搜索
首页后端开发php教程PHP 汉字转拼音源码(GB2312类库,大约支持6000个汉字左右)

最近一个项目中使用php作为为前端提供数据的开发语言,为了实现能够按照字母排序,需要提取中文的汉语拼音,借这个项目写了个汉字转拼音的脚本,脚本比较简单,注释也比较详细,这里就不多说了,直接上代码了。

使用方法:

  1. $py = new PinYin();
  2. $all_py = $py->get_all_py("吴国伟"); //输出 ['wu','guo','wei'],输出字符串调用join方法,join('',$all_py)
  3. $first_py = $py->get_first_py($all_py);//输出 wgw
  4. $first_letter = $py->get_first_letter($all_py);// 输出 w
复制代码


源码:

  1. /**
  2. * +------------------------------------------------------
  3. * PHP 汉字转拼音
  4. * +------------------------------------------------------
  5. * 使用方法:
  6. * $py = new PinYin();
  7. * $all_py = $py->get_all_py("吴国伟"); //输出 ['wu','guo','wei'],输出字符串调用join方法,join('',$all_py)
  8. * $first_py = $py->get_first_py($all_py);//输出 wgw
  9. * $first_letter = $py->get_first_letter($all_py);// 输出 w
  10. *
  11. * +------------------------------------------------------
  12. */
  13. class PinYin
  14. {
  15. private $dict_list = array(
  16. 'a' => -20319, 'ai' => -20317, 'an' => -20304, 'ang' => -20295, 'ao' => -20292,
  17. 'ba' => -20283, 'bai' => -20265, 'ban' => -20257, 'bang' => -20242, 'bao' => -20230, 'bei' => -20051, 'ben' => -20036, 'beng' => -20032, 'bi' => -20026, 'bian' => -20002, 'biao' => -19990, 'bie' => -19986, 'bin' => -19982, 'bing' => -19976, 'bo' => -19805, 'bu' => -19784,
  18. 'ca' => -19775, 'cai' => -19774, 'can' => -19763, 'cang' => -19756, 'cao' => -19751, 'ce' => -19746, 'ceng' => -19741, 'cha' => -19739, 'chai' => -19728, 'chan' => -19725, 'chang' => -19715, 'chao' => -19540, 'che' => -19531, 'chen' => -19525, 'cheng' => -19515, 'chi' => -19500, 'chong' => -19484, 'chou' => -19479, 'chu' => -19467, 'chuai' => -19289, 'chuan' => -19288, 'chuang' => -19281, 'chui' => -19275, 'chun' => -19270, 'chuo' => -19263, 'ci' => -19261, 'cong' => -19249, 'cou' => -19243, 'cu' => -19242, 'cuan' => -19238, 'cui' => -19235, 'cun' => -19227, 'cuo' => -19224,
  19. 'da' => -19218, 'dai' => -19212, 'dan' => -19038, 'dang' => -19023, 'dao' => -19018, 'de' => -19006, 'deng' => -19003, 'di' => -18996, 'dian' => -18977, 'diao' => -18961, 'die' => -18952, 'ding' => -18783, 'diu' => -18774, 'dong' => -18773, 'dou' => -18763, 'du' => -18756, 'duan' => -18741, 'dui' => -18735, 'dun' => -18731, 'duo' => -18722,
  20. 'e' => -18710, 'en' => -18697, 'er' => -18696,
  21. 'fa' => -18526, 'fan' => -18518, 'fang' => -18501, 'fei' => -18490, 'fen' => -18478, 'feng' => -18463, 'fo' => -18448, 'fou' => -18447, 'fu' => -18446,
