String
2020-08-29 本文已影响0人
虾米咬小米
String UML类图
image.png
String 被 final 修饰，String 类不可被继承，不可变类。
public final class String
implements java.io.Serializable, Comparable<String>, CharSequence {
}
String 类的构造方法：
/** The value is used for character storage. */
private final char value[];
/** Cache the hash code for the string */
private int hash; // Default to 0
/** use serialVersionUID from JDK 1.0.2 for interoperability */
private static final long serialVersionUID = -6849794470754667710L;
/**
* Class String is special cased within the Serialization Stream Protocol.
*
* A String instance is written into an ObjectOutputStream according to
* <a href="{@docRoot}/../platform/serialization/spec/output.html">
* Object Serialization Specification, Section 6.2, "Stream Elements"</a>
*/
private static final ObjectStreamField[] serialPersistentFields =
new ObjectStreamField[0];
/**
* Initializes a newly created {@code String} object so that it represents
* an empty character sequence. Note that use of this constructor is
* unnecessary since Strings are immutable.
*/
public String() {
this.value = "".value;
}
/**
* Initializes a newly created {@code String} object so that it represents
* the same sequence of characters as the argument; in other words, the
* newly created string is a copy of the argument string. Unless an
* explicit copy of {@code original} is needed, use of this constructor is
* unnecessary since Strings are immutable.
*
* @param original
* A {@code String}
*/
public String(String original) {
this.value = original.value;
this.hash = original.hash;
}
/**
* Allocates a new {@code String} so that it represents the sequence of
* characters currently contained in the character array argument. The
* contents of the character array are copied; subsequent modification of
* the character array does not affect the newly created string.
*
* @param value
* The initial value of the string
*/
public String(char value[]) {
this.value = Arrays.copyOf(value, value.length);
}
/**
* Allocates a new {@code String} that contains characters from a subarray
* of the character array argument. The {@code offset} argument is the
* index of the first character of the subarray and the {@code count}
* argument specifies the length of the subarray. The contents of the
* subarray are copied; subsequent modification of the character array does
* not affect the newly created string.
*
* @param value
* Array that is the source of characters
*
* @param offset
* The initial offset
*
* @param count
* The length
*
* @throws IndexOutOfBoundsException
* If the {@code offset} and {@code count} arguments index
* characters outside the bounds of the {@code value} array
*/
public String(char value[], int offset, int count) {
if (offset < 0) {
throw new StringIndexOutOfBoundsException(offset);
}
if (count <= 0) {
if (count < 0) {
throw new StringIndexOutOfBoundsException(count);
}
if (offset <= value.length) {
this.value = "".value;
return;
}
}
// Note: offset or count might be near -1>>>1.
if (offset > value.length - count) {
throw new StringIndexOutOfBoundsException(offset + count);
}
this.value = Arrays.copyOfRange(value, offset, offset+count);
}
/**
* Allocates a new {@code String} that contains characters from a subarray
* of the <a href="Character.html#unicode">Unicode code point</a> array
* argument. The {@code offset} argument is the index of the first code
* point of the subarray and the {@code count} argument specifies the
* length of the subarray. The contents of the subarray are converted to
* {@code char}s; subsequent modification of the {@code int} array does not
* affect the newly created string.
*
* @param codePoints
* Array that is the source of Unicode code points
*
* @param offset
* The initial offset
*
* @param count
* The length
*
* @throws IllegalArgumentException
* If any invalid Unicode code point is found in {@code
* codePoints}
*
* @throws IndexOutOfBoundsException
* If the {@code offset} and {@code count} arguments index
* characters outside the bounds of the {@code codePoints} array
*
* @since 1.5
*/
public String(int[] codePoints, int offset, int count) {
if (offset < 0) {
throw new StringIndexOutOfBoundsException(offset);
}
if (count <= 0) {
if (count < 0) {
throw new StringIndexOutOfBoundsException(count);
}
if (offset <= codePoints.length) {
this.value = "".value;
return;
}
}
// Note: offset or count might be near -1>>>1.
if (offset > codePoints.length - count) {
throw new StringIndexOutOfBoundsException(offset + count);
}
final int end = offset + count;
// Pass 1: Compute precise size of char[]
int n = count;
for (int i = offset; i < end; i++) {
int c = codePoints[i];
if (Character.isBmpCodePoint(c))
continue;
else if (Character.isValidCodePoint(c))
n++;
else throw new IllegalArgumentException(Integer.toString(c));
}
// Pass 2: Allocate and fill in char[]
final char[] v = new char[n];
for (int i = offset, j = 0; i < end; i++, j++) {
int c = codePoints[i];
if (Character.isBmpCodePoint(c))
v[j] = (char)c;
else
Character.toSurrogates(c, v, j++);
}
this.value = v;
}
/**
* Allocates a new {@code String} constructed from a subarray of an array
* of 8-bit integer values.
