Throughout the documentation of this class, the phrase "matching character" is used to mean * "any character {@code c} for which {@code this.matches(c)} returns {@code true}". * *
Note: This class deals only with {@code char} values; it does not understand * supplementary Unicode code points in the range {@code 0x10000} to {@code 0x10FFFF}. Such logical * characters are encoded into a {@code String} using surrogate pairs, and a {@code CharMatcher} * treats these just as two separate characters. * *
Example usages:
* String trimmed = {@link #WHITESPACE WHITESPACE}.{@link #trimFrom trimFrom}(userInput);
* if ({@link #ASCII ASCII}.{@link #matchesAllOf matchesAllOf}(s)) { ... }
*
* See the Guava User Guide article on
* {@code CharMatcher}.
*
* @author Kevin Bourrillion
* @since 1.0
*/
@Beta // Possibly change from chars to code points; decide constants vs. methods
@GwtCompatible(emulated = true)
public abstract class CharMatcher implements Predicate Note: as the reference file evolves, we will modify this constant to keep it up to
* date.
*/
public static final CharMatcher SINGLE_WIDTH = new RangesMatcher("CharMatcher.SINGLE_WIDTH",
"\u0000\u05be\u05d0\u05f3\u0600\u0750\u0e00\u1e00\u2100\ufb50\ufe70\uff61".toCharArray(),
"\u04f9\u05be\u05ea\u05f4\u06ff\u077f\u0e7f\u20af\u213a\ufdff\ufeff\uffdc".toCharArray());
/** Matches any character. */
public static final CharMatcher ANY =
new FastMatcher("CharMatcher.ANY") {
@Override public boolean matches(char c) {
return true;
}
@Override public int indexIn(CharSequence sequence) {
return (sequence.length() == 0) ? -1 : 0;
}
@Override public int indexIn(CharSequence sequence, int start) {
int length = sequence.length();
Preconditions.checkPositionIndex(start, length);
return (start == length) ? -1 : start;
}
@Override public int lastIndexIn(CharSequence sequence) {
return sequence.length() - 1;
}
@Override public boolean matchesAllOf(CharSequence sequence) {
checkNotNull(sequence);
return true;
}
@Override public boolean matchesNoneOf(CharSequence sequence) {
return sequence.length() == 0;
}
@Override public String removeFrom(CharSequence sequence) {
checkNotNull(sequence);
return "";
}
@Override public String replaceFrom(CharSequence sequence, char replacement) {
char[] array = new char[sequence.length()];
Arrays.fill(array, replacement);
return new String(array);
}
@Override public String replaceFrom(CharSequence sequence, CharSequence replacement) {
StringBuilder retval = new StringBuilder(sequence.length() * replacement.length());
for (int i = 0; i < sequence.length(); i++) {
retval.append(replacement);
}
return retval.toString();
}
@Override public String collapseFrom(CharSequence sequence, char replacement) {
return (sequence.length() == 0) ? "" : String.valueOf(replacement);
}
@Override public String trimFrom(CharSequence sequence) {
checkNotNull(sequence);
return "";
}
@Override public int countIn(CharSequence sequence) {
return sequence.length();
}
@Override public CharMatcher and(CharMatcher other) {
return checkNotNull(other);
}
@Override public CharMatcher or(CharMatcher other) {
checkNotNull(other);
return this;
}
@Override public CharMatcher negate() {
return NONE;
}
};
/** Matches no characters. */
public static final CharMatcher NONE =
new FastMatcher("CharMatcher.NONE") {
@Override public boolean matches(char c) {
return false;
}
@Override public int indexIn(CharSequence sequence) {
checkNotNull(sequence);
return -1;
}
@Override public int indexIn(CharSequence sequence, int start) {
int length = sequence.length();
Preconditions.checkPositionIndex(start, length);
return -1;
}
@Override public int lastIndexIn(CharSequence sequence) {
checkNotNull(sequence);
return -1;
}
@Override public boolean matchesAllOf(CharSequence sequence) {
return sequence.length() == 0;
}
@Override public boolean matchesNoneOf(CharSequence sequence) {
checkNotNull(sequence);
return true;
}
@Override public String removeFrom(CharSequence sequence) {
return sequence.toString();
}
@Override public String replaceFrom(CharSequence sequence, char replacement) {