  22. 'ga' => -18239, 'gai' => -18237, 'gan' => -18231, 'gang' => -18220, 'gao' => -18211, 'ge' => -18201, 'gei' => -18184, 'gen' => -18183, 'geng' => -18181, 'gong' => -18012, 'gou' => -17997, 'gu' => -17988, 'gua' => -17970, 'guai' => -17964, 'guan' => -17961, 'guang' => -17950, 'gui' => -17947,
  23. 'gun' => -17931, 'guo' => -17928,
  24. 'ha' => -17922, 'hai' => -17759, 'han' => -17752, 'hang' => -17733, 'hao' => -17730, 'he' => -17721, 'hei' => -17703, 'hen' => -17701, 'heng' => -17697, 'hong' => -17692, 'hou' => -17683, 'hu' => -17676, 'hua' => -17496, 'huai' => -17487, 'huan' => -17482, 'huang' => -17468, 'hui' => -17454,
  25. 'hun' => -17433, 'huo' => -17427,
  26. 'ji' => -17417, 'jia' => -17202, 'jian' => -17185, 'jiang' => -16983, 'jiao' => -16970, 'jie' => -16942, 'jin' => -16915, 'jing' => -16733, 'jiong' => -16708, 'jiu' => -16706, 'ju' => -16689, 'juan' => -16664, 'jue' => -16657, 'jun' => -16647,
  27. 'ka' => -16474, 'kai' => -16470, 'kan' => -16465, 'kang' => -16459, 'kao' => -16452, 'ke' => -16448, 'ken' => -16433, 'keng' => -16429, 'kong' => -16427, 'kou' => -16423, 'ku' => -16419, 'kua' => -16412, 'kuai' => -16407, 'kuan' => -16403, 'kuang' => -16401, 'kui' => -16393, 'kun' => -16220, 'kuo' => -16216,
  28. 'la' => -16212, 'lai' => -16205, 'lan' => -16202, 'lang' => -16187, 'lao' => -16180, 'le' => -16171, 'lei' => -16169, 'leng' => -16158, 'li' => -16155, 'lia' => -15959, 'lian' => -15958, 'liang' => -15944, 'liao' => -15933, 'lie' => -15920, 'lin' => -15915, 'ling' => -15903, 'liu' => -15889,
  29. 'long' => -15878, 'lou' => -15707, 'lu' => -15701, 'lv' => -15681, 'luan' => -15667, 'lue' => -15661, 'lun' => -15659, 'luo' => -15652,
  30. 'ma' => -15640, 'mai' => -15631, 'man' => -15625, 'mang' => -15454, 'mao' => -15448, 'me' => -15436, 'mei' => -15435, 'men' => -15419, 'meng' => -15416, 'mi' => -15408, 'mian' => -15394, 'miao' => -15385, 'mie' => -15377, 'min' => -15375, 'ming' => -15369, 'miu' => -15363, 'mo' => -15362, 'mou' => -15183, 'mu' => -15180,
  31. 'na' => -15165, 'nai' => -15158, 'nan' => -15153, 'nang' => -15150, 'nao' => -15149, 'ne' => -15144, 'nei' => -15143, 'nen' => -15141, 'neng' => -15140, 'ni' => -15139, 'nian' => -15128, 'niang' => -15121, 'niao' => -15119, 'nie' => -15117, 'nin' => -15110, 'ning' => -15109, 'niu' => -14941,
  32. 'nong' => -14937, 'nu' => -14933, 'nv' => -14930, 'nuan' => -14929, 'nue' => -14928, 'nuo' => -14926,
  33. 'o' => -14922, 'ou' => -14921,
  34. 'pa' => -14914, 'pai' => -14908, 'pan' => -14902, 'pang' => -14894, 'pao' => -14889, 'pei' => -14882, 'pen' => -14873, 'peng' => -14871, 'pi' => -14857, 'pian' => -14678, 'piao' => -14674, 'pie' => -14670, 'pin' => -14668, 'ping' => -14663, 'po' => -14654, 'pu' => -14645,
