acscommons.com.google.common.escape.Escaper Maven / Gradle / Ivy
Show all versions of acs-aem-commons-bundle Show documentation
/*
* Copyright (C) 2008 The Guava Authors
*
* Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except
* in compliance with the License. You may obtain a copy of the License at
*
* http://www.apache.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 acscommons.com.google.common.escape;
import acscommons.com.google.common.annotations.GwtCompatible;
import acscommons.com.google.common.base.Function;
import com.google.errorprone.annotations.DoNotMock;
/**
* An object that converts literal text into a format safe for inclusion in a particular context
* (such as an XML document). Typically (but not always), the inverse process of "unescaping" the
* text is performed automatically by the relevant parser.
*
* For example, an XML escaper would convert the literal string {@code "Foo"} into {@code
* "Foo<Bar>"} to prevent {@code ""} from being confused with an XML tag. When the
* resulting XML document is parsed, the parser API will return this text as the original literal
* string {@code "Foo"}.
*
* An {@code Escaper} instance is required to be stateless, and safe when used concurrently by
* multiple threads.
*
*
Because, in general, escaping operates on the code points of a string and not on its
* individual {@code char} values, it is not safe to assume that {@code escape(s)} is equivalent to
* {@code escape(s.substring(0, n)) + escape(s.substring(n))} for arbitrary {@code n}. This is
* because of the possibility of splitting a surrogate pair. The only case in which it is safe to
* escape strings and concatenate the results is if you can rule out this possibility, either by
* splitting an existing long string into short strings adaptively around {@linkplain
* Character#isHighSurrogate surrogate} {@linkplain Character#isLowSurrogate pairs}, or by starting
* with short strings already known to be free of unpaired surrogates.
*
*
The two primary implementations of this interface are {@link CharEscaper} and {@link
* UnicodeEscaper}. They are heavily optimized for performance and greatly simplify the task of
* implementing new escapers. It is strongly recommended that when implementing a new escaper you
* extend one of these classes. If you find that you are unable to achieve the desired behavior
* using either of these classes, please contact the Java libraries team for advice.
*
*
Popular escapers are defined as constants in classes like {@link
* acscommons.com.google.common.html.HtmlEscapers} and {@link acscommons.com.google.common.xml.XmlEscapers}. To create
* your own escapers, use {@link CharEscaperBuilder}, or extend {@code CharEscaper} or {@code
* UnicodeEscaper}.
*
* @author David Beaumont
* @since 15.0
*/
@DoNotMock("Use Escapers.nullEscaper() or another methods from the *Escapers classes")
@GwtCompatible
@ElementTypesAreNonnullByDefault
public abstract class Escaper {
// TODO(dbeaumont): evaluate custom implementations, considering package private constructor.
/** Constructor for use by subclasses. */
protected Escaper() {}
/**
* Returns the escaped form of a given literal string.
*
*
Note that this method may treat input characters differently depending on the specific
* escaper implementation.
*
*
* - {@link UnicodeEscaper} handles UTF-16
* correctly, including surrogate character pairs. If the input is badly formed the escaper
* should throw {@link IllegalArgumentException}.
*
- {@link CharEscaper} handles Java characters independently and does not verify the input
* for well formed characters. A {@code CharEscaper} should not be used in situations where
* input is not guaranteed to be restricted to the Basic Multilingual Plane (BMP).
*
*
* @param string the literal string to be escaped
* @return the escaped form of {@code string}
* @throws NullPointerException if {@code string} is null
* @throws IllegalArgumentException if {@code string} contains badly formed UTF-16 or cannot be
* escaped for any other reason
*/
public abstract String escape(String string);
private final Function asFunction = this::escape;
/** Returns a {@link Function} that invokes {@link #escape(String)} on this escaper. */
public final Function asFunction() {
return asFunction;
}
}