return sequence.toString();
}
@Override public String replaceFrom(CharSequence sequence, CharSequence replacement) {
checkNotNull(replacement);
return sequence.toString();
}
@Override public String collapseFrom(CharSequence sequence, char replacement) {
return sequence.toString();
}
@Override public String trimFrom(CharSequence sequence) {
return sequence.toString();
}
@Override
public String trimLeadingFrom(CharSequence sequence) {
return sequence.toString();
}
@Override
public String trimTrailingFrom(CharSequence sequence) {
return sequence.toString();
}
@Override public int countIn(CharSequence sequence) {
checkNotNull(sequence);
return 0;
}
@Override public CharMatcher and(CharMatcher other) {
checkNotNull(other);
return this;
}
@Override public CharMatcher or(CharMatcher other) {
return checkNotNull(other);
}
@Override public CharMatcher negate() {
return ANY;
}
};
// Static factories
/**
* Returns a {@code char} matcher that matches only one specified character.
*/
public static CharMatcher is(final char match) {
String description = "CharMatcher.is('" + showCharacter(match) + "')";
return new FastMatcher(description) {
@Override public boolean matches(char c) {
return c == match;
}
@Override public String replaceFrom(CharSequence sequence, char replacement) {
return sequence.toString().replace(match, replacement);
}
@Override public CharMatcher and(CharMatcher other) {
return other.matches(match) ? this : NONE;
}
@Override public CharMatcher or(CharMatcher other) {
return other.matches(match) ? other : super.or(other);
}
@Override public CharMatcher negate() {
return isNot(match);
}
@GwtIncompatible("java.util.BitSet")
@Override
void setBits(BitSet table) {
table.set(match);
}
};
}
/**
* Returns a {@code char} matcher that matches any character except the one specified.
*
* To negate another {@code CharMatcher}, use {@link #negate()}.
*/
public static CharMatcher isNot(final char match) {
String description = "CharMatcher.isNot(" + Integer.toHexString(match) + ")";
return new FastMatcher(description) {
@Override public boolean matches(char c) {
return c != match;
}
@Override public CharMatcher and(CharMatcher other) {
return other.matches(match) ? super.and(other) : other;
}
@Override public CharMatcher or(CharMatcher other) {
return other.matches(match) ? ANY : this;
}
@GwtIncompatible("java.util.BitSet")
@Override
void setBits(BitSet table) {
table.set(0, match);
table.set(match + 1, Character.MAX_VALUE + 1);
}
@Override public CharMatcher negate() {
return is(match);
}
};
}
/**
* Returns a {@code char} matcher that matches any character present in the given character
* sequence.
*/
public static CharMatcher anyOf(final CharSequence sequence) {
switch (sequence.length()) {
case 0:
return NONE;
case 1:
return is(sequence.charAt(0));
case 2:
return isEither(sequence.charAt(0), sequence.charAt(1));
default:
// continue below to handle the general case
}
// TODO(user): is it potentially worth just going ahead and building a precomputed matcher?
final char[] chars = sequence.toString().toCharArray();
Arrays.sort(chars);
StringBuilder description = new StringBuilder("CharMatcher.anyOf(\"");
for (char c : chars) {
description.append(showCharacter(c));
}
description.append("\")");
return new CharMatcher(description.toString()) {
@Override public boolean matches(char c) {
return Arrays.binarySearch(chars, c) >= 0;
}
@Override
@GwtIncompatible("java.util.BitSet")
void setBits(BitSet table) {
for (char c : chars) {
table.set(c);
}
}
};
}
private static CharMatcher isEither(
final char match1,
final char match2) {
String description = "CharMatcher.anyOf(\"" +
showCharacter(match1) + showCharacter(match2) + "\")";
return new FastMatcher(description) {
@Override public boolean matches(char c) {
return c == match1 || c == match2;
}
@GwtIncompatible("java.util.BitSet")
@Override void setBits(BitSet table) {
table.set(match1);
table.set(match2);
}
};
}
/**
* Returns a {@code char} matcher that matches any character not present in the given character
* sequence.
