PinYin.Class.php 6.4 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203
  1. <?php
  2. /**
  3. * Created by PhpStorm.
  4. * User: phperstar
  5. * Date: 2020/5/19
  6. * Time: 3:20 PM
  7. */
  8. namespace Util\PinYin;
  9. use Util\PinYin\ChinesePinYin;
  10. class PinYin
  11. {
  12. /**
  13. * @desc 字符串分割成顺序key单字符一维数组
  14. * @param string $string
  15. * @return array
  16. **/
  17. private static function splitString($string) {
  18. $result = array();
  19. $len = mb_strlen($string);
  20. while ($len) {
  21. $result[] = mb_substr($string, 0, 1, 'utf8');
  22. $string = mb_substr($string, 1, $len, 'utf8');
  23. $len = mb_strlen($string);
  24. }
  25. return $result;
  26. }
  27. /**
  28. * @desc 单字符一维数组转变成二维拼音数组
  29. * @param array $stringList
  30. * @return array
  31. **/
  32. private static function changePinyinList($stringList) {
  33. $result = array();
  34. if (!is_array($stringList)) {
  35. return $result;
  36. }
  37. $objChinesePinYin = new ChinesePinYin();
  38. foreach ($stringList as $string) {
  39. if ((strlen($string) === 3) && isset($objChinesePinYin::$chinesePinyin[$string])) {
  40. // 大部分汉字strlen长度为3,在拼音库里。所有读音都取出。
  41. $result[] = $objChinesePinYin::$chinesePinyin[$string];
  42. } else {
  43. $result[] = array($string);
  44. }
  45. }
  46. return $result;
  47. }
  48. /**
  49. * @desc 将字符串中汉字转换为完整拼音(不支持多音字),自定义转换连接符,默认为''
  50. * @param string $string
  51. * @param string $separator
  52. * @return string
  53. **/
  54. public static function convertPinyin($string, $separator = '') {
  55. $result = '';
  56. if (empty($string)) {
  57. return $result;
  58. }
  59. $stringList = self::splitString($string);
  60. $pinyinList = self::changePinyinList($stringList);
  61. $resultList = array();
  62. foreach ($pinyinList as $pinyin) {
  63. $resultList[] = $pinyin[0];
  64. }
  65. $result = implode($separator, $resultList);
  66. return $result;
  67. }
  68. /**
  69. * @desc 将字符串中汉字转换为完整拼音数组(支持所有多音字组合),自定义转换连接符,默认为''
  70. * @param string $string
  71. * @param string $separator
  72. * @return array
  73. **/
  74. public static function convertPinyinList($string, $separator = '') {
  75. $result = array();
  76. if (empty($string)) {
  77. return $result;
  78. }
  79. $stringList = self::splitString($string);
  80. $pinyinList = self::changePinyinList($stringList);
  81. // 弹出二维数组第一个元素作为起始数组。循环读取剩余数组元素。交叉笛卡儿积拼接生成所有多音字情况一维数组。
  82. // 将所有可能结果赋值给起始数组,进入下一轮循环。至循环结束。
  83. $prevPinyin = array_shift($pinyinList);
  84. foreach ($pinyinList as $pinyin) {
  85. $tmpPinyinList = array();
  86. foreach ($prevPinyin as $strPrevPinyin) {
  87. foreach ($pinyin as $strPinyin) {
  88. $tmpPinyinList[] = $strPrevPinyin . $separator . $strPinyin;
  89. }
  90. }
  91. $prevPinyin = $tmpPinyinList;
  92. }
  93. $result = array_unique($prevPinyin);
  94. return $result;
  95. }
  96. /**
  97. * @desc 将字符串中汉字转换为首字母拼音(不支持多音字),自定义转换连接符,默认为''
  98. * @param string $string
  99. * @param string $separator
  100. * @return string
  101. **/
  102. public static function convertInitalPinyin($string, $separator = '') {
  103. $result = '';
  104. if (empty($string)) {
  105. return $result;
  106. }
  107. $stringList = self::splitString($string);
  108. $pinyinList = self::changePinyinList($stringList);
  109. $resultList = array();
  110. foreach ($pinyinList as $pinyin) {
  111. if (ord($pinyin[0]) > 129) { // 非 a-z 字母
  112. $resultList[] = $pinyin[0];
  113. } else {
  114. $resultList[] = substr($pinyin[0], 0, 1);
  115. }
  116. }
  117. $result = implode($separator, $resultList);
  118. return $result;
  119. }
  120. /**
  121. * @desc 将字符串中汉字转换为首字母拼音数组(支持所有多音字组合),自定义转换连接符,默认为''
  122. * @param string $string
  123. * @param string $separator
  124. * @return array
  125. **/
  126. public static function convertInitalPinyinList($string, $separator = '') {
  127. $result = array();
  128. if (empty($string)) {
  129. return $result;
  130. }
  131. $stringList = self::splitString($string);
  132. $pinyinList = self::changePinyinList($stringList);
  133. // 弹出二维数组第一个元素作为起始数组。循环读取剩余数组元素。交叉笛卡儿积拼接生成所有多音字情况一维数组。
  134. // 将所有可能结果赋值给起始数组,进入下一轮循环。至循环结束。
  135. $prevPinyin = array_shift($pinyinList);
  136. // 处理起始数组,只有一个汉字和汉字开头的情况
  137. foreach ($prevPinyin as $key => $strPrevPinyin) {
  138. if (ord($strPinyin) > 129) { // 非 a-z 字母
  139. $prevPinyin[$key] = $strPrevPinyin;
  140. } else {
  141. $prevPinyin[$key] = substr($strPrevPinyin, 0, 1);
  142. }
  143. }
  144. foreach ($pinyinList as $pinyin) {
  145. $tmpPinyinList = array();
  146. foreach ($prevPinyin as $strPrevPinyin) {
  147. foreach ($pinyin as $strPinyin) {
  148. if (ord($strPinyin) > 129) { // 非 a-z 字母
  149. $tmpPinyinList[] = $strPrevPinyin . $separator . $strPinyin;
  150. } else {
  151. $tmpPinyinList[] = $strPrevPinyin . $separator . substr($strPinyin, 0, 1);
  152. }
  153. }
  154. }
  155. $prevPinyin = $tmpPinyinList;
  156. }
  157. $result = array_unique($prevPinyin);
  158. return $result;
  159. }
  160. /**
  161. * @desc 将字符串中汉字转换为完整拼音数组、首字母拼音数组(支持所有多音字组合),自定义转换连接符,默认为''
  162. * @param string $string
  163. * @param string $separator
  164. * @return array
  165. **/
  166. public static function convertAllPinyinList($string, $separator = '') {
  167. $result['full'] = self::convertPinyinList($string, $separator);
  168. $result['inital'] = self::convertInitalPinyinList($string, $separator);
  169. return $result;
  170. }
  171. }