  35. 'qi' => -14630, 'qia' => -14594, 'qian' => -14429, 'qiang' => -14407, 'qiao' => -14399, 'qie' => -14384, 'qin' => -14379, 'qing' => -14368, 'qiong' => -14355, 'qiu' => -14353, 'qu' => -14345, 'quan' => -14170, 'que' => -14159, 'qun' => -14151,
  36. 'ran' => -14149, 'rang' => -14145, 'rao' => -14140, 're' => -14137, 'ren' => -14135, 'reng' => -14125, 'ri' => -14123, 'rong' => -14122, 'rou' => -14112, 'ru' => -14109, 'ruan' => -14099, 'rui' => -14097, 'run' => -14094, 'ruo' => -14092,
  37. 'sa' => -14090, 'sai' => -14087, 'san' => -14083, 'sang' => -13917, 'sao' => -13914, 'se' => -13910, 'sen' => -13907, 'seng' => -13906, 'sha' => -13905, 'shai' => -13896, 'shan' => -13894, 'shang' => -13878, 'shao' => -13870, 'she' => -13859, 'shen' => -13847, 'sheng' => -13831, 'shi' => -13658, 'shou' => -13611, 'shu' => -13601, 'shua' => -13406, 'shuai' => -13404, 'shuan' => -13400, 'shuang' => -13398, 'shui' => -13395, 'shun' => -13391, 'shuo' => -13387, 'si' => -13383, 'song' => -13367, 'sou' => -13359, 'su' => -13356, 'suan' => -13343, 'sui' => -13340, 'sun' => -13329, 'suo' => -13326,
  38. 'ta' => -13318, 'tai' => -13147, 'tan' => -13138, 'tang' => -13120, 'tao' => -13107, 'te' => -13096, 'teng' => -13095, 'ti' => -13091, 'tian' => -13076, 'tiao' => -13068, 'tie' => -13063, 'ting' => -13060, 'tong' => -12888, 'tou' => -12875, 'tu' => -12871, 'tuan' => -12860, 'tui' => -12858, 'tun' => -12852, 'tuo' => -12849,
  39. 'wa' => -12838, 'wai' => -12831, 'wan' => -12829, 'wang' => -12812, 'wei' => -12802, 'wen' => -12607, 'weng' => -12597, 'wo' => -12594, 'wu' => -12585,
  40. 'xi' => -12556, 'xia' => -12359, 'xian' => -12346, 'xiang' => -12320, 'xiao' => -12300, 'xie' => -12120, 'xin' => -12099, 'xing' => -12089, 'xiong' => -12074, 'xiu' => -12067, 'xu' => -12058, 'xuan' => -12039, 'xue' => -11867, 'xun' => -11861,
  41. 'ya' => -11847, 'yan' => -11831, 'yang' => -11798, 'yao' => -11781, 'ye' => -11604, 'yi' => -11589, 'yin' => -11536, 'ying' => -11358, 'yo' => -11340, 'yong' => -11339, 'you' => -11324, 'yu' => -11303, 'yuan' => -11097, 'yue' => -11077, 'yun' => -11067,
  42. 'za' => -11055, 'zai' => -11052, 'zan' => -11045, 'zang' => -11041, 'zao' => -11038, 'ze' => -11024, 'zei' => -11020, 'zen' => -11019, 'zeng' => -11018, 'zha' => -11014, 'zhai' => -10838, 'zhan' => -10832, 'zhang' => -10815, 'zhao' => -10800, 'zhe' => -10790, 'zhen' => -10780, 'zheng' => -10764, 'zhi' => -10587, 'zhong' => -10544, 'zhou' => -10533, 'zhu' => -10519, 'zhua' => -10331, 'zhuai' => -10329, 'zhuan' => -10328, 'zhuang' => -10322, 'zhui' => -10315, 'zhun' => -10309, 'zhuo' => -10307, 'zi' => -10296, 'zong' => -10281, 'zou' => -10274, 'zu' => -10270, 'zuan' => -10262,
