1 // Copyright (c) 2011, Mike Samuel 2 // All rights reserved. 3 // 4 // Redistribution and use in source and binary forms, with or without 5 // modification, are permitted provided that the following conditions 6 // are met: 7 // 8 // Redistributions of source code must retain the above copyright 9 // notice, this list of conditions and the following disclaimer. 10 // Redistributions in binary form must reproduce the above copyright 11 // notice, this list of conditions and the following disclaimer in the 12 // documentation and/or other materials provided with the distribution. 13 // Neither the name of the OWASP nor the names of its contributors may 14 // be used to endorse or promote products derived from this software 15 // without specific prior written permission. 16 // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 17 // "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 18 // LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS 19 // FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 20 // COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, 21 // INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, 22 // BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; 23 // LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER 24 // CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 25 // LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN 26 // ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 27 // POSSIBILITY OF SUCH DAMAGE. 28 29 package org.owasp.html; 30 31 /** 32 * Types of HTML tokens. 33 * 34 * @author Mike Samuel <mikesamuel@gmail.com> 35 */ 36 enum HtmlTokenType { 37 /** 38 * An HTML or XML attribute name consisting of characters other than 39 * whitespace, =, or specials. 40 */ 41 ATTRNAME, 42 /** An HTML value, possibly a quoted string. */ 43 ATTRVALUE, 44 /** 45 * An HTML bogus comment, XML Prologue, or XML processing instruction like 46 * <tt><? content ></tt>. 47 */ 48 QMARKMETA, 49 /** An HTML or XML style comment, <tt><!-- for example --></tt>. */ 50 COMMENT, 51 /** 52 * A directive such as a DOCTYPE declaration. 53 */ 54 DIRECTIVE, 55 /** Unescaped tag, for instance, inside a script, or {@code xmp} tag. */ 56 UNESCAPED, 57 /** 58 * A quoted string. Should not show up in well formed HTML, but may where 59 * there is an attribute value without a corresponding name. 60 */ 61 QSTRING, 62 /** 63 * The beginning of a tag -- not to be confused with a start tag. 64 * Valid tag beginnings include <tt><a</tt> and <tt></a</tt>. The 65 * rest of the tag is a series of attribute names, values, and the tag end. 66 */ 67 TAGBEGIN, 68 /** The end of a tag. Either <tt>></tt> or <tt>/></tt>. */ 69 TAGEND, 70 /** A block of text, either inside a tag, or as element content. */ 71 TEXT, 72 /** Ignorable whitespace nodes. */ 73 IGNORABLE, 74 /** A server side script block a la php or jsp. */ 75 SERVERCODE, 76 ; 77 } 78