*/
public static CharMatcher noneOf(CharSequence sequence) {
return anyOf(sequence).negate();
}
/**
* Returns a {@code char} matcher that matches any character in a given range (both endpoints are
* inclusive). For example, to match any lowercase letter of the English alphabet, use {@code
* CharMatcher.inRange('a', 'z')}.
*
* @throws IllegalArgumentException if {@code endInclusive < startInclusive}
*/
public static CharMatcher inRange(final char startInclusive, final char endInclusive) {
checkArgument(endInclusive >= startInclusive);
String description = "CharMatcher.inRange('" +
showCharacter(startInclusive) + "', '" +
showCharacter(endInclusive) + "')";
return inRange(startInclusive, endInclusive, description);
}
static CharMatcher inRange(final char startInclusive, final char endInclusive,
String description) {
return new FastMatcher(description) {
@Override public boolean matches(char c) {
return startInclusive <= c && c <= endInclusive;
}
@GwtIncompatible("java.util.BitSet")
@Override void setBits(BitSet table) {
table.set(startInclusive, endInclusive + 1);
}
};
}
/**
* Returns a matcher with identical behavior to the given {@link Character}-based predicate, but
* which operates on primitive {@code char} instances instead.
*/
public static CharMatcher forPredicate(final Predicate predicate) {
checkNotNull(predicate);
if (predicate instanceof CharMatcher) {
return (CharMatcher) predicate;
}
String description = "CharMatcher.forPredicate(" + predicate + ")";
return new CharMatcher(description) {
@Override public boolean matches(char c) {
return predicate.apply(c);
}
@Override public boolean apply(Character character) {
return predicate.apply(checkNotNull(character));
}
};
}
// State
final String description;
// Constructors
/**
* Sets the {@code toString()} from the given description.
*/
CharMatcher(String description) {
this.description = description;
}
/**
* Constructor for use by subclasses. When subclassing, you may want to override
* {@code toString()} to provide a useful description.
*/
protected CharMatcher() {
description = super.toString();
}
// Abstract methods
/** Determines a true or false value for the given character. */
public abstract boolean matches(char c);
// Non-static factories
/**
* Returns a matcher that matches any character not matched by this matcher.
*/
public CharMatcher negate() {
return new NegatedMatcher(this);
}
private static class NegatedMatcher extends CharMatcher {
final CharMatcher original;
NegatedMatcher(String toString, CharMatcher original) {
super(toString);
this.original = original;
}
NegatedMatcher(CharMatcher original) {
this(original + ".negate()", original);
}
@Override public boolean matches(char c) {
return !original.matches(c);
}
@Override public boolean matchesAllOf(CharSequence sequence) {
return original.matchesNoneOf(sequence);
}
@Override public boolean matchesNoneOf(CharSequence sequence) {
return original.matchesAllOf(sequence);
}
@Override public int countIn(CharSequence sequence) {
return sequence.length() - original.countIn(sequence);
}
@GwtIncompatible("java.util.BitSet")
@Override
void setBits(BitSet table) {
BitSet tmp = new BitSet();
original.setBits(tmp);
tmp.flip(Character.MIN_VALUE, Character.MAX_VALUE + 1);
table.or(tmp);
}
@Override public CharMatcher negate() {
return original;
}
@Override
CharMatcher withToString(String description) {
return new NegatedMatcher(description, original);
}
}
/**
* Returns a matcher that matches any character matched by both this matcher and {@code other}.