  43. 'zui' => -10260, 'zun' => -10256, 'zuo' => -10254
  44. );
  45. /**
  46. * 获取全部拼音,返回拼音的数组,如 '张三丰' ==> ['zhang','san','feng']
  47. * @param $chinese
  48. * @param string $charset
  49. * @return array
  50. */
  51. public function get_all_py($chinese, $charset = 'utf-8')
  52. {
  53. if ($charset != 'gb2312') $chinese = $this->_U2_Utf8_Gb($chinese);
  54. $py = $this->zh_to_pys($chinese);
  55. return $py;
  56. }
  57. /**
  58. * 获取拼音首字母,如['zhang','san','feng'] ==> zsf
  59. * @param $all_pys
  60. * @return string
  61. */
  62. public function get_first_py($all_pys)
  63. {
  64. if (count($all_pys) return '';
  65. }
  66. $result = [];
  67. foreach ($all_pys as $one) {
  68. if (is_null($one) || strlen($one) continue;
  69. }
  70. $result[] = substr($one, 0, 1);
  71. }
  72. return join('', $result);
  73. }
  74. /**
  75. * 获取拼音首字母,如['zhang','san','feng'] ==> z
  76. * @param $all_pys
  77. * @return string
  78. */
  79. public function get_first_letter($all_pys)
  80. {
  81. if (count($all_pys) return '';
  82. }
  83. foreach ($all_pys as $one) {
  84. if (is_null($one) || strlen($one) continue;
  85. }
  86. return substr($one, 0, 1);
  87. }
  88. return '';
  89. }
  90. private function _U2_Utf8_Gb($_C)
  91. {
  92. $_String = '';
  93. if ($_C elseif ($_C $_String .= chr(0xC0 | $_C >> 6);
  94. $_String .= chr(0x80 | $_C & 0x3F);
  95. } elseif ($_C $_String .= chr(0xE0 | $_C >> 12);
  96. $_String .= chr(0x80 | $_C >> 6 & 0x3F);
  97. $_String .= chr(0x80 | $_C & 0x3F);
  98. } elseif ($_C $_String .= chr(0xF0 | $_C >> 18);
  99. $_String .= chr(0x80 | $_C >> 12 & 0x3F);
  100. $_String .= chr(0x80 | $_C >> 6 & 0x3F);
  101. $_String .= chr(0x80 | $_C & 0x3F);
  102. }
  103. return iconv('UTF-8', 'GB2312', $_String);
  104. }
  105. private function zh_to_py($num, $blank = '')
  106. {
  107. if ($num > 0 && $num return chr($num);
  108. } elseif ($num -10247) {
  109. return $blank;
  110. } else {
  111. foreach ($this->dict_list as $py => $code) {
  112. if ($code > $num) break;
  113. $result = $py;
  114. }
  115. return $result;
  116. }
  117. }
  118. private function zh_to_pys($chinese)
  119. {
  120. $result = array();
  121. for ($i = 0; $i $p = ord(substr($chinese, $i, 1));
  122. if ($p > 160) {
  123. $q = ord(substr($chinese, ++$i, 1));
  124. $p = $p * 256 + $q - 65536;
  125. }
  126. $result[] = $this->zh_to_py($p);
  127. }
  128. return $result;
  129. }
  130. }
复制代码