*
* <p> The {@code offset} argument is the index of the first byte of the
* subarray, and the {@code count} argument specifies the length of the
* subarray.
*
* <p> Each {@code byte} in the subarray is converted to a {@code char} as
* specified in the method above.
*
* @deprecated This method does not properly convert bytes into characters.
* As of JDK 1.1, the preferred way to do this is via the
* {@code String} constructors that take a {@link
* java.nio.charset.Charset}, charset name, or that use the platform's
* default charset.
*
* @param ascii
* The bytes to be converted to characters
*
* @param hibyte
* The top 8 bits of each 16-bit Unicode code unit
*
* @param offset
* The initial offset
* @param count
* The length
*
* @throws IndexOutOfBoundsException
* If the {@code offset} or {@code count} argument is invalid
*
* @see #String(byte[], int)
* @see #String(byte[], int, int, java.lang.String)
* @see #String(byte[], int, int, java.nio.charset.Charset)
* @see #String(byte[], int, int)
* @see #String(byte[], java.lang.String)
* @see #String(byte[], java.nio.charset.Charset)
* @see #String(byte[])
*/
@Deprecated
public String(byte ascii[], int hibyte, int offset, int count) {
checkBounds(ascii, offset, count);
char value[] = new char[count];
if (hibyte == 0) {
for (int i = count; i-- > 0;) {
value[i] = (char)(ascii[i + offset] & 0xff);
}
} else {
hibyte <<= 8;
for (int i = count; i-- > 0;) {
value[i] = (char)(hibyte | (ascii[i + offset] & 0xff));
}
}
this.value = value;
}
/**
* Allocates a new {@code String} containing characters constructed from
* an array of 8-bit integer values. Each character <i>c</i>in the
* resulting string is constructed from the corresponding component
* <i>b</i> in the byte array such that:
*
* <blockquote><pre>
* <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
* | (<b><i>b</i></b> & 0xff))
* </pre></blockquote>
*
* @deprecated This method does not properly convert bytes into
* characters. As of JDK 1.1, the preferred way to do this is via the
* {@code String} constructors that take a {@link
* java.nio.charset.Charset}, charset name, or that use the platform's
* default charset.
*
* @param ascii
* The bytes to be converted to characters
*
* @param hibyte
* The top 8 bits of each 16-bit Unicode code unit
*
* @see #String(byte[], int, int, java.lang.String)
* @see #String(byte[], int, int, java.nio.charset.Charset)
* @see #String(byte[], int, int)
* @see #String(byte[], java.lang.String)
* @see #String(byte[], java.nio.charset.Charset)
* @see #String(byte[])
*/
@Deprecated
public String(byte ascii[], int hibyte) {
this(ascii, hibyte, 0, ascii.length);
}
/* Common private utility method used to bounds check the byte array
* and requested offset & length values used by the String(byte[],..)
* constructors.
*/
private static void checkBounds(byte[] bytes, int offset, int length) {
if (length < 0)
throw new StringIndexOutOfBoundsException(length);
if (offset < 0)
throw new StringIndexOutOfBoundsException(offset);
if (offset > bytes.length - length)
throw new StringIndexOutOfBoundsException(offset + length);
}
/**
* Constructs a new {@code String} by decoding the specified subarray of
* bytes using the specified charset. The length of the new {@code String}
* is a function of the charset, and hence may not be equal to the length
* of the subarray.
*
* <p> The behavior of this constructor when the given bytes are not valid
* in the given charset is unspecified. The {@link
* java.nio.charset.CharsetDecoder} class should be used when more control
* over the decoding process is required.
*
* @param bytes
* The bytes to be decoded into characters
*
* @param offset
* The index of the first byte to decode
*
* @param length
* The number of bytes to decode
* @param charsetName
* The name of a supported {@linkplain java.nio.charset.Charset
* charset}
*
* @throws UnsupportedEncodingException
* If the named charset is not supported
*
* @throws IndexOutOfBoundsException
* If the {@code offset} and {@code length} arguments index
* characters outside the bounds of the {@code bytes} array
*
* @since JDK1.1
*/
public String(byte bytes[], int offset, int length, String charsetName)
throws UnsupportedEncodingException {
if (charsetName == null)
throw new NullPointerException("charsetName");
checkBounds(bytes, offset, length);
this.value = StringCoding.decode(charsetName, bytes, offset, length);
}
/**
* Constructs a new {@code String} by decoding the specified subarray of
* bytes using the specified {@linkplain java.nio.charset.Charset charset}.
* The length of the new {@code String} is a function of the charset, and
* hence may not be equal to the length of the subarray.
*
* <p> This method always replaces malformed-input and unmappable-character
* sequences with this charset's default replacement string. The {@link
* java.nio.charset.CharsetDecoder} class should be used when more control
* over the decoding process is required.
