Two examples of getting the first letter of a Chinese character in php

Example 1

The main functions are: clear functions, easy to modify, maintain, and expand; English strings: unchanged return (including numbers); Chinese Strings: return the first character of pinyin; Chinese-English string: returns the first and English characters of pinyin. This algorithm uses a binary search method to fix the error of reading the letter Z to Y. Good things need to be added to favorites, so we leave a mark here for future generations to study!

The code is as follows:

Copy code

<? Php /** * Solution * Tool for the first letter of Chinese character and Pinyin * Note: The English string does not change and returns (including numbers) eg. abc123 => abc123 * Chinese character string: return the first character of pinyin. For example, test string => CSZFC * Chinese-English mixed string: return the first character of the Chinese alphabet and the English eg. I j => WIWJ * Eg. * $ Py = new str2PY (); * $ Result = $ py-> getInitials ('Ah, it's just like Ele. Me, I saw it. You know, it's just him uv, I want to be '); */ Class str2PY { Private $ _ pinyins = array ( 176161 => 'A ', 176197 => 'B ', 178193 => 'C ', 180238 => 'D ', 182234 => 'e ', 183162 => 'F ', 184193 => 'G ', 185254 => 'h ', 187247 => 'J ', 191166 => 'K ', 192172 => 'L ', 194232 =>'m ', 196195 => 'N ', 197182 => 'O ', 197190 => 'P ', 198218 => 'Q ', 200187 => 'R ', 200246 =>'s ', 203250 => 'T ', 205218 => 'W ', 206244 => 'X ', 209185 => 'y ', 212209 => 'Z ', ); Private $ _ charset = null; /** * Constructor, specifying the required encoding default: UTF-8 * UTF-8 and gb2312 supported      * * @ Param unknown_type $ charset */ Public function _ construct ($ charset = 'utf-8 ')     { $ This-> _ charset = $ charset;     } /** * Chinese character string substr      * * @ Param string $ str * @ Param int $ start * @ Param int $ len * @ Return string */ Private function _ msubstr ($ str, $ start, $ len)     { $ Start = $ start * 2; $ Len = $ len * 2; $ Strlen = strlen ($ str ); $ Result = ''; For ($ I = 0; $ I <$ strlen; $ I ++ ){ If ($ I >=$ start & $ I <($ start + $ len )){ If (ord (substr ($ str, $ I, 1)> 129) $ result. = substr ($ str, $ I, 2 ); Else $ result. = substr ($ str, $ I, 1 );             } If (ord (substr ($ str, $ I, 1)> 129) $ I ++;         } Return $ result;     } /** * The string is partitioned into arrays (Chinese characters or characters in units)      * * @ Param string $ str * @ Return array */ Private function _ cutWord ($ str)     { $ Words = array (); While ($ str! = "")          { If ($ this-> _ isAscii ($ str) {/* non-Chinese */ $ Words [] = $ str [0]; $ Str = substr ($ str, strlen ($ str [0]); } Else { $ Word = $ this-> _ msubstr ($ str, 0, 1 ); $ Words [] = $ word; $ Str = substr ($ str, strlen ($ word ));             }          } Return $ words;     } /** * Determines whether the character is an ascii character.      * * @ Param string $ char * @ Return bool */ Private function _ isAscii ($ char)     { Return (ord (substr ($ char, 160) <);     } /** * Determines whether the first three characters of a string are ascii characters.      * * @ Param string $ str * @ Return bool */ Private function _ isAsciis ($ str)     { $ Len = strlen ($ str)> = 3? 3: 2; $ Chars = array (); For ($ I = 1; $ I <$ len-1; $ I ++ ){ $ Chars [] = $ this-> _ isAscii ($ str [$ I])? 'Yes': 'no ';         } $ Result = array_count_values ($ chars ); If (empty ($ result ['no']) { Return true;         } Return false;     } /** * Obtain the first character of a Chinese string in Chinese.      * * @ Param string $ str * @ Return string */ Public function getInitials ($ str)     { If (empty ($ str) return ''; If ($ this-> _ isAscii ($ str [0]) & $ this-> _ isAsciis ($ str )){ Return $ str;         } $ Result = array (); If ($ this-> _ charset = 'utf-8 '){ $ Str = iconv ('utf-8', 'gb2312', $ str );         } $ Words = $ this-> _ cutWord ($ str ); Foreach ($ words as $ word)         { If ($ this-> _ isAscii ($ word) {/* non-Chinese */ $ Result [] = $ word; Continue;             } $ Code = ord (substr ($ word, 0, 1) * 1000 + ord (substr ($ word, 1, 1 )); /* Get the A--Z of the first letter of pinyin */ If ($ I = $ this-> _ search ($ code ))! =-1 ){ $ Result [] = $ this-> _ pinyins [$ I];             }         } Return strtoupper (implode ('', $ result ));     } Private function _ getChar ($ ascii)     { If ($ ascii >=48 & $ ascii <= 57 ){ Return chr ($ ascii);/* number */ } Elseif ($ ascii >=65 & $ ascii <= 90 ){ Return chr ($ ascii);/X A--Z */ } Elseif ($ ascii >=97 & $ ascii <= 122 ){ Return chr ($ ascii-32);/* a -- z */ } Else { Return '-';/* other */         }     } /** * Search for the expected Chinese character inner code (gb2312) corresponding to the Pinyin character (bipartite)      * * @ Param int $ code * @ Return int */ Private function _ search ($ code)     { $ Data = array_keys ($ this-> _ pinyins ); $ Lower = 0; $ Upper = sizeof ($ data)-1; $ Middle = (int) round ($ lower + $ upper)/2 ); If ($ code <$ data [0]) return-1; For (;;){ If ($ lower> $ upper ){ Return $ data [$ lower-1];             } $ Tmp = (int) round ($ lower + $ upper)/2 ); If (! Isset ($ data [$ tmp]) { Return $ data [$ middle]; } Else { $ Middle = $ tmp;    } If ($ data [$ middle] <$ code ){ $ Lower = (int) $ middle + 1; } Else if ($ data [$ middle] = $ code ){ Return $ data [$ middle]; } Else { $ Upper = (int) $ middle-1;             }         }     } } ?>