类库, PHP


声明
本文内容由网友自发贡献,版权归原作者所有,本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容,请联系admin@php.cn
绝对会话超时有什么区别?绝对会话超时有什么区别?May 03, 2025 am 12:21 AM

绝对会话超时从会话创建时开始计时,闲置会话超时则从用户无操作时开始计时。绝对会话超时适用于需要严格控制会话生命周期的场景,如金融应用;闲置会话超时适合希望用户长时间保持会话活跃的应用,如社交媒体。

如果会话在服务器上不起作用,您将采取什么步骤?如果会话在服务器上不起作用,您将采取什么步骤?May 03, 2025 am 12:19 AM

服务器会话失效可以通过以下步骤解决:1.检查服务器配置,确保会话设置正确。2.验证客户端cookies,确认浏览器支持并正确发送。3.检查会话存储服务,如Redis,确保其正常运行。4.审查应用代码,确保会话逻辑正确。通过这些步骤,可以有效诊断和修复会话问题,提升用户体验。

session_start()函数的意义是什么?session_start()函数的意义是什么?May 03, 2025 am 12:18 AM

session_start()iscucialinphpformanagingusersessions.1)ItInitiateSanewsessionifnoneexists,2)resumesanexistingsessions,and3)setsasesessionCookieforContinuityActinuityAccontinuityAcconActInityAcconActInityAcconAccRequests,EnablingApplicationsApplicationsLikeUseAppericationLikeUseAthenticationalticationaltication and PersersonalizedContentent。

为会话cookie设置httponly标志的重要性是什么?为会话cookie设置httponly标志的重要性是什么?May 03, 2025 am 12:10 AM

设置httponly标志对会话cookie至关重要,因为它能有效防止XSS攻击,保护用户会话信息。具体来说,1)httponly标志阻止JavaScript访问cookie,2)在PHP和Flask中可以通过setcookie和make_response设置该标志,3)尽管不能防范所有攻击,但应作为整体安全策略的一部分。

PHP会议在网络开发中解决了什么问题?PHP会议在网络开发中解决了什么问题?May 03, 2025 am 12:02 AM

phpsessions solvathepromblymaintainingStateAcrossMultipleHttpRequestsbyStoringDataTaNthEserVerAndAssociatingItwithaIniquesestionId.1)他们储存了AtoredAtaserver side,通常是Infilesordatabases,InseasessessionIdStoreDistordStoredStoredStoredStoredStoredStoredStoreDoreToreTeReTrestaa.2)

可以在PHP会话中存储哪些数据?可以在PHP会话中存储哪些数据?May 02, 2025 am 12:17 AM

phpsessionscanStorestrings,数字,数组和原始物。

您如何开始PHP会话?您如何开始PHP会话?May 02, 2025 am 12:16 AM

tostartaphpsession,usesesses_start()attheScript'Sbeginning.1)placeitbeforeanyOutputtosetThesessionCookie.2)useSessionsforuserDatalikeloginstatusorshoppingcarts.3)regenerateSessiveIdStopreventFentfixationAttacks.s.4)考虑使用AttActAcks.s.s.4)

什么是会话再生,如何提高安全性?什么是会话再生,如何提高安全性?May 02, 2025 am 12:15 AM

会话再生是指在用户进行敏感操作时生成新会话ID并使旧ID失效,以防会话固定攻击。实现步骤包括:1.检测敏感操作,2.生成新会话ID,3.销毁旧会话ID,4.更新用户端会话信息。

See all articles

热AI工具

Undresser.AI Undress

Undresser.AI Undress

人工智能驱动的应用程序,用于创建逼真的裸体照片

AI Clothes Remover

AI Clothes Remover

用于从照片中去除衣服的在线人工智能工具。

Undress AI Tool

Undress AI Tool

免费脱衣服图片

Clothoff.io

Clothoff.io

AI脱衣机

Video Face Swap

Video Face Swap

使用我们完全免费的人工智能换脸工具轻松在任何视频中换脸!

热工具

SublimeText3 英文版

SublimeText3 英文版

推荐:为Win版本,支持代码提示!

Dreamweaver CS6

Dreamweaver CS6

视觉化网页开发工具

SublimeText3 Mac版

SublimeText3 Mac版

神级代码编辑软件(SublimeText3)

SublimeText3 Linux新版

SublimeText3 Linux新版

SublimeText3 Linux最新版

ZendStudio 13.5.1 Mac

ZendStudio 13.5.1 Mac

功能强大的PHP集成开发环境