*
* @param bytes
* The bytes to be decoded into characters
*
* @param offset
* The index of the first byte to decode
*
* @param length
* The number of bytes to decode
*
* @param charset
* The {@linkplain java.nio.charset.Charset charset} to be used to
* decode the {@code bytes}
*
* @throws IndexOutOfBoundsException
* If the {@code offset} and {@code length} arguments index
* characters outside the bounds of the {@code bytes} array
*
* @since 1.6
*/
public String(byte bytes[], int offset, int length, Charset charset) {
if (charset == null)
throw new NullPointerException("charset");
checkBounds(bytes, offset, length);
this.value = StringCoding.decode(charset, bytes, offset, length);
}
/**
* Constructs a new {@code String} by decoding the specified array of bytes
* using the specified {@linkplain java.nio.charset.Charset charset}. The
* length of the new {@code String} is a function of the charset, and hence
* may not be equal to the length of the byte array.
*
* <p> The behavior of this constructor when the given bytes are not valid
* in the given charset is unspecified. The {@link
* java.nio.charset.CharsetDecoder} class should be used when more control
* over the decoding process is required.
*
* @param bytes
* The bytes to be decoded into characters
*
* @param charsetName
* The name of a supported {@linkplain java.nio.charset.Charset
* charset}
*
* @throws UnsupportedEncodingException
* If the named charset is not supported
*
* @since JDK1.1
*/
public String(byte bytes[], String charsetName)
throws UnsupportedEncodingException {
this(bytes, 0, bytes.length, charsetName);
}
/**
* Constructs a new {@code String} by decoding the specified array of
* bytes using the specified {@linkplain java.nio.charset.Charset charset}.
* The length of the new {@code String} is a function of the charset, and
* hence may not be equal to the length of the byte array.
*
* <p> This method always replaces malformed-input and unmappable-character
* sequences with this charset's default replacement string. The {@link
* java.nio.charset.CharsetDecoder} class should be used when more control
* over the decoding process is required.
*
* @param bytes
* The bytes to be decoded into characters
*
* @param charset
* The {@linkplain java.nio.charset.Charset charset} to be used to
* decode the {@code bytes}
*
* @since 1.6
*/
public String(byte bytes[], Charset charset) {
this(bytes, 0, bytes.length, charset);
}
/**
* Constructs a new {@code String} by decoding the specified subarray of
* bytes using the platform's default charset. The length of the new
* {@code String} is a function of the charset, and hence may not be equal
* to the length of the subarray.
*
* <p> The behavior of this constructor when the given bytes are not valid
* in the default charset is unspecified. The {@link
* java.nio.charset.CharsetDecoder} class should be used when more control
* over the decoding process is required.
*
* @param bytes
* The bytes to be decoded into characters
*
* @param offset
* The index of the first byte to decode
*
* @param length
* The number of bytes to decode
*
* @throws IndexOutOfBoundsException
* If the {@code offset} and the {@code length} arguments index
* characters outside the bounds of the {@code bytes} array
*
* @since JDK1.1
*/
public String(byte bytes[], int offset, int length) {
checkBounds(bytes, offset, length);
this.value = StringCoding.decode(bytes, offset, length);
}
/**
* Constructs a new {@code String} by decoding the specified array of bytes
* using the platform's default charset. The length of the new {@code
* String} is a function of the charset, and hence may not be equal to the
* length of the byte array.
*
* <p> The behavior of this constructor when the given bytes are not valid
* in the default charset is unspecified. The {@link
* java.nio.charset.CharsetDecoder} class should be used when more control
* over the decoding process is required.
*
* @param bytes
* The bytes to be decoded into characters
*
* @since JDK1.1
*/
public String(byte bytes[]) {
this(bytes, 0, bytes.length);
}
/**
* Allocates a new string that contains the sequence of characters
* currently contained in the string buffer argument. The contents of the
* string buffer are copied; subsequent modification of the string buffer
* does not affect the newly created string.
*
* @param buffer
* A {@code StringBuffer}
*/
public String(StringBuffer buffer) {
synchronized(buffer) {
this.value = Arrays.copyOf(buffer.getValue(), buffer.length());
}
}
/**
* Allocates a new string that contains the sequence of characters
* currently contained in the string builder argument. The contents of the
* string builder are copied; subsequent modification of the string builder
* does not affect the newly created string.
*
* <p> This constructor is provided to ease migration to {@code
* StringBuilder}. Obtaining a string from a string builder via the {@code
* toString} method is likely to run faster and is generally preferred.
*
* @param builder
* A {@code StringBuilder}
*
* @since 1.5
*/
public String(StringBuilder builder) {
this.value = Arrays.copyOf(builder.getValue(), builder.length());
}
/*
* Package private constructor which shares value array for speed.
