|qin|qing|qiong|qiu|qu|quan|que|qun|ran|rang".
  13. "|rao|re|ren|reng|ri|rong|rou|ru|ruan|rui|run|ruo|sa|sai|san|sang|sao|se|sen|seng|sha|shai|shan|shang|shao|".
  14. "she|shen|sheng|shi|shou|shu|shua|shuai|shuan|shuang|shui|shun|shuo|si|song|sou|su|suan|sui|sun|suo|ta|tai|".
  15. "tan|tang|tao|te|teng|ti|tian|tiao|tie|ting|tong|tou|tu|tuan|tui|tun|tuo|wa|wai|wan|wang|wei|wen|weng|wo|wu".
  16. "|xi|xia|xian|xiang|xiao|xie|xin|xing|xiong|xiu|xu|xuan|xue|xun|ya|yan|yang|yao|ye|yi|yin|ying|yo|yong|you".
  17. "|yu|yuan|yue|yun|za|zai|zan|zang|zao|ze|zei|zen|zeng|zha|zhai|zhan|zhang|zhao|zhe|zhen|zheng|zhi|zhong|".
  18. "zhou|zhu|zhua|zhuai|zhuan|zhuang|zhui|zhun|zhuo|zi|zong|zou|zu|zuan|zui|zun|zuo";
  19. $_DataValue = "-20319|-20317|-20304|-20295|-20292|-20283|-20265|-20257|-20242|-20230|-20051|-20036|-20032|-20026|-20002|-19990".
  20. "|-19986|-19982|-19976|-19805|-19784|-19775|-19774|-19763|-19756|-19751|-19746|-19741|-19739|-19728|-19725".
  21. "|-19715|-19540|-19531|-19525|-19515|-19500|-19484|-19479|-19467|-19289|-19288|-19281|-19275|-19270|-19263".
  22. "|-19261|-19249|-19243|-19242|-19238|-19235|-19227|-19224|-19218|-19212|-19038|-19023|-19018|-19006|-19003".
  23. "|-18996|-18977|-18961|-18952|-18783|-18774|-18773|-18763|-18756|-18741|-18735|-18731|-18722|-18710|-18697".
  24. "|-18696|-18526|-18518|-18501|-18490|-18478|-18463|-18448|-18447|-18446|-18239|-18237|-18231|-18220|-18211".
  25. "|-18201|-18184|-18183|-18181|-18012|-17997|-17988|-17970|-17964|-17961|-17950|-17947|-17931|-17928|-17922".
  26. "|-17759|-17752|-17733|-17730|-17721|-17703|-17701|-17697|-17692|-17683|-17676|-17496|-17487|-17482|-17468".
  27. "|-17454|-17433|-17427|-17417|-17202|-17185|-16983|-16970|-16942|-16915|-16733|-16708|-16706|-16689|-16664".
  28. "|-16657|-16647|-16474|-16470|-16465|-16459|-16452|-16448|-16433|-16429|-16427|-16423|-16419|-16412|-16407".
  29. "|-16403|-16401|-16393|-16220|-16216|-16212|-16205|-16202|-16187|-16180|-16171|-16169|-16158|-16155|-15959".
  30. "|-15958|-15944|-15933|-15920|-15915|-15903|-15889|-15878|-15707|-15701|-15681|-15667|-15661|-15659|-15652".
  31. "|-15640|-15631|-15625|-15454|-15448|-15436|-15435|-15419|-15416|-15408|-15394|-15385|-15377|-15375|-15369".
  32. "|-15363|-15362|-15183|-15180|-15165|-15158|-15153|-15150|-15149|-15144|-15143|-15141|-15140|-15139|-15128".
  33. "|-15121|-15119|-15117|-15110|-15109|-14941|-14937|-14933|-14930|-14929|-14928|-14926|-14922|-14921|-14914".
  34. "|-14908|-14902|-14894|-14889|-14882|-14873|-14871|-14857|-14678|-14674|-14670|-14668|-14663|-14654|-14645".
  35. "|-14630|-14594|-14429|-14407|-14399|-14384|-14379|-14368|-14355|-14353|-14345|-14170|-14159|-14151|-14149".
