Php Chinese support function php Chinese intercept string function PHP Chinese character string flip

Php Chinese support function php Chinese intercept string function PHP Chinese character string flip

/** * Convert a string containing full-width numeric characters, letters, spaces, or '% +-()' to the corresponding half-width characters. * * @ Access public * @ Param string $ str string to be converted * * @ Return string $ str string after processing */ Function make_semiangle ($ str) { $ Arr = array ('0' => '0', '1' => '1', '2' => '2 ', '3' => '3', '4' => '4 ', '5' => '5', '6' => '6', '7' => '7', '8' => '8 ', '9' => '9 ', 'A' => 'A', 'B' => 'B', 'c' => 'C', 'D' => 'D ', 'E' => 'e ', 'F' => 'F', 'G' => 'G', 'H' => 'h', 'I' => 'I ', 'j' => 'J ', 'K' => 'K', 'L' => 'L', 'M' => 'm', 'n' => 'N ', 'o' => 'O ', 'P' => 'P', 'q' => 'Q', 'R' => 'R', 's' =>'s ', 'T' => 'T ', 'U' => 'u', 'V' => 'V', 'W' => 'W', 'x' => 'X ', 'y' => 'y ', 'Z' => 'Z', 'a' => 'A', 'B' => 'B', 'c' => 'C ', 'D' => 'D ', 'E' => 'e', 'F' => 'F', 'G' => 'G', 'H' => 'h ', 'I' => 'I ', 'J' => 'J', 'K' => 'K', 'L' => 'L', 'M' =>'m ', 'n' => 'N ', 'O' => 'O', 'P' => 'P', 'q' => 'Q', 'R' => 'R ','s '=>'s ', 'T' => 'T', 'u' => 'u', 'V' => 'V', 'W' => 'W ', 'X' => 'X ', 'Y' => 'y', 'Z' => 'Z ', '(' => '(', ')' => ')', '[' => '[', ']' => ']', '[' => '[', ']' => ']', '<' => '[', '<' => ']', '=> '[', '"' => ']', ''' => '[', ''' => ']', '{' => '{', '}' => '}', '=>' <', '"' => ', '%' => '%', '+' => '+', '-' => '-', '-' => '-','~ '=> '-', ':' => ':','. '=>'. ',', '=>', '=>'. ',', '=> '.', ';' => ',','? '=> '? ','! '=> '! ','... '=>'-', ''' =>' | ', '"' => '"', ''' => ''', ''' => ''', '|' => '| ', 'Region' => '"', ''=>'', '$' => '$', '@' => '@', '#' => '#', '^' => '^', '&' => '&', '*' => '*'); Return strtr ($ str, $ arr ); } Example 2: php Chinese truncation string /* Chinese character truncation functions supported by Utf-8 and gb2312 Cut_str (string, truncation length, start length, encoding ); The default encoding format is UTF-8. The default start length is 0. * Edit: bbs.it-home.org */ Function cut_str ($ string, $ sublen, $ start = 0, $ code = 'utf-8 '){ If ($ code = 'utf-8 '){ $ Pa = "/[\ x01-\ x7f] | [\ xc2-\ xdf] [\ x80-\ xbf] | \ xe0 [\ xa0-\ xbf] [\ x80 -\ xbf] | [\ xe1-\ xef] [\ x80-\ xbf] [\ x80-\ xbf] | \ xf0 [\ x90-\ xbf] [\ x80- \ xbf] [\ x80-\ xbf] | [\ xf1-\ xf7] [\ x80-\ xbf] [\ x80-\ xbf] [\ x80-\ xbf]/ "; Preg_match_all ($ pa, $ string, $ t_string ); If (count ($ t_string [0])-$ start> $ sublen) Return join ('', array_slice ($ t_string [0], $ start, $ sublen ))."..."; Return join ('', array_slice ($ t_string [0], $ start, $ sublen )); } Else { $ Start = $ start * 2; $ Sublen = $ sublen * 2; $ Strlen = strlen ($ string ); $ Tmpstr = ''; For ($ I = 0; $ I <$ strlen; $ I ++ ){ If ($ I >=$ start & $ I <($ start + $ sublen )){ If (ord (substr ($ string, $ I, 1) & gt; 129 ){ $ Tmpstr. = substr ($ string, $ I, 2 ); } Else { $ Tmpstr. = substr ($ string, $ I, 1 ); } } If (ord (substr ($ string, $ I, 1)> 129) $ I ++; } If (strlen ($ tmpstr) <$ strlen) $ Tmpstr. = "..."; Return $ tmpstr; } } $ Str = "the string to be intercepted by abcd "; Echo cut_str ($ str, 1, 0, 'gb2312 '); ?