*/
public CharMatcher and(CharMatcher other) {
return new And(this, checkNotNull(other));
}
private static class And extends CharMatcher {
final CharMatcher first;
final CharMatcher second;
And(CharMatcher a, CharMatcher b) {
this(a, b, "CharMatcher.and(" + a + ", " + b + ")");
}
And(CharMatcher a, CharMatcher b, String description) {
super(description);
first = checkNotNull(a);
second = checkNotNull(b);
}
@Override
public boolean matches(char c) {
return first.matches(c) && second.matches(c);
}
@GwtIncompatible("java.util.BitSet")
@Override
void setBits(BitSet table) {
BitSet tmp1 = new BitSet();
first.setBits(tmp1);
BitSet tmp2 = new BitSet();
second.setBits(tmp2);
tmp1.and(tmp2);
table.or(tmp1);
}
@Override
CharMatcher withToString(String description) {
return new And(first, second, description);
}
}
/**
* Returns a matcher that matches any character matched by either this matcher or {@code other}.
*/
public CharMatcher or(CharMatcher other) {
return new Or(this, checkNotNull(other));
}
private static class Or extends CharMatcher {
final CharMatcher first;
final CharMatcher second;
Or(CharMatcher a, CharMatcher b, String description) {
super(description);
first = checkNotNull(a);
second = checkNotNull(b);
}
Or(CharMatcher a, CharMatcher b) {
this(a, b, "CharMatcher.or(" + a + ", " + b + ")");
}
@GwtIncompatible("java.util.BitSet")
@Override
void setBits(BitSet table) {
first.setBits(table);
second.setBits(table);
}
@Override
public boolean matches(char c) {
return first.matches(c) || second.matches(c);
}
@Override
CharMatcher withToString(String description) {
return new Or(first, second, description);
}
}
/**
* Returns a {@code char} matcher functionally equivalent to this one, but which may be faster to
* query than the original; your mileage may vary. Precomputation takes time and is likely to be
* worthwhile only if the precomputed matcher is queried many thousands of times.
*
* This method has no effect (returns {@code this}) when called in GWT: it's unclear whether a
* precomputed matcher is faster, but it certainly consumes more memory, which doesn't seem like a
* worthwhile tradeoff in a browser.
*/
public CharMatcher precomputed() {
return Platform.precomputeCharMatcher(this);
}
/**
* Subclasses should provide a new CharMatcher with the same characteristics as {@code this},
* but with their {@code toString} method overridden with the new description.
*
* This is unsupported by default.
*/
CharMatcher withToString(String description) {
throw new UnsupportedOperationException();
}
private static final int DISTINCT_CHARS = Character.MAX_VALUE - Character.MIN_VALUE + 1;
/**
* This is the actual implementation of {@link #precomputed}, but we bounce calls through a
* method on {@link Platform} so that we can have different behavior in GWT.
*
* This implementation tries to be smart in a number of ways. It recognizes cases where
* the negation is cheaper to precompute than the matcher itself; it tries to build small
* hash tables for matchers that only match a few characters, and so on. In the worst-case
* scenario, it constructs an eight-kilobyte bit array and queries that.
* In many situations this produces a matcher which is faster to query than the original.
*/
@GwtIncompatible("java.util.BitSet")
CharMatcher precomputedInternal() {
final BitSet table = new BitSet();
setBits(table);
int totalCharacters = table.cardinality();
if (totalCharacters * 2 <= DISTINCT_CHARS) {
return precomputedPositive(totalCharacters, table, description);
} else {
// TODO(user): is it worth it to worry about the last character of large matchers?
table.flip(Character.MIN_VALUE, Character.MAX_VALUE + 1);
int negatedCharacters = DISTINCT_CHARS - totalCharacters;
return new NegatedFastMatcher(toString(),
precomputedPositive(negatedCharacters, table, description + ".negate()"));
}
}
/**
* A matcher for which precomputation will not yield any significant benefit.