* this constructor is always expected to be called with share==true.
* a separate constructor is needed because we already have a public
* String(char[]) constructor that makes a copy of the given char[].
*/
String(char[] value, boolean share) {
// assert share : "unshared not supported";
this.value = value;
}
String 类的成员方法
/**
* Returns the length of this string.
* The length is equal to the number of <a href="Character.html#unicode">Unicode
* code units</a> in the string.
*
* @return the length of the sequence of characters represented by this
* object.
*/
public int length() {
return value.length;
}
/**
* Returns {@code true} if, and only if, {@link #length()} is {@code 0}.
*
* @return {@code true} if {@link #length()} is {@code 0}, otherwise
* {@code false}
*
* @since 1.6
*/
public boolean isEmpty() {
return value.length == 0;
}
/**
* Returns the {@code char} value at the
* specified index. An index ranges from {@code 0} to
* {@code length() - 1}. The first {@code char} value of the sequence
* is at index {@code 0}, the next at index {@code 1},
* and so on, as for array indexing.
*
* <p>If the {@code char} value specified by the index is a
* <a href="Character.html#unicode">surrogate</a>, the surrogate
* value is returned.
*
* @param index the index of the {@code char} value.
* @return the {@code char} value at the specified index of this string.
* The first {@code char} value is at index {@code 0}.
* @exception IndexOutOfBoundsException if the {@code index}
* argument is negative or not less than the length of this
* string.
*/
public char charAt(int index) {
if ((index < 0) || (index >= value.length)) {
throw new StringIndexOutOfBoundsException(index);
}
return value[index];
}
/**
* Returns the character (Unicode code point) at the specified
* index. The index refers to {@code char} values
* (Unicode code units) and ranges from {@code 0} to
* {@link #length()}{@code - 1}.
*
* <p> If the {@code char} value specified at the given index
* is in the high-surrogate range, the following index is less
* than the length of this {@code String}, and the
* {@code char} value at the following index is in the
* low-surrogate range, then the supplementary code point
* corresponding to this surrogate pair is returned. Otherwise,
* the {@code char} value at the given index is returned.
*
* @param index the index to the {@code char} values
* @return the code point value of the character at the
* {@code index}
* @exception IndexOutOfBoundsException if the {@code index}
* argument is negative or not less than the length of this
* string.
* @since 1.5
*/
public int codePointAt(int index) {
if ((index < 0) || (index >= value.length)) {
throw new StringIndexOutOfBoundsException(index);
}
return Character.codePointAtImpl(value, index, value.length);
}
/**
* Returns the character (Unicode code point) before the specified
* index. The index refers to {@code char} values
* (Unicode code units) and ranges from {@code 1} to {@link
* CharSequence#length() length}.
*
* <p> If the {@code char} value at {@code (index - 1)}
* is in the low-surrogate range, {@code (index - 2)} is not
* negative, and the {@code char} value at {@code (index -
* 2)} is in the high-surrogate range, then the
* supplementary code point value of the surrogate pair is
* returned. If the {@code char} value at {@code index -
* 1} is an unpaired low-surrogate or a high-surrogate, the
* surrogate value is returned.
*
* @param index the index following the code point that should be returned
* @return the Unicode code point value before the given index.
* @exception IndexOutOfBoundsException if the {@code index}
* argument is less than 1 or greater than the length
* of this string.
* @since 1.5
*/
public int codePointBefore(int index) {
int i = index - 1;
if ((i < 0) || (i >= value.length)) {
throw new StringIndexOutOfBoundsException(index);
}
return Character.codePointBeforeImpl(value, index, 0);
}
/**
* Returns the number of Unicode code points in the specified text
* range of this {@code String}. The text range begins at the
* specified {@code beginIndex} and extends to the
* {@code char} at index {@code endIndex - 1}. Thus the
* length (in {@code char}s) of the text range is
* {@code endIndex-beginIndex}. Unpaired surrogates within
* the text range count as one code point each.
*
* @param beginIndex the index to the first {@code char} of
* the text range.
* @param endIndex the index after the last {@code char} of
* the text range.
* @return the number of Unicode code points in the specified text
* range
* @exception IndexOutOfBoundsException if the
* {@code beginIndex} is negative, or {@code endIndex}
* is larger than the length of this {@code String}, or
* {@code beginIndex} is larger than {@code endIndex}.
* @since 1.5
*/
public int codePointCount(int beginIndex, int endIndex) {
if (beginIndex < 0 || endIndex > value.length || beginIndex > endIndex) {
throw new IndexOutOfBoundsException();
}
return Character.codePointCountImpl(value, beginIndex, endIndex - beginIndex);
}
/**
* Returns the index within this {@code String} that is
* offset from the given {@code index} by
* {@code codePointOffset} code points. Unpaired surrogates
* within the text range given by {@code index} and
* {@code codePointOffset} count as one code point each.
