一、编码范围

1.gbk (gb2312/gb18030)

x00-xff gbk双字节编码范围

x20-x7f ascii

xa1-xff 中文

x80-xff 中文

2.utf-8 (unicode)

u4e00-u9fa5 (中文)

x3130-x318f (韩文)

xac00-xd7a3 (韩文)

u0800-u4e00 (日文)

ps: 韩文是大于[u9fa5]的字符

正则例子:

preg_replace("/([x80-xff])/","",$str);

preg_replace("/([u4e00-u9fa5])/","",$str);

二、代码例子

1. //判断内容里有没有中文-gbk (php教程)
2. function check_is_chinese($s){
3. return preg_match('/[x80-xff]./', $s);
4. }
5. //获取字符串长度-gbk (php)
6. function gb_strlen($str){
7. $count = 0;
8. for($i=0; $i<strlen($str); $i++){
9. $s = substr($str, $i, 1);
10. if (preg_match("/[x80-xff]/", $s)) ++$i;
11. ++$count;
12. }
13. return $count;
14. }
15. //截取字符串字串-gbk (php)
16. function gb_substr($str, $len){
17. $count = 0;
18. for($i=0; $i<strlen($str); $i++){
19. if($count == $len) break;
20. if(preg_match("/[x80-xff]/", substr($str, $i, 1))) ++$i;
21. ++$count;
22. }
23. return substr($str, 0, $i);
24. }
25. //统计字符串长度-utf8 (php)
26. function utf8_strlen($str) {
27. $count = 0;
28. for($i = 0; $i < strlen($str); $i++){
29. $value = ord($str[$i]);
30. if($value > 127) {
31. $count++;
32. if($value >= 192 && $value <= 223) $i++;
33. elseif($value >= 224 && $value <= 239) $i = $i + 2;
34. elseif($value >= 240 && $value <= 247) $i = $i + 3;
35. else die('not a utf-8 compatible string');
36. }
37. $count++;
38. }
39. return $count;
40. }
41. //截取字符串-utf8(php)
42. function utf8_substr($str,$position,$length){
43. $start_position = strlen($str);
44. $start_byte = 0;
45. $end_position = strlen($str);
46. $count = 0;
47. for($i = 0; $i < strlen($str); $i++){
48. if($count >= $position && $start_position > $i){
49. $start_position = $i;
50. $start_byte = $count;
51. }
52. if(($count-$start_byte)>=$length) {
53. $end_position = $i;
54. break;
55. }
56. $value = ord($str[$i]);
57. if($value > 127){
58. $count++;
59. if($value >= 192 && $value <= 223) $i++;
60. elseif($value >= 224 && $value <= 239) $i = $i + 2;
61. elseif($value >= 240 && $value <= 247) $i = $i + 3;
62. else die('not a utf-8 compatible string');
63. }
64. $count++;
65. }
66. return(substr($str,$start_position,$end_position-$start_position));
67. }
68. //字符串长度统计-utf8 [中文3个字节，俄文、韩文占2个字节，字母占1个字节] (ruby)
69. def utf8_string_length(str)
70. temp = cgi::unescape(str)
71. i = 0;
72. j = 0;
73. temp.length.times{|t|
74. if temp[t] < 127
75. i += 1
76. elseif temp[t] >= 127 and temp[t] < 224
77. j += 1
78. if 0 == (j % 2)
79. i += 2
80. j = 0
81. end
82. else
83. j += 1
84. if 0 == (j % 3)
85. i +=2
86. j = 0
87. end
88. end
89. }
90. return i
91. }
92. //判断是否是含有韩文-utf-8 (网页特效)
93. function checkkoreachar(str) {
94. for(i=0; i<str.length; i++) {
95. if(((str.charcodeat(i) > 0x3130 && str.charcodeat(i) < 0x318f) || (str.charcodeat(i) >= 0xac00 && str.charcodeat(i) <= 0xd7a3))) {
96. return true;
97. }
98. }
99. return false;
100. }//开源代码phpfensi.com
101. //判断是否有中文字符-gbk (javascript)
102. function check_chinese_char(s){
103. return (s.length != s.replace(/[^x00-xff]/g,"**").length);
104. }