> Example 3: string loading /** * UTF-8/GBK character truncation is supported. * @ Param $ string * @ Param $ length * @ Param $ dot */ Function str_cut ($ string, $ length, $ charset = 'utf-8', $ dot = '...'){ $ Strlen = strlen ($ string ); If ($ strlen <= $ length) return $ string; $ String = str_replace (array ('','', '&', '"', ''', '-', '<', '> ','·','... '), Array ('region', '',' & ','" ', "'", ''', ','-',' <', '> ','·','... '), $ String ); $ Strcut = ''; If (strtolower ($ charset) = 'utf-8 '){ $ Length = intval ($ length-strlen ($ dot)-$ length/3 ); $ N = $ tn = $ noc = 0; While ($ n <strlen ($ string )){ $ T = ord ($ string [$ n]); If ($ t = 9 | $ t = 10 | (32 <= $ t & $ t <= 126 )){ $ Tn = 1; $ n ++; $ noc ++; } Elseif (194 <=$ t & $ t <= 223 ){ $ Tn = 2; $ n + = 2; $ noc + = 2; } Elseif (224 <=$ t & $ t <= 239 ){ $ Tn = 3; $ n + = 3; $ noc + = 2; } Elseif (240 <=$ t & $ t <= 247 ){ $ Tn = 4; $ n + = 4; $ noc + = 2; } Elseif (248 <=$ t & $ t <= 251 ){ $ Tn = 5; $ n + = 5; $ noc + = 2; } Elseif ($ t = 252 | $ t = 253 ){ $ Tn = 6; $ n + = 6; $ noc + = 2; } Else { $ N ++; } If ($ noc >=$ length ){ Break; } } If ($ noc> $ length ){ $ N-= $ tn; } $ Strcut = substr ($ string, 0, $ n ); $ Strcut = str_replace (array ('hour', '&', '"'," '",'-',' <', '> ','·','... '), Array ('',' & ','" ', ''','-',' <','> ', '·','... '), $ Strcut ); } Else { $ Dotlen = strlen ($ dot ); $ Maxi = $ length-$ dotlen-1; $ Current_str = ''; $ Search_arr = array ('&', '', '"', "'",'-',' <','> ', '·','... ', 'Signature '); $ Replace_arr = array ('&', '', '"', ''', '-', '<', '> ', '·','... ',''); $ Search_flip = array_flip ($ search_arr ); For ($ I = 0; $ I <$ maxi; $ I ++ ){ $ Current_str = ord ($ string [$ I])> 127? $ String [$ I]. $ string [++ $ I]: $ string [$ I]; If (in_array ($ current_str, $ search_arr )){ $ Key = $ search_flip [$ current_str]; $ Current_str = str_replace ($ search_arr [$ key], $ replace_arr [$ key], $ current_str ); } $ Strcut. = $ current_str; } } Return $ strcut. $ dot; } Example 4: Use the strrev () function to flip a character string in PHP. However, sometimes it is necessary to handle strings that contain Chinese characters, so that garbled characters will occur when strrev is used. Here, we define a function to process Chinese characters. /** * Chinese string flip * By bbs.it-home.org */ Function cstrrev ($ str) { $ Len = strlen ($ str ); For ($ I = 0; $ I <$ len; $ I ++) { $ Char = $ str {0 }; 'If (ord ($ char)> 127) { $ I ++; If ($ I <$ len) { $ Arr [] = substr ($ str, 0, 2 ); $ Str = substr ($ str, 2 ); } } Else { $ Arr [] = $ char; $ Str = substr ($ str, 1 ); } } Return join (array_reverse ($ arr )); } # Usage: $ Str = 'Chinese. look! '; Echo cstrrev ($ str ); # Result output :! Kool. Appendix 5, Function str_replace_cn ($ needle, $ str, $ haystack, $ charset = "UTF-8 "){ $ Re ['utf-8'] = "/[\ x01-\ x7f] | [\ xc2-\ xdf] [\ x80-\ xbf] | [\ xe0 -\ xef] [\ x80-\ xbf] {2} | [\ xf0-\ xff] [\ x80-\ xbf] {3 }/"; $ Re ['gb2312'] = "/[\ x01-\ x7f] | [\ xb0-\ xf7] [\ xa0-\ xfe]/"; $ Re ['gbk'] = "/[\ x01-\ x7f] | [\ x81-\ xfe] [\ x40-\ xfe]/"; $ Re ['big5'] = "/[\ x01-\ x7f] | [\ x81-\ xfe] ([\ x40-\ x7e] | \ xa1-\ xfe]) /"; Preg_match_all ($ re [$ charset], $ haystack, $ match_haystack ); Preg_match_all ($ re [$ charset], $ needle, $ match_needle ); For ($ I = 0; $ I <count ($ match_needle); $ I ++ ){ If (! In_array ($ match_needle [0] [$ I], $ match_haystack [0]) return $ haystack; // no matching } $ Match_haystack = $ match_haystack [0]; $ Match_needle = $ match_needle [0]; For ($ I = 0; $ I <count ($ match_haystack); $ I ++ ){ If ($ match_haystack [$ I] = "") continue; If ($ match_haystack [$ I] = $ match_needle [0]) { If (count ($ match_needle) = 1) {// if only one character $ Match_haystack [$ I] = $ str; } Else { $ Flag = true; For ($ j = 1; $ j <count ($ match_needle); $ j ++ ){ If ($ match_haystack [$ I + $ j]! = $ Match_needle [$ j]) { $ Flag = false; Break; } } If ($ flag) {// Match $ Match_haystack [$ I] = $ str; For ($ j = 1; $ j <count ($ match_needle); $ j ++ ){ $ Match_haystack [$ I + $ j] = ""; } } } } } Return implode ("", $ match_haystack ); }