*
* @param index the index to be offset
* @param codePointOffset the offset in code points
* @return the index within this {@code String}
* @exception IndexOutOfBoundsException if {@code index}
* is negative or larger then the length of this
* {@code String}, or if {@code codePointOffset} is positive
* and the substring starting with {@code index} has fewer
* than {@code codePointOffset} code points,
* or if {@code codePointOffset} is negative and the substring
* before {@code index} has fewer than the absolute value
* of {@code codePointOffset} code points.
* @since 1.5
*/
public int offsetByCodePoints(int index, int codePointOffset) {
if (index < 0 || index > value.length) {
throw new IndexOutOfBoundsException();
}
return Character.offsetByCodePointsImpl(value, 0, value.length,
index, codePointOffset);
}
/**
* Copy characters from this string into dst starting at dstBegin.
* This method doesn't perform any range checking.
*/
void getChars(char dst[], int dstBegin) {
System.arraycopy(value, 0, dst, dstBegin, value.length);
}
/**
* Copies characters from this string into the destination character
* array.
* <p>
* The first character to be copied is at index {@code srcBegin};
* the last character to be copied is at index {@code srcEnd-1}
* (thus the total number of characters to be copied is
* {@code srcEnd-srcBegin}). The characters are copied into the
* subarray of {@code dst} starting at index {@code dstBegin}
* and ending at index:
* <blockquote><pre>
* dstBegin + (srcEnd-srcBegin) - 1
* </pre></blockquote>
*
* @param srcBegin index of the first character in the string
* to copy.
* @param srcEnd index after the last character in the string
* to copy.
* @param dst the destination array.
* @param dstBegin the start offset in the destination array.
* @exception IndexOutOfBoundsException If any of the following
* is true:
* <ul><li>{@code srcBegin} is negative.
* <li>{@code srcBegin} is greater than {@code srcEnd}
* <li>{@code srcEnd} is greater than the length of this
* string
* <li>{@code dstBegin} is negative
* <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than
* {@code dst.length}</ul>
*/
public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
if (srcBegin < 0) {
throw new StringIndexOutOfBoundsException(srcBegin);
}
if (srcEnd > value.length) {
throw new StringIndexOutOfBoundsException(srcEnd);
}
if (srcBegin > srcEnd) {
throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
}
System.arraycopy(value, srcBegin, dst, dstBegin, srcEnd - srcBegin);
}
/**
* Copies characters from this string into the destination byte array. Each
* byte receives the 8 low-order bits of the corresponding character. The
* eight high-order bits of each character are not copied and do not
* participate in the transfer in any way.
*
* <p> The first character to be copied is at index {@code srcBegin}; the
* last character to be copied is at index {@code srcEnd-1}. The total
* number of characters to be copied is {@code srcEnd-srcBegin}. The
* characters, converted to bytes, are copied into the subarray of {@code
* dst} starting at index {@code dstBegin} and ending at index:
*
* <blockquote><pre>
* dstBegin + (srcEnd-srcBegin) - 1
* </pre></blockquote>
*
* @deprecated This method does not properly convert characters into
* bytes. As of JDK 1.1, the preferred way to do this is via the
* {@link #getBytes()} method, which uses the platform's default charset.
*
* @param srcBegin
* Index of the first character in the string to copy
*
* @param srcEnd
* Index after the last character in the string to copy
*
* @param dst
* The destination array
*
* @param dstBegin
* The start offset in the destination array
*
* @throws IndexOutOfBoundsException
* If any of the following is true:
* <ul>
* <li> {@code srcBegin} is negative
* <li> {@code srcBegin} is greater than {@code srcEnd}
* <li> {@code srcEnd} is greater than the length of this String
* <li> {@code dstBegin} is negative
* <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
* dst.length}
* </ul>
*/
@Deprecated
public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
if (srcBegin < 0) {
throw new StringIndexOutOfBoundsException(srcBegin);
}
if (srcEnd > value.length) {
throw new StringIndexOutOfBoundsException(srcEnd);
}
if (srcBegin > srcEnd) {
throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
}
Objects.requireNonNull(dst);
int j = dstBegin;
int n = srcEnd;
int i = srcBegin;
char[] val = value; /* avoid getfield opcode */
while (i < n) {
dst[j++] = (byte)val[i++];
}
}
/**
* Encodes this {@code String} into a sequence of bytes using the named
* charset, storing the result into a new byte array.
*
* <p> The behavior of this method when this string cannot be encoded in
* the given charset is unspecified. The {@link
* java.nio.charset.CharsetEncoder} class should be used when more control
* over the encoding process is required.