*/
abstract static class FastMatcher extends CharMatcher {
FastMatcher() {
super();
}
FastMatcher(String description) {
super(description);
}
@Override
public final CharMatcher precomputed() {
return this;
}
@Override
public CharMatcher negate() {
return new NegatedFastMatcher(this);
}
}
static final class NegatedFastMatcher extends NegatedMatcher {
NegatedFastMatcher(CharMatcher original) {
super(original);
}
NegatedFastMatcher(String toString, CharMatcher original) {
super(toString, original);
}
@Override
public final CharMatcher precomputed() {
return this;
}
@Override
CharMatcher withToString(String description) {
return new NegatedFastMatcher(description, original);
}
}
/**
* Helper method for {@link #precomputedInternal} that doesn't test if the negation is cheaper.
*/
@GwtIncompatible("java.util.BitSet")
private static CharMatcher precomputedPositive(
int totalCharacters,
BitSet table,
String description) {
switch (totalCharacters) {
case 0:
return NONE;
case 1:
return is((char) table.nextSetBit(0));
case 2:
char c1 = (char) table.nextSetBit(0);
char c2 = (char) table.nextSetBit(c1 + 1);
return isEither(c1, c2);
default:
return isSmall(totalCharacters, table.length())
? SmallCharMatcher.from(table, description)
: new BitSetMatcher(table, description);
}
}
private static boolean isSmall(int totalCharacters, int tableLength) {
return totalCharacters <= SmallCharMatcher.MAX_SIZE
&& tableLength > (totalCharacters * 4 * Character.SIZE);
// err on the side of BitSetMatcher
}
@GwtIncompatible("java.util.BitSet")
private static class BitSetMatcher extends FastMatcher {
private final BitSet table;
private BitSetMatcher(BitSet table, String description) {
super(description);
if (table.length() + Long.SIZE < table.size()) {
table = (BitSet) table.clone();
// If only we could actually call BitSet.trimToSize() ourselves...
}
this.table = table;
}
@Override public boolean matches(char c) {
return table.get(c);
}
@Override
void setBits(BitSet bitSet) {
bitSet.or(table);
}
}
/**
* Sets bits in {@code table} matched by this matcher.
*/
@GwtIncompatible("java.util.BitSet")
void setBits(BitSet table) {
for (int c = Character.MAX_VALUE; c >= Character.MIN_VALUE; c--) {
if (matches((char) c)) {
table.set(c);
}
}
}
// Text processing routines
/**
* Returns {@code true} if a character sequence contains at least one matching character.
* Equivalent to {@code !matchesNoneOf(sequence)}.
*
* The default implementation iterates over the sequence, invoking {@link #matches} for each
* character, until this returns {@code true} or the end is reached.
*
* @param sequence the character sequence to examine, possibly empty
* @return {@code true} if this matcher matches at least one character in the sequence
* @since 8.0
*/
public boolean matchesAnyOf(CharSequence sequence) {
return !matchesNoneOf(sequence);
}
/**
* Returns {@code true} if a character sequence contains only matching characters.
*
* The default implementation iterates over the sequence, invoking {@link #matches} for each
* character, until this returns {@code false} or the end is reached.
*
* @param sequence the character sequence to examine, possibly empty
* @return {@code true} if this matcher matches every character in the sequence, including when
* the sequence is empty
*/
public boolean matchesAllOf(CharSequence sequence) {
for (int i = sequence.length() - 1; i >= 0; i--) {
if (!matches(sequence.charAt(i))) {
return false;
}
}
return true;
}
/**
* Returns {@code true} if a character sequence contains no matching characters. Equivalent to
* {@code !matchesAnyOf(sequence)}.
*
* The default implementation iterates over the sequence, invoking {@link #matches} for each
* character, until this returns {@code false} or the end is reached.
*
* @param sequence the character sequence to examine, possibly empty
* @return {@code true} if this matcher matches every character in the sequence, including when
* the sequence is empty
*/
public boolean matchesNoneOf(CharSequence sequence) {
return indexIn(sequence) == -1;
}
/**
* Returns the index of the first matching character in a character sequence, or {@code -1} if no
* matching character is present.
*
* The default implementation iterates over the sequence in forward order calling {@link
* #matches} for each character.
