XSS过滤 XssFilter

XSS过滤 XssFilter

组件说明

跨站脚本攻击，为不和层叠样式表的缩写混淆，故将跨站脚本攻击缩写为XSS。恶意攻击者往Web页面里插入恶意html代码，当用户浏览该页之时，嵌入其中Web里面的html代码会被执行，从而达到恶意攻击用户的特殊目的

实现原理

通过注册过滤器，通过HTMLFilter工具类，对于前端有可能产生安全问题的标签进行替换操作。

HTMLFilter核心源码

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"