XML文件处理过程中的0x1A 错误处理

XML文件处理过程中的0x1A 错误处理

package testjavaBasic;

import java.io.ByteArrayInputStream;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;

import org.w3c.dom.Document;
import org.w3c.dom.Element;

/**
 * @author zhangdi
 *
 */
public class TestXMlTransferException_0x1a {
    public static void main(String[] args) {

        String text_UAT="..."; //见test_xml

        //System.out.println(CleanInvalidXmlChars_2());
        //String cleanInvalidXmlChars = CleanInvalidXmlChars(text);
        String[] cleanInvalidXmlChars = (String[])CleanInvalidXmlChars(text_UAT);
        for (String string : cleanInvalidXmlChars) {
            System.out.println(string);
        }
    }

    /**
     * 实例1
     * @param text
     * @return
     */
    public static <T> T CleanInvalidXmlChars(String text) {
        //0-注释
        // From xml spec valid chars:
        // #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
        // any Unicode character, excluding the surrogate blocks, FFFE, and FFFF.
        // [^//x09//x0A//x0D//x20-//xD7EF//xE000-//xFFFD//x10000-//x10FFFF]
        /*Pattern pt = Pattern.compile("[^//x09//x0A//x0D//x20-//xD7EF//xE000-//xFFFD//x10000-x10FFFF]");
        Matcher mat = pt.matcher(text);
        return mat.replaceAll("");*/

        //1-注释
        //String filter = text.replaceAll("[\x00-\x08\x0b-\x0c\x0e-\x1f]", "");
        String[] split = text.split("[\x00-\x08\x0b-\x0c\x0e-\x1f]");
        return (T) split;  

        }

    /**
     * @return 实例2
     */
    public static String  CleanInvalidXmlChars_2(){
         // 测试的字符串应该为：<r><c d="s" n="j"></c></r>  
        // 正常的对应的byte数组为  
        byte[] ba1 = new byte[] { 60, 114, 62, 60, 99, 32, 100, 61, 34, 115,  
                34, 32, 110, 61, 34, 106, 34, 62, 60, 47, 99, 62, 60, 47, 114,  
                62 };  
        System.out.println("ba1     length=" + ba1.length);  
        String ba1str = new String(ba1);  
        System.out.println(ba1str);  
        System.out.println("ba1str  length=" + ba1str.length());  
        System.out.println("-----------------------------------------");  
        // 和正常的byte 数组相比 多了一个不可见的 31  
        byte[] ba2 = new byte[] { 60, 114, 62, 60, 99, 32, 100, 61, 34, 115,  
                34, 32, 110, 61, 34, 106, 31, 34, 62, 60, 47, 99, 62, 60, 47,  
                114, 62 };  
        System.out.println("ba2     length=" + ba2.length);  
        String ba2str = new String(ba2);  
        System.out.println(ba2str);  
        System.out.println("ba2str  length=" + ba2str.length());  
        System.out.println("-----------------------------------------");  
        try {  
            DocumentBuilderFactory dbfactory = DocumentBuilderFactory  
                    .newInstance();  
            dbfactory.setIgnoringComments(true);  
            DocumentBuilder docBuilder = dbfactory.newDocumentBuilder();  

            // 过滤掉非法不可见字符 如果不过滤 XML解析就报异常  
            String filter = ba2str.replaceAll(  
                    "[\x00-\x08\x0b-\x0c\x0e-\x1f]", "");  
            System.out.println("过滤后的length=" + filter.length());  
            ByteArrayInputStream bais = new ByteArrayInputStream(filter  
                    .getBytes());  
            Document doc = docBuilder.parse(bais);  
            Element rootEl = doc.getDocumentElement();  
            System.out.println("过滤后解析正常 root child length="  
                    + rootEl.getChildNodes().getLength());  
        } catch (Exception e) {  
            e.printStackTrace();  
        }
        return ba2str;  
    }  
}