[PHP]-extract strings by length (for UTF-8)

CodeIs to look at the specifications, copy and modify, hope it is perfect...

 

 /*  **************************************** * ***************************** Func Name: substrex ** Description: * truncated string by length *** parameters: * $ sstring [String]: string * $ nlength [int]: length * $ sdot [String = "... "]: truncation character * $ scharset [String =" UTF-8 "]: encoding ** returns: [bool] Save the result *********************************** **********************************  */  Function Substrex ( $ Sstring , $ Nlength , $ Sdot = "...",$ Scharset = "UTF-8" ){  If ( Strlen ( $ Sstring ) <= $ Nlength  ){  Return   $ Sstring  ;}  $ Sstring = Str_replace ( Array ("&", "\" "," <","> "), Array ("&", "\" "," <","> "), $ Sstring  );  $ Sstrcut = "" ;  If ( Strtoupper ( $ Scharset ) = "UTF-8" ){  $ NPOs = 0 ;  $ Nwordlen = 0 ;  $ NOC = 0; // Single-byte characters + 1, multi-byte + 2 (the length of non-single-byte characters is regarded as 2 [should be visual])          While ( $ NPOs < Strlen ( $ Sstring  )){  $ T = ORD ( $ Sstring [ $ NPOs  ]);  If ( $ T = 9 | $ T = 10 | (32 <= $ T && $ T <= 126 )){  $ Nwordlen = 1 ;  $ NOC ++ ;}  Elseif (194 <= $ T && $ T <= 223 ){  $ Nwordlen = 2;  $ NOC + = 2 ;}  Elseif (224 <= $ T && $ T <= 239 ){  $ Nwordlen = 3 ;  $ NOC + = 2 ;}  Elseif (240 <= $ T &&$ T <= 247 ){  $ Nwordlen = 4 ;  $ NOC + = 2 ;}  Elseif (248 <= $ T && $ T <= 251 ){  $ Nwordlen = 5 ;  $ NOC + = 2;}  Elseif ( $ T = 252 | $ T = 253 ){  $ Nwordlen = 6 ;  $ NOC + = 2 ;}  Else  {  $ Nwordlen = 0 ;}  $ NPOs + = ( $ Nwordlen > 0 )? $ Nwordlen : 1 ;  If ( $ NOC > = $ Nlength  ){  Break  ;}}  If ( $ NOC > $ Nlength  ){  $ NPOs -= $ Nwordlen  ;}  $ Sstrcut = Substr ( $ Sstring , 0, $ NPOs  );}  Else  {  For ( $ I = 0; $ I < $ Nlength ; $ I ++){  $ Sstrcut . = ORD ( $ Sstring [ $ I ])> 127? $ Sstring [ $ I ]. $ Sstring [++ $ I ]: $ Sstring [ $ I  ] ;}}  $ Sstrcut =Str_replace ( Array ("&", "\" "," <","> "), Array ("&", "\" "," <","> "), $ Sstrcut  );  Return   $ Sstrcut . $ Sdot  ;}