UTF-8字符集在AJAX下中文乱码的解决办法

Question

转自http://bbs.lampbrother.net/read-htm-tid-2610.html

本以为全部UTF-8 就不用关心乱码问题了呢 , 结果乱码还是来了.. 查了点英文资料 , 搞定.

方法很简单 , 直接对提交的数据进行编码即可..

但是 UTF-8 的 和ASCII的不怎么一样.. 下面是修正办法

var str = document.frm.username.value
修改成
var str = encode(document.frm.username.value)

然后在 这个标记前面 把下面代码复制进去

1. var unreserved = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz-_.~";
2. var reserved = "!*'();:@&=+$,/?%#[]";
3. var allowed = unreserved + reserved;
4. var hexchars = "0123456789ABCDEFabcdef";
6. // --------------------------------- Encoding -------------------------------
8. // This function returns a percent sign followed by two hexadecimal digits.
9. // Input is a decimal value not greater than 255.
10. function gethex(decimal) {
11. return "%" + hexchars.charAt(decimal >> 4) + hexchars.charAt(decimal & 0xF);
12. }
15. function encode(str) {
16. // Clear output field:
18. // Some variables:
19. var decoded = str;
20. var encoded = "";
23. for (var i = 0; i < decoded.length; i++ ) {
24. var ch = decoded.charAt(i);
25. // Check if character is an unreserved character:
26. if (unreserved.indexOf(ch) != -1) {
27. encoded = encoded + ch;
28. } else {
30. // The position in the Unicode table tells us how many bytes are needed.
31. // Note that if we talk about first, second, etc. in the following, we are
32. // counting from left to right:
33. //
34. // Position in | Bytes needed | Binary representation
35. // Unicode table | for UTF-8 | of UTF-8
36. // ----------------------------------------------------------
37. // 0 - 127 | 1 byte | 0XXX.XXXX
38. // 128 - 2047 | 2 bytes | 110X.XXXX 10XX.XXXX
39. // 2048 - 65535 | 3 bytes | 1110.XXXX 10XX.XXXX 10XX.XXXX
40. // 65536 - 2097151 | 4 bytes | 1111.0XXX 10XX.XXXX 10XX.XXXX 10XX.XXXX
42. var charcode = decoded.charCodeAt(i);
44. // Position 0 - 127 is equal to percent-encoding with an ASCII character encoding:
45. if (charcode < 128) {
46. encoded = encoded + gethex(charcode);
47. }
49. // Position 128 - 2047: two bytes for UTF-8 character encoding.
50. if (charcode > 127 && charcode < 2048) {
51. // First UTF byte: Mask the first five bits of charcode with binary 110X.XXXX:
52. encoded = encoded + gethex((charcode >> 6) | 0xC0);
53. // Second UTF byte: Get last six bits of charcode and mask them with binary 10XX.XXXX:
54. encoded = encoded + gethex((charcode & 0x3F) | 0x80);
55. }
57. // Position 2048 - 65535: three bytes for UTF-8 character encoding.
58. if (charcode > 2047 && charcode < 65536) {
59. // First UTF byte: Mask the first four bits of charcode with binary 1110.XXXX:
60. encoded = encoded + gethex((charcode >> 12) | 0xE0);
61. // Second UTF byte: Get the next six bits of charcode and mask them binary 10XX.XXXX:
62. encoded = encoded + gethex(((charcode >> 6) & 0x3F) | 0x80);
63. // Third UTF byte: Get the last six bits of charcode and mask them binary 10XX.XXXX:
64. encoded = encoded + gethex((charcode & 0x3F) | 0x80);
65. }
67. // Position 65536 - : four bytes for UTF-8 character encoding.
68. if (charcode > 65535) {
69. // First UTF byte: Mask the first three bits of charcode with binary 1111.0XXX:
70. encoded = encoded + gethex((charcode >> 18) | 0xF0);
71. // Second UTF byte: Get the next six bits of charcode and mask them binary 10XX.XXXX:
72. encoded = encoded + gethex(((charcode >> 12) & 0x3F) | 0x80);
73. // Third UTF byte: Get the last six bits of charcode and mask them binary 10XX.XXXX:
74. encoded = encoded + gethex(((charcode >> 6) & 0x3F) | 0x80);
75. // Fourth UTF byte: Get the last six bits of charcode and mask them binary 10XX.XXXX:
76. encoded = encoded + gethex((charcode & 0x3F) | 0x80);
77. }
79. }
81. } // end of for ...
83. // Write result:
84. return encoded;
85. }

复制代码ok，大功告成！