*
* @param charsetName
* The name of a supported {@linkplain java.nio.charset.Charset
* charset}
*
* @return The resultant byte array
*
* @throws UnsupportedEncodingException
* If the named charset is not supported
*
* @since JDK1.1
*/
public byte[] getBytes(String charsetName)
throws UnsupportedEncodingException {
if (charsetName == null) throw new NullPointerException();
return StringCoding.encode(charsetName, value, 0, value.length);
}
/**
* Encodes this {@code String} into a sequence of bytes using the given
* {@linkplain java.nio.charset.Charset charset}, storing the result into a
* new byte array.
*
* <p> This method always replaces malformed-input and unmappable-character
* sequences with this charset's default replacement byte array. The
* {@link java.nio.charset.CharsetEncoder} class should be used when more
* control over the encoding process is required.
*
* @param charset
* The {@linkplain java.nio.charset.Charset} to be used to encode
* the {@code String}
*
* @return The resultant byte array
*
* @since 1.6
*/
public byte[] getBytes(Charset charset) {
if (charset == null) throw new NullPointerException();
return StringCoding.encode(charset, value, 0, value.length);
}
/**
* Encodes this {@code String} into a sequence of bytes using the
* platform's default charset, storing the result into a new byte array.
*
* <p> The behavior of this method when this string cannot be encoded in
* the default charset is unspecified. The {@link
* java.nio.charset.CharsetEncoder} class should be used when more control
* over the encoding process is required.
*
* @return The resultant byte array
*
* @since JDK1.1
*/
public byte[] getBytes() {
return StringCoding.encode(value, 0, value.length);
}
/**
* Compares this string to the specified object. The result is {@code
* true} if and only if the argument is not {@code null} and is a {@code
* String} object that represents the same sequence of characters as this
* object.
*
* @param anObject
* The object to compare this {@code String} against
*
* @return {@code true} if the given object represents a {@code String}
* equivalent to this string, {@code false} otherwise
*
* @see #compareTo(String)
* @see #equalsIgnoreCase(String)
*/
public boolean equals(Object anObject) {
if (this == anObject) {
return true;
}
if (anObject instanceof String) {
String anotherString = (String)anObject;
int n = value.length;
if (n == anotherString.value.length) {
char v1[] = value;
char v2[] = anotherString.value;
int i = 0;
while (n-- != 0) {
if (v1[i] != v2[i])
return false;
i++;
}
return true;
}
}
return false;
}
/**
* Compares this string to the specified {@code StringBuffer}. The result
* is {@code true} if and only if this {@code String} represents the same
* sequence of characters as the specified {@code StringBuffer}. This method
* synchronizes on the {@code StringBuffer}.
*
* @param sb
* The {@code StringBuffer} to compare this {@code String} against
*
* @return {@code true} if this {@code String} represents the same
* sequence of characters as the specified {@code StringBuffer},
* {@code false} otherwise
*
* @since 1.4
*/
public boolean contentEquals(StringBuffer sb) {
return contentEquals((CharSequence)sb);
}
private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
char v1[] = value;
char v2[] = sb.getValue();
int n = v1.length;
if (n != sb.length()) {
return false;
}
for (int i = 0; i < n; i++) {
if (v1[i] != v2[i]) {
return false;
}
}
return true;
}
/**
* Compares this string to the specified {@code CharSequence}. The
* result is {@code true} if and only if this {@code String} represents the
* same sequence of char values as the specified sequence. Note that if the
* {@code CharSequence} is a {@code StringBuffer} then the method
* synchronizes on it.
*
* @param cs
* The sequence to compare this {@code String} against
*
* @return {@code true} if this {@code String} represents the same
* sequence of char values as the specified sequence, {@code
* false} otherwise
*
* @since 1.5
*/
public boolean contentEquals(CharSequence cs) {
// Argument is a StringBuffer, StringBuilder
if (cs instanceof AbstractStringBuilder) {
if (cs instanceof StringBuffer) {
synchronized(cs) {
return nonSyncContentEquals((AbstractStringBuilder)cs);
}
} else {
return nonSyncContentEquals((AbstractStringBuilder)cs);
}
}
// Argument is a String
if (cs instanceof String) {
return equals(cs);
}
// Argument is a generic CharSequence
char v1[] = value;
int n = v1.length;
if (n != cs.length()) {
return false;
}
for (int i = 0; i < n; i++) {
if (v1[i] != cs.charAt(i)) {
return false;
}
}
return true;
}
/**
* Compares this {@code String} to another {@code String}, ignoring case
* considerations. Two strings are considered equal ignoring case if they
* are of the same length and corresponding characters in the two strings
* are equal ignoring case.