*
* @param sequence the character sequence to examine from the beginning
* @return an index, or {@code -1} if no character matches
*/
public int indexIn(CharSequence sequence) {
int length = sequence.length();
for (int i = 0; i < length; i++) {
if (matches(sequence.charAt(i))) {
return i;
}
}
return -1;
}
/**
* Returns the index of the first matching character in a character sequence, starting from a
* given position, or {@code -1} if no character matches after that position.
*
* The default implementation iterates over the sequence in forward order, beginning at {@code
* start}, calling {@link #matches} for each character.
*
* @param sequence the character sequence to examine
* @param start the first index to examine; must be nonnegative and no greater than {@code
* sequence.length()}
* @return the index of the first matching character, guaranteed to be no less than {@code start},
* or {@code -1} if no character matches
* @throws IndexOutOfBoundsException if start is negative or greater than {@code
* sequence.length()}
*/
public int indexIn(CharSequence sequence, int start) {
int length = sequence.length();
Preconditions.checkPositionIndex(start, length);
for (int i = start; i < length; i++) {
if (matches(sequence.charAt(i))) {
return i;
}
}
return -1;
}
/**
* Returns the index of the last matching character in a character sequence, or {@code -1} if no
* matching character is present.
*
* The default implementation iterates over the sequence in reverse order calling {@link
* #matches} for each character.
*
* @param sequence the character sequence to examine from the end
* @return an index, or {@code -1} if no character matches
*/
public int lastIndexIn(CharSequence sequence) {
for (int i = sequence.length() - 1; i >= 0; i--) {
if (matches(sequence.charAt(i))) {
return i;
}
}
return -1;
}
/**
* Returns the number of matching characters found in a character sequence.
*/
public int countIn(CharSequence sequence) {
int count = 0;
for (int i = 0; i < sequence.length(); i++) {
if (matches(sequence.charAt(i))) {
count++;
}
}
return count;
}
/**
* Returns a string containing all non-matching characters of a character sequence, in order. For
* example: The default implementation uses {@link #indexIn(CharSequence)} to find the first matching
* character, then iterates the remainder of the sequence calling {@link #matches(char)} for each
* character.
*
* @param sequence the character sequence to replace matching characters in
* @param replacement the character to append to the result string in place of each matching
* character in {@code sequence}
* @return the new string
*/
@CheckReturnValue
public String replaceFrom(CharSequence sequence, char replacement) {
String string = sequence.toString();
int pos = indexIn(string);
if (pos == -1) {
return string;
}
char[] chars = string.toCharArray();
chars[pos] = replacement;
for (int i = pos + 1; i < chars.length; i++) {
if (matches(chars[i])) {
chars[i] = replacement;
}
}
return new String(chars);
}
/**
* Returns a string copy of the input character sequence, with each character that matches this
* matcher replaced by a given replacement sequence. For example: Note: If the replacement is a fixed string with only one character, you are better
* off calling {@link #replaceFrom(CharSequence, char)} directly.
*
* @param sequence the character sequence to replace matching characters in
* @param replacement the characters to append to the result string in place of each matching
* character in {@code sequence}
* @return the new string
*/
@CheckReturnValue
public String replaceFrom(CharSequence sequence, CharSequence replacement) {
int replacementLen = replacement.length();
if (replacementLen == 0) {
return removeFrom(sequence);
}
if (replacementLen == 1) {
return replaceFrom(sequence, replacement.charAt(0));
}
String string = sequence.toString();
int pos = indexIn(string);
if (pos == -1) {
return string;
}
int len = string.length();
StringBuilder buf = new StringBuilder((len * 3 / 2) + 16);
int oldpos = 0;
do {
buf.append(string, oldpos, pos);
buf.append(replacement);
oldpos = pos + 1;
pos = indexIn(string, oldpos);
} while (pos != -1);
buf.append(string, oldpos, len);
return buf.toString();
}
/**
* Returns a substring of the input character sequence that omits all characters this matcher
* matches from the beginning and from the end of the string. For example: Note that: The default implementation uses {@link #indexIn(CharSequence)} to find the first matching
* character, then iterates the remainder of the sequence calling {@link #matches(char)} for each
* character.
