Ejemplo n.º 1
0
 /// <summary>
 /// Instantiates the filter where only the character ranges specified by <paramref name="allowedRanges"/>
 /// are allowed by the filter.
 /// </summary>
 public TextEncoderSettings(params UnicodeRange[] allowedRanges)
 {
     if (allowedRanges == null)
     {
         throw new ArgumentNullException(nameof(allowedRanges));
     }
     _allowedCharactersBitmap = AllowedCharactersBitmap.CreateNew();
     AllowRanges(allowedRanges);
 }
Ejemplo n.º 2
0
 /// <summary>
 /// Instantiates an empty filter (allows no code points through by default).
 /// </summary>
 public TextEncoderSettings()
 {
     _allowedCharactersBitmap = AllowedCharactersBitmap.CreateNew();
 }
Ejemplo n.º 3
0
 /// <summary>
 /// Instantiates the filter by cloning the allow list of another <see cref="TextEncoderSettings"/>.
 /// </summary>
 public TextEncoderSettings(TextEncoderSettings other)
 {
     _allowedCharactersBitmap = AllowedCharactersBitmap.CreateNew();
     AllowCodePoints(other.GetAllowedCodePoints());
 }
Ejemplo n.º 4
0
        public DefaultUrlEncoder(TextEncoderSettings filter)
        {
            if (filter == null)
            {
                throw new ArgumentNullException(nameof(filter));
            }

            _allowedCharacters = filter.GetAllowedCharacters();

            // Forbid codepoints which aren't mapped to characters or which are otherwise always disallowed
            // (includes categories Cc, Cs, Co, Cn, Zs [except U+0020 SPACE], Zl, Zp)
            _allowedCharacters.ForbidUndefinedCharacters();

            // Forbid characters that are special in HTML.
            // Even though this is a not HTML encoder,
            // it's unfortunately common for developers to
            // forget to HTML-encode a string once it has been URL-encoded,
            // so this offers extra protection.
            //important comment by jiayongqiang2018.7.6
            //DefaultHtmlEncoder.ForbidHtmlCharacters(_allowedCharacters);

            // Per RFC 3987, Sec. 2.2, we want encodings that are safe for
            // four particular components: 'isegment', 'ipath-noscheme',
            // 'iquery', and 'ifragment'. The relevant definitions are below.
            //
            //    ipath-noscheme = isegment-nz-nc *( "/" isegment )
            //
            //    isegment       = *ipchar
            //
            //    isegment-nz-nc = 1*( iunreserved / pct-encoded / sub-delims
            //                         / "@" )
            //                   ; non-zero-length segment without any colon ":"
            //
            //    ipchar         = iunreserved / pct-encoded / sub-delims / ":"
            //                   / "@"
            //
            //    iquery         = *( ipchar / iprivate / "/" / "?" )
            //
            //    ifragment      = *( ipchar / "/" / "?" )
            //
            //    iunreserved    = ALPHA / DIGIT / "-" / "." / "_" / "~" / ucschar
            //
            //    ucschar        = %xA0-D7FF / %xF900-FDCF / %xFDF0-FFEF
            //                   / %x10000-1FFFD / %x20000-2FFFD / %x30000-3FFFD
            //                   / %x40000-4FFFD / %x50000-5FFFD / %x60000-6FFFD
            //                   / %x70000-7FFFD / %x80000-8FFFD / %x90000-9FFFD
            //                   / %xA0000-AFFFD / %xB0000-BFFFD / %xC0000-CFFFD
            //                   / %xD0000-DFFFD / %xE1000-EFFFD
            //
            //    pct-encoded    = "%" HEXDIG HEXDIG
            //
            //    sub-delims     = "!" / "$" / "&" / "'" / "(" / ")"
            //                   / "*" / "+" / "," / ";" / "="
            //
            // The only common characters between these four components are the
            // intersection of 'isegment-nz-nc' and 'ipchar', which is really
            // just 'isegment-nz-nc' (colons forbidden).
            //
            // From this list, the base encoder already forbids "&", "'", "+",
            // and we'll additionally forbid "=" since it has special meaning
            // in x-www-form-urlencoded representations.
            //
            // This means that the full list of allowed characters from the
            // Basic Latin set is:
            // ALPHA / DIGIT / "-" / "." / "_" / "~" / "!" / "$" / "(" / ")" / "*" / "," / ";" / "@"

            const string forbiddenChars = @" #%/:=?[\]^`{|}"; // chars from Basic Latin which aren't already disallowed by the base encoder

            foreach (char character in forbiddenChars)
            {
                _allowedCharacters.ForbidCharacter(character);
            }

            // Specials (U+FFF0 .. U+FFFF) are forbidden by the definition of 'ucschar' above
            for (int i = 0; i < 16; i++)
            {
                _allowedCharacters.ForbidCharacter((char)(0xFFF0 | i));
            }
        }