2005年11月3日

?????? 眾所周知，XML的快速發展，已經越來越多地出現在數據交互、文件配置和格式化的數據載體中，盡管XML支持的語言越來越多，但是還是有些字符是不被支持的。我在工作中就遇到了這樣的問題，通過.csv文件錄入數據，然后通過在程序中轉化為XML中間文件，再將XML文件錄入進行處理時發生異常，經過分析，是由于.csv文件中含有XML不支持的非法字符。

?????? 查詢XML規范(http://www.w3.org/TR/2004/REC-xml-20040204)，得知：XML支持的字符范圍：

Character Range

?

?

從字符串中檢測XML不支持的字符的Java代碼：

??1public?static?int?checkCharacterData(String?text){
??2
??3????????int?errorChar=0;
??4
??5????????if?(text?==?null)?{
??6
??7????????????return?errorChar;
??8
??9????????}
?10
?11????????//?do?check
?12
?13????????char[]?data?=?text.toCharArray();
?14
?15????????for?(int?i?=?0,?len?=?data.length;?i?<?len;?i++)?{
?16
?17????????????char?c?=?data[i];
?18
?19????????????int?result?=?c;
?20
?21????????????//?high?surrogate
?22
?23????????????if?(result?>=?0xD800?&&?result?<=?0xDBFF)?{
?24
?25????????????????//?Decode?surrogate?pair
?26
?27???????????????int?high?=?c;
?28
?29???????????????try?{
?30
?31?????????????????int?low?=?text.charAt(i+1);
?32
?33?????????????????if?(low?<?0xDC00?||?low?>?0xDFFF)?{
?34
?35????????????????????char?ch=(char)low;
?36
?37????????????????????//System.err.println(ch);
?38
?39?????????????????}
?40
?41?????????????????//?Algorithm?defined?in?Unicode?spec
?42
?43?????????????????result?=?(high-0xD800)*0x400?+?(low-0xDC00)?+?0x10000;
?44
?45?????????????????i++;
?46
?47???????????????}
?48
?49???????????????catch?(IndexOutOfBoundsException?e)?{
?50
?51???????????????????e.printStackTrace();
?52
?53???????????????}
?54
?55????????????}
?56
?57?
?58
?59????????????if?(!isXMLCharacter(result))?{
?60
?61????????????????//?Likely?this?character?can't?be?easily?displayed
?62
?63????????????????//?because?it's?a?control?so?we?use?its?hexadecimal
?64
?65????????????????//?representation?in?the?reason.
?66
?67????????????????errorChar++;
?68
?69????????????}??????
?70
?71????????}
?72
?73????????//?If?we?got?here,?everything?is?OK
?74
?75????????return?errorChar;
?76
?77????}
?78
?79?
?80
?81????
?82
?83????private?static?boolean?isXMLCharacter(int?c)?{
?84
?85?????????if?(c?<=?0xD7FF)??{
?86
?87?????????????if?(c?>=?0x20)?return?true;
?88
?89?????????????else?{
?90
?91??????????????????if?(c?==?'\n')?return?true;
?92
?93??????????????????if?(c?==?'\r')?return?true;
?94
?95??????????????????if?(c?==?'\t')?return?true;
?96
?97??????????????????return?false;
?98
?99?????????????}
100
101?????????}
102
103?
104
105?????????if?(c?<?0xE000)?return?false;??if?(c?<=?0xFFFD)?return?true;
106
107?????????if?(c?<?0x10000)?return?false;??if?(c?<=?0x10FFFF)?return?true;
108
109???????
110
111?????????return?false;
112
113????}
114