*
* @param sequence the character sequence to replace matching groups of characters in
* @param replacement the character to append to the result string in place of each group of
* matching characters in {@code sequence}
* @return the new string
*/
@CheckReturnValue
public String collapseFrom(CharSequence sequence, char replacement) {
// This implementation avoids unnecessary allocation.
int len = sequence.length();
for (int i = 0; i < len; i++) {
char c = sequence.charAt(i);
if (matches(c)) {
if (c == replacement
&& (i == len - 1 || !matches(sequence.charAt(i + 1)))) {
// a no-op replacement
i++;
} else {
StringBuilder builder = new StringBuilder(len)
.append(sequence.subSequence(0, i))
.append(replacement);
return finishCollapseFrom(sequence, i + 1, len, replacement, builder, true);
}
}
}
// no replacement needed
return sequence.toString();
}
/**
* Collapses groups of matching characters exactly as {@link #collapseFrom} does, except that
* groups of matching characters at the start or end of the sequence are removed without
* replacement.
*/
@CheckReturnValue
public String trimAndCollapseFrom(CharSequence sequence, char replacement) {
// This implementation avoids unnecessary allocation.
int len = sequence.length();
int first;
int last;
for (first = 0; first < len && matches(sequence.charAt(first)); first++) {}
for (last = len - 1; last > first && matches(sequence.charAt(last)); last--) {}
return (first == 0 && last == len - 1)
? collapseFrom(sequence, replacement)
: finishCollapseFrom(
sequence, first, last + 1, replacement,
new StringBuilder(last + 1 - first),
false);
}
private String finishCollapseFrom(
CharSequence sequence, int start, int end, char replacement,
StringBuilder builder, boolean inMatchingGroup) {
for (int i = start; i < end; i++) {
char c = sequence.charAt(i);
if (matches(c)) {
if (!inMatchingGroup) {
builder.append(replacement);
inMatchingGroup = true;
}
} else {
builder.append(c);
inMatchingGroup = false;
}
}
return builder.toString();
}
// Predicate interface
/**
* Equivalent to {@link #matches}; provided only to satisfy the {@link Predicate} interface. When
* using a reference of type {@code CharMatcher}, invoke {@link #matches} directly instead.
*/
@Override public boolean apply(Character character) {
return matches(character);
}
/**
* Returns a string representation of this {@code CharMatcher}, such as
* {@code CharMatcher.or(WHITESPACE, JAVA_DIGIT)}.
*/
@Override
public String toString() {
return description;
}
/**
* A special-case CharMatcher for Unicode whitespace characters that is extremely
* efficient both in space required and in time to check for matches.
*
* Implementation details.
* It turns out that all current (early 2012) Unicode characters are unique modulo 79:
* so we can construct a lookup table of exactly 79 entries, and just check the character code
* mod 79, and see if that character is in the table.
*
* There is a 1 at the beginning of the table so that the null character is not listed
* as whitespace.
*
* Other things we tried that did not prove to be beneficial, mostly due to speed concerns:
*
* * Binary search into the sorted list of characters, i.e., what
* CharMatcher.anyOf() does
* * Perfect hash function into a table of size 26 (using an offset table and a special
* Jenkins hash function)
* * Perfect-ish hash function that required two lookups into a single table of size 26.
* * Using a power-of-2 sized hash table (size 64) with linear probing.
*
* --Christopher Swenson, February 2012.
*/
private static final String WHITESPACE_TABLE = "\u0001\u0000\u00a0\u0000\u0000\u0000\u0000\u0000"
+ "\u0000\u0009\n\u000b\u000c\r\u0000\u0000\u2028\u2029\u0000\u0000\u0000\u0000\u0000\u202f"
+ "\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0020\u0000\u0000\u0000\u0000\u0000"
+ "\u0000\u0000\u0000\u0000\u0000\u3000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000"
+ "\u0000\u0000\u0085\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200a"
+ "\u0000\u0000\u0000\u0000\u0000\u205f\u1680\u0000\u0000\u180e\u0000\u0000\u0000";
/**
* Determines whether a character is whitespace according to the latest Unicode standard, as
* illustrated
* here.
