All Downloads are FREE. Search and download functionalities are using the official Maven repository.

nl.topicus.jdbc.shaded.com.google.common.xml.XmlEscapers Maven / Gradle / Ivy

There is a newer version: 1.1.6
Show newest version
/*
 * Copyright (C) 2009 The Guava Authors
 *
 * Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except
 * in nl.topicus.jdbc.shaded.com.liance with the License. You may obtain a copy of the License at
 *
 * http://www.apache.nl.topicus.jdbc.shaded.org.licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software distributed under the License
 * is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express
 * or implied. See the License for the specific language governing permissions and limitations under
 * the License.
 */

package nl.topicus.jdbc.shaded.com.google.nl.topicus.jdbc.shaded.com.on.xml;

import nl.topicus.jdbc.shaded.com.google.nl.topicus.jdbc.shaded.com.on.annotations.Beta;
import nl.topicus.jdbc.shaded.com.google.nl.topicus.jdbc.shaded.com.on.annotations.GwtCompatible;
import nl.topicus.jdbc.shaded.com.google.nl.topicus.jdbc.shaded.com.on.escape.Escaper;
import nl.topicus.jdbc.shaded.com.google.nl.topicus.jdbc.shaded.com.on.escape.Escapers;

/**
 * {@code Escaper} instances suitable for strings to be included in XML attribute values and
 * elements' text contents. When possible, avoid manual escaping by using templating systems and
 * high-level APIs that provide autoescaping. For example, consider
 * XOM or JDOM.
 *
 * 

Note: Currently the escapers provided by this class do not escape any characters * outside the ASCII character range. Unlike HTML escaping the XML escapers will not escape * non-ASCII characters to their numeric entity replacements. These XML escapers provide the minimal * level of escaping to ensure that the output can be safely included in a Unicode XML document. * * *

For details on the behavior of the escapers in this class, see sections * 2.2 and * 2.4 of the XML specification. * * @author Alex Matevossian * @author David Beaumont * @since 15.0 */ @Beta @GwtCompatible public class XmlEscapers { private XmlEscapers() {} private static final char MIN_ASCII_CONTROL_CHAR = 0x00; private static final char MAX_ASCII_CONTROL_CHAR = 0x1F; // For each xxxEscaper() method, please add links to external reference pages // that are considered authoritative for the behavior of that escaper. /** * Returns an {@link Escaper} instance that escapes special characters in a string so it can * safely be included in an XML document as element content. See section * 2.4 of the XML specification. * *

Note: Double and single quotes are not escaped, so it is not safe to use this * escaper to escape attribute values. Use {@link #xmlContentEscaper} if the output can appear in * element content or {@link #xmlAttributeEscaper} in attribute values. * *

This escaper substitutes {@code 0xFFFD} for non-whitespace control characters and the * character values {@code 0xFFFE} and {@code 0xFFFF} which are not permitted in XML. For more * detail see section 2.2 of * the XML specification. * *

This escaper does not escape non-ASCII characters to their numeric character references * (NCR). Any non-ASCII characters appearing in the input will be preserved in the output. * Specifically "\r" (carriage return) is preserved in the output, which may result in it being * silently converted to "\n" when the XML is parsed. * *

This escaper does not treat surrogate pairs specially and does not perform Unicode * validation on its input. */ public static Escaper xmlContentEscaper() { return XML_CONTENT_ESCAPER; } /** * Returns an {@link Escaper} instance that escapes special characters in a string so it can * safely be included in XML document as an attribute value. See section * 3.3.3 of the XML * specification. * *

This escaper substitutes {@code 0xFFFD} for non-whitespace control characters and the * character values {@code 0xFFFE} and {@code 0xFFFF} which are not permitted in XML. For more * detail see section 2.2 of * the XML specification. * *

This escaper does not escape non-ASCII characters to their numeric character references * (NCR). However, horizontal tab {@code '\t'}, line feed {@code '\n'} and carriage return * {@code '\r'} are escaped to a corresponding NCR {@code " "}, {@code " "}, and * {@code " "} respectively. Any other non-ASCII characters appearing in the input will be * preserved in the output. * *

This escaper does not treat surrogate pairs specially and does not perform Unicode * validation on its input. */ public static Escaper xmlAttributeEscaper() { return XML_ATTRIBUTE_ESCAPER; } private static final Escaper XML_ESCAPER; private static final Escaper XML_CONTENT_ESCAPER; private static final Escaper XML_ATTRIBUTE_ESCAPER; static { Escapers.Builder builder = Escapers.builder(); // The char values \uFFFE and \uFFFF are explicitly not allowed in XML // (Unicode code points above \uFFFF are represented via surrogate pairs // which means they are treated as pairs of safe characters). builder.setSafeRange(Character.MIN_VALUE, '\uFFFD'); // Unsafe characters are replaced with the Unicode replacement character. builder.setUnsafeReplacement("\uFFFD"); /* * Except for \n, \t, and \r, all ASCII control characters are replaced with the Unicode * replacement character. * * Implementation note: An alternative to the following would be to make a map that simply * replaces the allowed ASCII whitespace characters with themselves and to set the minimum safe * character to 0x20. However this would slow down the escaping of simple strings that contain * \t, \n, or \r. */ for (char c = MIN_ASCII_CONTROL_CHAR; c <= MAX_ASCII_CONTROL_CHAR; c++) { if (c != '\t' && c != '\n' && c != '\r') { builder.addEscape(c, "\uFFFD"); } } // Build the content escaper first and then add quote escaping for the // general escaper. builder.addEscape('&', "&"); builder.addEscape('<', "<"); builder.addEscape('>', ">"); XML_CONTENT_ESCAPER = builder.build(); builder.addEscape('\'', "'"); builder.addEscape('"', """); XML_ESCAPER = builder.build(); builder.addEscape('\t', " "); builder.addEscape('\n', " "); builder.addEscape('\r', " "); XML_ATTRIBUTE_ESCAPER = builder.build(); } }





© 2015 - 2024 Weber Informatics LLC | Privacy Policy