001/* 002 * Copyright (C) 2009 The Guava Authors 003 * 004 * Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except 005 * in compliance with the License. You may obtain a copy of the License at 006 * 007 * http://www.apache.org/licenses/LICENSE-2.0 008 * 009 * Unless required by applicable law or agreed to in writing, software distributed under the License 010 * is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express 011 * or implied. See the License for the specific language governing permissions and limitations under 012 * the License. 013 */ 014 015package com.google.common.xml; 016 017import com.google.common.annotations.Beta; 018import com.google.common.annotations.GwtCompatible; 019import com.google.common.escape.Escaper; 020import com.google.common.escape.Escapers; 021 022/** 023 * {@code Escaper} instances suitable for strings to be included in XML attribute values and 024 * elements' text contents. When possible, avoid manual escaping by using templating systems and 025 * high-level APIs that provide autoescaping. For example, consider <a 026 * href="http://www.xom.nu/">XOM</a> or <a href="http://www.jdom.org/">JDOM</a>. 027 * 028 * <p><b>Note:</b> Currently the escapers provided by this class do not escape any characters 029 * outside the ASCII character range. Unlike HTML escaping the XML escapers will not escape 030 * non-ASCII characters to their numeric entity replacements. These XML escapers provide the minimal 031 * level of escaping to ensure that the output can be safely included in a Unicode XML document. 032 * 033 * <p>For details on the behavior of the escapers in this class, see sections <a 034 * href="http://www.w3.org/TR/2008/REC-xml-20081126/#charsets">2.2</a> and <a 035 * href="http://www.w3.org/TR/2008/REC-xml-20081126/#syntax">2.4</a> of the XML specification. 036 * 037 * @author Alex Matevossian 038 * @author David Beaumont 039 * @since 15.0 040 */ 041@Beta 042@GwtCompatible 043public class XmlEscapers { 044 private XmlEscapers() {} 045 046 private static final char MIN_ASCII_CONTROL_CHAR = 0x00; 047 private static final char MAX_ASCII_CONTROL_CHAR = 0x1F; 048 049 // For each xxxEscaper() method, please add links to external reference pages 050 // that are considered authoritative for the behavior of that escaper. 051 052 /** 053 * Returns an {@link Escaper} instance that escapes special characters in a string so it can 054 * safely be included in an XML document as element content. See section <a 055 * href="http://www.w3.org/TR/2008/REC-xml-20081126/#syntax">2.4</a> of the XML specification. 056 * 057 * <p><b>Note:</b> Double and single quotes are not escaped, so it is <b>not safe</b> to use this 058 * escaper to escape attribute values. Use {@link #xmlContentEscaper} if the output can appear in 059 * element content or {@link #xmlAttributeEscaper} in attribute values. 060 * 061 * <p>This escaper substitutes {@code 0xFFFD} for non-whitespace control characters and the 062 * character values {@code 0xFFFE} and {@code 0xFFFF} which are not permitted in XML. For more 063 * detail see section <a href="http://www.w3.org/TR/2008/REC-xml-20081126/#charsets">2.2</a> of 064 * the XML specification. 065 * 066 * <p>This escaper does not escape non-ASCII characters to their numeric character references 067 * (NCR). Any non-ASCII characters appearing in the input will be preserved in the output. 068 * Specifically "\r" (carriage return) is preserved in the output, which may result in it being 069 * silently converted to "\n" when the XML is parsed. 070 * 071 * <p>This escaper does not treat surrogate pairs specially and does not perform Unicode 072 * validation on its input. 073 */ 074 public static Escaper xmlContentEscaper() { 075 return XML_CONTENT_ESCAPER; 076 } 077 078 /** 079 * Returns an {@link Escaper} instance that escapes special characters in a string so it can 080 * safely be included in XML document as an attribute value. See section <a 081 * href="http://www.w3.org/TR/2008/REC-xml-20081126/#AVNormalize">3.3.3</a> of the XML 082 * specification. 083 * 084 * <p>This escaper substitutes {@code 0xFFFD} for non-whitespace control characters and the 085 * character values {@code 0xFFFE} and {@code 0xFFFF} which are not permitted in XML. For more 086 * detail see section <a href="http://www.w3.org/TR/2008/REC-xml-20081126/#charsets">2.2</a> of 087 * the XML specification. 088 * 089 * <p>This escaper does not escape non-ASCII characters to their numeric character references 090 * (NCR). However, horizontal tab {@code '\t'}, line feed {@code '\n'} and carriage return {@code 091 * '\r'} are escaped to a corresponding NCR {@code "	"}, {@code "
"}, and {@code "
"} 092 * respectively. Any other non-ASCII characters appearing in the input will be preserved in the 093 * output. 094 * 095 * <p>This escaper does not treat surrogate pairs specially and does not perform Unicode 096 * validation on its input. 097 */ 098 public static Escaper xmlAttributeEscaper() { 099 return XML_ATTRIBUTE_ESCAPER; 100 } 101 102 private static final Escaper XML_ESCAPER; 103 private static final Escaper XML_CONTENT_ESCAPER; 104 private static final Escaper XML_ATTRIBUTE_ESCAPER; 105 106 static { 107 Escapers.Builder builder = Escapers.builder(); 108 // The char values \uFFFE and \uFFFF are explicitly not allowed in XML 109 // (Unicode code points above \uFFFF are represented via surrogate pairs 110 // which means they are treated as pairs of safe characters). 111 builder.setSafeRange(Character.MIN_VALUE, '\uFFFD'); 112 // Unsafe characters are replaced with the Unicode replacement character. 113 builder.setUnsafeReplacement("\uFFFD"); 114 115 /* 116 * Except for \n, \t, and \r, all ASCII control characters are replaced with the Unicode 117 * replacement character. 118 * 119 * Implementation note: An alternative to the following would be to make a map that simply 120 * replaces the allowed ASCII whitespace characters with themselves and to set the minimum safe 121 * character to 0x20. However this would slow down the escaping of simple strings that contain 122 * \t, \n, or \r. 123 */ 124 for (char c = MIN_ASCII_CONTROL_CHAR; c <= MAX_ASCII_CONTROL_CHAR; c++) { 125 if (c != '\t' && c != '\n' && c != '\r') { 126 builder.addEscape(c, "\uFFFD"); 127 } 128 } 129 130 // Build the content escaper first and then add quote escaping for the 131 // general escaper. 132 builder.addEscape('&', "&"); 133 builder.addEscape('<', "<"); 134 builder.addEscape('>', ">"); 135 XML_CONTENT_ESCAPER = builder.build(); 136 builder.addEscape('\'', "'"); 137 builder.addEscape('"', """); 138 XML_ESCAPER = builder.build(); 139 builder.addEscape('\t', "	"); 140 builder.addEscape('\n', "
"); 141 builder.addEscape('\r', "
"); 142 XML_ATTRIBUTE_ESCAPER = builder.build(); 143 } 144}