* This is not the same definition used by other Java APIs. (See a
* comparison of several
* definitions of "whitespace".)
*
* Note: as the Unicode definition evolves, we will modify this constant to keep it up
* to date.
*/
public static final CharMatcher WHITESPACE = new FastMatcher("CharMatcher.WHITESPACE") {
@Override public boolean matches(char c) {
return WHITESPACE_TABLE.charAt(c % 79) == c;
}
};
}
{@code
*
* CharMatcher.is('a').removeFrom("bazaar")}
*
* ... returns {@code "bzr"}.
*/
@CheckReturnValue
public String removeFrom(CharSequence sequence) {
String string = sequence.toString();
int pos = indexIn(string);
if (pos == -1) {
return string;
}
char[] chars = string.toCharArray();
int spread = 1;
// This unusual loop comes from extensive benchmarking
OUT: while (true) {
pos++;
while (true) {
if (pos == chars.length) {
break OUT;
}
if (matches(chars[pos])) {
break;
}
chars[pos - spread] = chars[pos];
pos++;
}
spread++;
}
return new String(chars, 0, pos - spread);
}
/**
* Returns a string containing all matching characters of a character sequence, in order. For
* example: {@code
*
* CharMatcher.is('a').retainFrom("bazaar")}
*
* ... returns {@code "aaa"}.
*/
@CheckReturnValue
public String retainFrom(CharSequence sequence) {
return negate().removeFrom(sequence);
}
/**
* Returns a string copy of the input character sequence, with each character that matches this
* matcher replaced by a given replacement character. For example: {@code
*
* CharMatcher.is('a').replaceFrom("radar", 'o')}
*
* ... returns {@code "rodor"}.
*
* {@code
*
* CharMatcher.is('a').replaceFrom("yaha", "oo")}
*
* ... returns {@code "yoohoo"}.
*
* {@code
*
* CharMatcher.anyOf("ab").trimFrom("abacatbab")}
*
* ... returns {@code "cat"}.
*
* {@code
*
* CharMatcher.inRange('\0', ' ').trimFrom(str)}
*
* ... is equivalent to {@link String#trim()}.
*/
@CheckReturnValue
public String trimFrom(CharSequence sequence) {
int len = sequence.length();
int first;
int last;
for (first = 0; first < len; first++) {
if (!matches(sequence.charAt(first))) {
break;
}
}
for (last = len - 1; last > first; last--) {
if (!matches(sequence.charAt(last))) {
break;
}
}
return sequence.subSequence(first, last + 1).toString();
}
/**
* Returns a substring of the input character sequence that omits all characters this matcher
* matches from the beginning of the string. For example: {@code
*
* CharMatcher.anyOf("ab").trimLeadingFrom("abacatbab")}
*
* ... returns {@code "catbab"}.
*/
@CheckReturnValue
public String trimLeadingFrom(CharSequence sequence) {
int len = sequence.length();
for (int first = 0; first < len; first++) {
if (!matches(sequence.charAt(first))) {
return sequence.subSequence(first, len).toString();
}
}
return "";
}
/**
* Returns a substring of the input character sequence that omits all characters this matcher
* matches from the end of the string. For example: {@code
*
* CharMatcher.anyOf("ab").trimTrailingFrom("abacatbab")}
*
* ... returns {@code "abacat"}.
*/
@CheckReturnValue
public String trimTrailingFrom(CharSequence sequence) {
int len = sequence.length();
for (int last = len - 1; last >= 0; last--) {
if (!matches(sequence.charAt(last))) {
return sequence.subSequence(0, last + 1).toString();
}
}
return "";
}
/**
* Returns a string copy of the input character sequence, with each group of consecutive
* characters that match this matcher replaced by a single replacement character. For example:
* {@code
*
* CharMatcher.anyOf("eko").collapseFrom("bookkeeper", '-')}
*
* ... returns {@code "b-p-r"}.
*
*