java 字符串标签_java截取带html标签的字符串并把标签补全(保证款式).

public static String subStringHTML(String param,int

length,String end) {

StringBuffer result = new StringBuffer();

int n = 0;

char temp;

boolean isCode = false; //是不是HTML代码

boolean isHTML = false; //是不是HTML特异字符,如 

for (int i = 0; i < param.length(); i++) {

temp = param.charAt(i);

if (temp == '

isCode = true;

}

else if (temp == '&') {

isHTML = true;

}

else if (temp == '>'

&& isCode) {

n = n - 1;

isCode = false;

}

else if (temp == ';' && isHTML)

{

isHTML = false;

}

if (!isCode && !isHTML) {

n = n + 1;

//UNICODE码字符占两个字节

if ( (temp + "").getBytes().length > 1) {

n = n + 1;

}

}

result.append(temp);

if (n >= length) {

break;

}

}

result.append(end);

//取出截取字符串中的HTML符号

String temp_result =

result.toString().replaceAll("(>)[^<>]*()",

"$1$2");

//去掉无须要结素符号的HTML符号

temp_result =

temp_result.replaceAll("?(AREA|BASE|BASEFONT|BODY|BR|COL|COLGROUP|DD|DT|FRAME|HEAD|HR|HTML|IMG|INPUT|ISINDEX|LI|LINK|META|OPTION|P|PARAM|TBODY|TD|TFOOT|TH|THEAD|TR|area|base|basefont|body|br|col|colgroup|dd|dt|frame|head|hr|html|img|input|isindex|li|link|meta|option|p|param|tbody|td|tfoot|th|thead|tr)[^<>]*/?>",

"");

//去掉成对的HTML符号

temp_result=temp_result.replaceAll("]*>(.*?)//1>","$2");

//用正则表白式取出符号

Pattern p =

Pattern.compile("]*>");

Matcher m = p.matcher(temp_result);

List endHTML = new ArrayList();

while (m.find()) {

endHTML.add(m.group(1));

}

//补全不成对的HTML符号

for (int i = endHTML.size() - 1; i >= 0; i--)

{

result.append("");

result.append(endHTML.get(i));

result.append(">");

}

return result.toString();

}试图利用setValues()措施来设置负值会引发失常。不幸的是，