Example 2

Take the asc range of the Chinese character and return the first letter of the Chinese character.

 

The code is as follows:

Copy code

<Meta http-equiv = "Content-Type" content = "text/html; charset = UTF-8"/> <? Php Function getfirstchar ($ s0 ){ $ Fchar = ord ($ s0 {0 }); If ($ fchar> = ord ("A") and $ fchar <= ord ("z") return strtoupper ($ s0 {0 }); $ S1 = iconv ("UTF-8", "gb2312", $ s0 ); $ S2 = iconv ("gb2312", "UTF-8", $ s1 ); If ($ s2 = $ s0) {$ s = $ s1;} else {$ s = $ s0 ;} $ Asc = ord ($ s {0}) * 256 + ord ($ s {1})-65536; If ($ asc >=- 20319 and $ asc <=-20284) return ""; If ($ asc >=- 20283 and $ asc <=-19776) return "B "; If ($ asc >=- 19775 and $ asc <=-19219) return "C "; If ($ asc >=- 19218 and $ asc <=-18711) return "D "; If ($ asc >=- 18710 and $ asc <=-18527) return "E "; If ($ asc >=- 18526 and $ asc <=-18240) return "F "; If ($ asc >=- 18239 and $ asc <=-17923) return "G "; If ($ asc >=- 17922 and $ asc <=-17418) return "I "; If ($ asc >=- 17417 and $ asc <=-16475) return "J "; If ($ asc >=- 16474 and $ asc <=-16213) return "K "; If ($ asc >=- 16212 and $ asc <=-15641) return "L "; If ($ asc >=- 15640 and $ asc <=-15166) return "M "; If ($ asc >=- 15165 and $ asc <=-14923) return "N "; If ($ asc >=- 14922 and $ asc <=-14915) return "O "; If ($ asc >=- 14914 and $ asc <=- 14631) return "P "; If ($ asc >=- 14630 and $ asc <=-14150) return "Q "; If ($ asc >=- 14149 and $ asc <=-14091) return "R "; If ($ asc >=- 14090 and $ asc <=-13319) return "S "; If ($ asc >=- 13318 and $ asc <=-12839) return "T "; If ($ asc >=- 12838 and $ asc <=-12557) return "W "; If ($ asc >=- 12556 and $ asc <=-11848) return "X "; If ($ asc >=- 11847 and $ asc <=-11056) return "Y "; If ($ asc >=- 11055 and $ asc <=- 10247) return "Z "; Return null; }     Function pinyin1 ($ zh ){ $ Ret = ""; $ S1 = iconv ("UTF-8", "gb2312", $ zh ); $ S2 = iconv ("gb2312", "UTF-8", $ s1 ); If ($ s2 = $ zh) {$ zh = $ s1 ;} For ($ I = 0; $ I <strlen ($ zh); $ I ++ ){ $ S1 = substr ($ zh, $ I, 1 ); $ P = ord ($ s1 ); If ($ p & gt; 160 ){ $ S2 = substr ($ zh, $ I ++, 2 ); $ Ret. = getfirstchar ($ s2 ); } Else { $ Ret. = $ s1;         }     } Return $ ret; } Echo "this is a Chinese string <br/> "; Echo pinyin1 ('This is a Chinese string ');   ?>