import java.util.regex.Matcher; import java.util.regex.Pattern; /** *

* Title: HTML 相关的正则表达式工具类 *

*

* Description: 包括过滤 HTML 标记，转换 HTML 标记，替换特定 HTML 标记 *

*

* Copyright: Copyright (c) 2006 *

* * @author hejian * @version 1.0 * @createtime 2006-10-16 */ public class HtmlRegexpUtil { private final static String regxpForHtml = "<([^>]*)>"; // 过滤所有以<开头以>结尾的标签 private final static String regxpForImgTag = "<\\s*img\\s+([^>]*)\\s*>"; // 找出 IMG 标签 private final static String regxpForImaTagSrcAttrib = "src=\"([^\"]+)\""; // 找出 IMG 标签的 SRC 属性 /** * */ public HtmlRegexpUtil() { // TODO Auto-generated constructor stub } /** * * 基本功能：替换标记以正常显示 *

* * @param input * @return String */ public String replaceTag(String input) { if (!hasSpecialChars(input)) { 

return input; } StringBuffer filtered = new StringBuffer(input.length()); char c; for (int i = 0; i <= input.length() - 1; i++) { c = input.charAt(i); switch (c) { case '<': filtered.append("<"); break; case '>': filtered.append(">"); break; case '"': filtered.append("""); break; case '&': filtered.append("&"); break; default: filtered.append(c); } } return (filtered.toString()); } /** * * 基本功能：判断标记是否存在 *

* * @param input * @return boolean */ public boolean hasSpecialChars(String input) { boolean flag = false; if ((input != null) && (input.length() > 0)) { char c; for (int i = 0; i <= input.length() - 1; i++) { c = input.charAt(i); switch (c) { case '>': flag = true; 

break; case '<': flag = true; break; case '"': flag = true; break; case '&': flag = true; break; } } } return flag; } /** * * 基本功能：过滤所有以"<"开头以">"结尾的标签 *

* * @param str * @return String */ public static String filterHtml(String str) { Pattern pattern = Pattern.compile(regxpForHtml); Matcher matcher = pattern.matcher(str); StringBuffer sb = new StringBuffer(); boolean result1 = matcher.find(); while (result1) { matcher.appendReplacement(sb, ""); result1 = matcher.find(); } matcher.appendTail(sb); return sb.toString(); } /** * * 基本功能：过滤指定标签 *

* * @param str * @param tag 

指定标签 * * @return String */ public static String fiterHtmlTag(String str, String tag) { String regxp = "<\\s*" + tag + "\\s+([^>]*)\\s*>"; Pattern pattern = Pattern.compile(regxp); Matcher matcher = pattern.matcher(str); StringBuffer sb = new StringBuffer(); boolean result1 = matcher.find(); while (result1) { matcher.appendReplacement(sb, ""); result1 = matcher.find(); } matcher.appendTail(sb); return sb.toString(); } 要替换的标签 /** * * 基本功能：替换指定的标签 *

* * @param str * @param beforeTag * * @param tagAttrib * * @param startTag * * @param endTag * * @return String * @如：替换 img 标签的 src 属性值为[img]属性值[/img] */ public static String replaceHtmlTag(String str, String beforeTag, 要替换的标签属性值 新标签开始标记 新标签结束标记 String tagAttrib, String startTag, String endTag) { String regxpForTag = "<\\s*" + beforeTag + "\\s+([^>]*)\\s*>"; String regxpForTagAttrib = tagAttrib + "=\"([^\"]+)\""; Pattern patternForTag = Pattern.compile(regxpForTag); Pattern patternForAttrib = Pattern.compile(regxpForTagAttrib); Matcher matcherForTag = patternForTag.matcher(str); StringBuffer sb = new StringBuffer(); boolean result = matcherForTag.find(); while (result) { 

StringBuffer sbreplace = new StringBuffer(); Matcher matcherForAttrib = patternForAttrib.matcher(matcherForTag .group(1)); if (matcherForAttrib.find()) { matcherForAttrib.appendReplacement(sbreplace, startTag + matcherForAttrib.group(1) + endTag); } matcherForTag.appendReplacement(sb, sbreplace.toString()); result = matcherForTag.find(); } matcherForTag.appendTail(sb); return sb.toString(); } } if($this->compress){ $KindData = preg_replace("~>\s+\r~", ">", preg_replace("~>\s+\n~", ">", $KindData)); //modify 压缩 $KindData = preg_replace("~>\s+<~", "><", $KindData); } 只压缩 HTML 代码,对 JAVASCRIPT 不影响.