*
* <p> Two characters {@code c1} and {@code c2} are considered the same
* ignoring case if at least one of the following is true:
* <ul>
* <li> The two characters are the same (as compared by the
* {@code ==} operator)
* <li> Applying the method {@link
* java.lang.Character#toUpperCase(char)} to each character
* produces the same result
* <li> Applying the method {@link
* java.lang.Character#toLowerCase(char)} to each character
* produces the same result
* </ul>
*
* @param anotherString
* The {@code String} to compare this {@code String} against
*
* @return {@code true} if the argument is not {@code null} and it
* represents an equivalent {@code String} ignoring case; {@code
* false} otherwise
*
* @see #equals(Object)
*/
public boolean equalsIgnoreCase(String anotherString) {
return (this == anotherString) ? true
: (anotherString != null)
&& (anotherString.value.length == value.length)
&& regionMatches(true, 0, anotherString, 0, value.length);
}
/**
* Compares two strings lexicographically.
* The comparison is based on the Unicode value of each character in
* the strings. The character sequence represented by this
* {@code String} object is compared lexicographically to the
* character sequence represented by the argument string. The result is
* a negative integer if this {@code String} object
* lexicographically precedes the argument string. The result is a
* positive integer if this {@code String} object lexicographically
* follows the argument string. The result is zero if the strings
* are equal; {@code compareTo} returns {@code 0} exactly when
* the {@link #equals(Object)} method would return {@code true}.
* <p>
* This is the definition of lexicographic ordering. If two strings are
* different, then either they have different characters at some index
* that is a valid index for both strings, or their lengths are different,
* or both. If they have different characters at one or more index
* positions, let <i>k</i> be the smallest such index; then the string
* whose character at position <i>k</i> has the smaller value, as
* determined by using the < operator, lexicographically precedes the
* other string. In this case, {@code compareTo} returns the
* difference of the two character values at position {@code k} in
* the two string -- that is, the value:
* <blockquote><pre>
* this.charAt(k)-anotherString.charAt(k)
* </pre></blockquote>
* If there is no index position at which they differ, then the shorter
* string lexicographically precedes the longer string. In this case,
* {@code compareTo} returns the difference of the lengths of the
* strings -- that is, the value:
* <blockquote><pre>
* this.length()-anotherString.length()
* </pre></blockquote>
*
* @param anotherString the {@code String} to be compared.
* @return the value {@code 0} if the argument string is equal to
* this string; a value less than {@code 0} if this string
* is lexicographically less than the string argument; and a
* value greater than {@code 0} if this string is
* lexicographically greater than the string argument.
*/
public int compareTo(String anotherString) {
int len1 = value.length;
int len2 = anotherString.value.length;
int lim = Math.min(len1, len2);
char v1[] = value;
char v2[] = anotherString.value;
int k = 0;
while (k < lim) {
char c1 = v1[k];
char c2 = v2[k];
if (c1 != c2) {
return c1 - c2;
}
k++;
}
return len1 - len2;
}
/**
* A Comparator that orders {@code String} objects as by
* {@code compareToIgnoreCase}. This comparator is serializable.
* <p>
* Note that this Comparator does <em>not</em> take locale into account,
* and will result in an unsatisfactory ordering for certain locales.
* The java.text package provides <em>Collators</em> to allow
* locale-sensitive ordering.
*
* @see java.text.Collator#compare(String, String)
* @since 1.2
*/
public static final Comparator<String> CASE_INSENSITIVE_ORDER
= new CaseInsensitiveComparator();
private static class CaseInsensitiveComparator
implements Comparator<String>, java.io.Serializable {
// use serialVersionUID from JDK 1.2.2 for interoperability
private static final long serialVersionUID = 8575799808933029326L;
public int compare(String s1, String s2) {
int n1 = s1.length();
int n2 = s2.length();
int min = Math.min(n1, n2);
for (int i = 0; i < min; i++) {
char c1 = s1.charAt(i);
char c2 = s2.charAt(i);
if (c1 != c2) {
c1 = Character.toUpperCase(c1);
c2 = Character.toUpperCase(c2);
if (c1 != c2) {
c1 = Character.toLowerCase(c1);
c2 = Character.toLowerCase(c2);
if (c1 != c2) {
// No overflow because of numeric promotion
return c1 - c2;
}
}
}
}
return n1 - n2;
}
/** Replaces the de-serialized object. */
private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
}
/**
* Compares two strings lexicographically, ignoring case
* differences. This method returns an integer whose sign is that of
* calling {@code compareTo} with normalized versions of the strings
* where case differences have been eliminated by calling
* {@code Character.toLowerCase(Character.toUpperCase(character))} on
* each character.
* <p>
* Note that this method does <em>not</em> take locale into account,
* and will result in an unsatisfactory ordering for certain locales.
* The java.text package provides <em>collators</em> to allow
* locale-sensitive ordering.
*
* @param str the {@code String} to be compared.