  36. "|-14145|-14140|-14137|-14135|-14125|-14123|-14122|-14112|-14109|-14099|-14097|-14094|-14092|-14090|-14087".
  37. "|-14083|-13917|-13914|-13910|-13907|-13906|-13905|-13896|-13894|-13878|-13870|-13859|-13847|-13831|-13658".
  38. "|-13611|-13601|-13406|-13404|-13400|-13398|-13395|-13391|-13387|-13383|-13367|-13359|-13356|-13343|-13340".
  39. "|-13329|-13326|-13318|-13147|-13138|-13120|-13107|-13096|-13095|-13091|-13076|-13068|-13063|-13060|-12888".
  40. "|-12875|-12871|-12860|-12858|-12852|-12849|-12838|-12831|-12829|-12812|-12802|-12607|-12597|-12594|-12585".
  41. "|-12556|-12359|-12346|-12320|-12300|-12120|-12099|-12089|-12074|-12067|-12058|-12039|-11867|-11861|-11847".
  42. "|-11831|-11798|-11781|-11604|-11589|-11536|-11358|-11340|-11339|-11324|-11303|-11097|-11077|-11067|-11055".
  43. "|-11052|-11045|-11041|-11038|-11024|-11020|-11019|-11018|-11014|-10838|-10832|-10815|-10800|-10790|-10780".
  44. "|-10764|-10587|-10544|-10533|-10519|-10331|-10329|-10328|-10322|-10315|-10309|-10307|-10296|-10281|-10274".
  45. "|-10270|-10262|-10260|-10256|-10254";
  46. $_TDataKey = explode('|', $_DataKey);
  47. $_TDataValue = explode('|', $_DataValue);
  48. $_Data = (PHP_VERSION>='5.0') ? array_combine($_TDataKey, $_TDataValue) : _Array_Combine($_TDataKey, $_TDataValue);
  49. arsort($_Data);
  50. reset($_Data);
  51. if($_Code != 'gb2312') $_String = _U2_Utf8_Gb($_String);
  52. $_Res = '';
  53. for($i=0; $i<strlen($_String); $i++){
  54. $_P = ord(substr($_String, $i, 1));
  55. if($_P>160) { $_Q = ord(substr($_String, ++$i, 1)); $_P = $_P*256 + $_Q - 65536; }
  56. $_Res .= _Pinyin($_P, $_Data);
  57. }
  58. return preg_replace("/[^a-z0-9]*/", '', $_Res);
  59. }


  60. function _Pinyin($_Num, $_Data){
  61. if ($_Num>0 && $_Num<160 ) {
  62. return chr($_Num);
  63. }elseif($_Num<-20319 || $_Num>-10247) {
  64. return '';
  65. }else {
  66. foreach($_Data as $k=>$v){ if($v<=$_Num) break; }
  67. return $k;
  68. }
  69. }
  70. function _U2_Utf8_Gb($_C){
  71. $_String = '';
  72. if($_C < 0x80){
  73. $_String .= $_C;
  74. }elseif($_C < 0x800){
  75. $_String .= chr(0xC0 | $_C>>6);
  76. $_String .= chr(0x80 | $_C & 0x3F);
  77. }elseif($_C < 0x10000){
  78. $_String .= chr(0xE0 | $_C>>12);
  79. $_String .= chr(0x80 | $_C>>6 & 0x3F);
  80. $_String .= chr(0x80 | $_C & 0x3F);
  81. } elseif($_C < 0x200000) {
  82. $_String .= chr(0xF0 | $_C>>18);
  83. $_String .= chr(0x80 | $_C>>12 & 0x3F);
  84. $_String .= chr(0x80 | $_C>>6 & 0x3F);
  85. $_String .= chr(0x80 | $_C & 0x3F);
  86. }
  87. return iconv('UTF-8', 'GB2312', $_String);
  88. }
  89. function _Array_Combine($_Arr1, $_Arr2){
  90. for($i=0; $i<count($_Arr1); $i++) $_Res[$_Arr1[$i]] = $_Arr2[$i];
  91. return $_Res;
  92. }
  93. //用法:
  94. //第二个参数留空则为gb1232编码
  95. // echo Pinyin('老吧博客');
  96. //第二个参数随意设置则为utf-8编码
  97. echo Pinyin('老吧博客',1);