Source code
package com.google.common.escape;
import static com.google.common.base.Preconditions.checkNotNull;
import com.google.common.annotations.GwtCompatible;
import java.util.Map;
import org.jspecify.annotations.Nullable;
/**
* A {@link CharEscaper} that uses an array to quickly look up replacement characters for a given
* {@code char} value. An additional safe range is provided that determines whether {@code char}
* values without specific replacements are to be considered safe and left unescaped or should be
* escaped in a general way.
*
* <p>A good example of usage of this class is for Java source code escaping where the replacement
* array contains information about special ASCII characters such as {@code \\t} and {@code \\n}
* while {@link #escapeUnsafe} is overridden to handle general escaping of the form {@code \\uxxxx}.
*
* <p>The size of the data structure used by {@link ArrayBasedCharEscaper} is proportional to the
* highest valued character that requires escaping. For example a replacement map containing the
* single character '{@code \}{@code u1000}' will require approximately 16K of memory. If you need
* to create multiple escaper instances that have the same character replacement mapping consider
* using {@link ArrayBasedEscaperMap}.
*
* @author Sven Mawson
* @author David Beaumont
* @since 15.0
*/
@GwtCompatible
public abstract class ArrayBasedCharEscaper extends CharEscaper {
// The replacement array (see ArrayBasedEscaperMap).
private final char[][] replacements;
// The number of elements in the replacement array.
private final int replacementsLength;
// The first character in the safe range.
private final char safeMin;
// The last character in the safe range.
private final char safeMax;
/**
* Creates a new ArrayBasedCharEscaper instance with the given replacement map and specified safe
* range. If {@code safeMax < safeMin} then no characters are considered safe.
*
* <p>If a character has no mapped replacement then it is checked against the safe range. If it
* lies outside that, then {@link #escapeUnsafe} is called, otherwise no escaping is performed.
*
* @param replacementMap a map of characters to their escaped representations
* @param safeMin the lowest character value in the safe range
* @param safeMax the highest character value in the safe range
*/
protected ArrayBasedCharEscaper(
Map<Character, String> a, char b, char d) {
this(ArrayBasedEscaperMap.create(a), b, d);
}
/**
* Creates a new ArrayBasedCharEscaper instance with the given replacement map and specified safe
* range. If {@code safeMax < safeMin} then no characters are considered safe. This initializer is
* useful when explicit instances of ArrayBasedEscaperMap are used to allow the sharing of large
* replacement mappings.
*
* <p>If a character has no mapped replacement then it is checked against the safe range. If it
* lies outside that, then {@link #escapeUnsafe} is called, otherwise no escaping is performed.
*
* @param escaperMap the mapping of characters to be escaped
* @param safeMin the lowest character value in the safe range
* @param safeMax the highest character value in the safe range
*/
protected ArrayBasedCharEscaper(ArrayBasedEscaperMap e, char f, char g) {
checkNotNull(e); // GWT specific check (do not optimize)
this.replacements = e.getReplacementArray();
this.replacementsLength = replacements.length;
if (g < f) {
// If the safe range is empty, set the range limits to opposite extremes
// to ensure the first test of either value will (almost certainly) fail.
g = Character.MIN_VALUE;
f = Character.MAX_VALUE;
}
this.safeMin = f;
this.safeMax = g;
}
/*
* This is overridden to improve performance. Rough benchmarking shows that this almost doubles
* the speed when processing strings that do not require any escaping.
*/
@Override
public final String a(String h) {
checkNotNull(h); // GWT specific check (do not optimize).
for (int i = 0; i < h.length(); i++) {
char c = h.charAt(i);
if ((c < replacementsLength && replacements[c] != null) || c > safeMax || c < safeMin) {
return escapeSlow(h, i);
}
}
return h;
}
/**
* Escapes a single character using the replacement array and safe range values. If the given
* character does not have an explicit replacement and lies outside the safe range then {@link
* #escapeUnsafe} is called.
*
* @return the replacement characters, or {@code null} if no escaping was required
*/
@Override
protected final char @Nullable [] a(char c) {
if (c < replacementsLength) {
char[] j = replacements[c];
if (j != null) {
return j;
}
}
if (c >= safeMin && c <= safeMax) {
return null;
}
return b(c);
}
/**
* Escapes a {@code char} value that has no direct explicit value in the replacement array and
* lies outside the stated safe range. Subclasses should override this method to provide
* generalized escaping for characters.
*
* <p>Note that arrays returned by this method must not be modified once they have been returned.
* However it is acceptable to return the same array multiple times (even for different input
* characters).
*
* @param c the character to escape
* @return the replacement characters, or {@code null} if no escaping was required
*/
// TODO(dbeaumont,cpovirk): Rename this something better once refactoring done
protected abstract char @Nullable [] b(char c);
}