* @return a negative integer, zero, or a positive integer as the
* specified String is greater than, equal to, or less
* than this String, ignoring case considerations.
* @see java.text.Collator#compare(String, String)
* @since 1.2
*/
public int compareToIgnoreCase(String str) {
return CASE_INSENSITIVE_ORDER.compare(this, str);
}
/**
* Tests if two string regions are equal.
* <p>
* A substring of this {@code String} object is compared to a substring
* of the argument other. The result is true if these substrings
* represent identical character sequences. The substring of this
* {@code String} object to be compared begins at index {@code toffset}
* and has length {@code len}. The substring of other to be compared
* begins at index {@code ooffset} and has length {@code len}. The
* result is {@code false} if and only if at least one of the following
* is true:
* <ul><li>{@code toffset} is negative.
* <li>{@code ooffset} is negative.
* <li>{@code toffset+len} is greater than the length of this
* {@code String} object.
* <li>{@code ooffset+len} is greater than the length of the other
* argument.
* <li>There is some nonnegative integer <i>k</i> less than {@code len}
* such that:
* {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + }
* <i>k</i>{@code )}
* </ul>
*
* @param toffset the starting offset of the subregion in this string.
* @param other the string argument.
* @param ooffset the starting offset of the subregion in the string
* argument.
* @param len the number of characters to compare.
* @return {@code true} if the specified subregion of this string
* exactly matches the specified subregion of the string argument;
* {@code false} otherwise.
*/
public boolean regionMatches(int toffset, String other, int ooffset,
int len) {
char ta[] = value;
int to = toffset;
char pa[] = other.value;
int po = ooffset;
// Note: toffset, ooffset, or len might be near -1>>>1.
if ((ooffset < 0) || (toffset < 0)
|| (toffset > (long)value.length - len)
|| (ooffset > (long)other.value.length - len)) {
return false;
}
while (len-- > 0) {
if (ta[to++] != pa[po++]) {
return false;
}
}
return true;
}
/**
* Tests if two string regions are equal.
* <p>
* A substring of this {@code String} object is compared to a substring
* of the argument {@code other}. The result is {@code true} if these
* substrings represent character sequences that are the same, ignoring
* case if and only if {@code ignoreCase} is true. The substring of
* this {@code String} object to be compared begins at index
* {@code toffset} and has length {@code len}. The substring of
* {@code other} to be compared begins at index {@code ooffset} and
* has length {@code len}. The result is {@code false} if and only if
* at least one of the following is true:
* <ul><li>{@code toffset} is negative.
* <li>{@code ooffset} is negative.
* <li>{@code toffset+len} is greater than the length of this
* {@code String} object.
* <li>{@code ooffset+len} is greater than the length of the other
* argument.
* <li>{@code ignoreCase} is {@code false} and there is some nonnegative
* integer <i>k</i> less than {@code len} such that:
* <blockquote><pre>
* this.charAt(toffset+k) != other.charAt(ooffset+k)
* </pre></blockquote>
* <li>{@code ignoreCase} is {@code true} and there is some nonnegative
* integer <i>k</i> less than {@code len} such that:
* <blockquote><pre>
* Character.toLowerCase(this.charAt(toffset+k)) !=
Character.toLowerCase(other.charAt(ooffset+k))
* </pre></blockquote>
* and:
* <blockquote><pre>
* Character.toUpperCase(this.charAt(toffset+k)) !=
* Character.toUpperCase(other.charAt(ooffset+k))
* </pre></blockquote>
* </ul>
*
* @param ignoreCase if {@code true}, ignore case when comparing
* characters.
* @param toffset the starting offset of the subregion in this
* string.
* @param other the string argument.
* @param ooffset the starting offset of the subregion in the string
* argument.
* @param len the number of characters to compare.
* @return {@code true} if the specified subregion of this string
* matches the specified subregion of the string argument;
* {@code false} otherwise. Whether the matching is exact
* or case insensitive depends on the {@code ignoreCase}
* argument.
*/
public boolean regionMatches(boolean ignoreCase, int toffset,
String other, int ooffset, int len) {
char ta[] = value;
int to = toffset;
char pa[] = other.value;
int po = ooffset;
// Note: toffset, ooffset, or len might be near -1>>>1.
if ((ooffset < 0) || (toffset < 0)
|| (toffset > (long)value.length - len)
|| (ooffset > (long)other.value.length - len)) {
return false;
}
while (len-- > 0) {
char c1 = ta[to++];
char c2 = pa[po++];
if (c1 == c2) {
continue;
}
if (ignoreCase) {
// If characters don't match but case may be ignored,
// try converting both characters to uppercase.
// If the results match, then the comparison scan should
// continue.
char u1 = Character.toUpperCase(c1);
char u2 = Character.toUpperCase(c2);
if (u1 == u2) {
continue;
}
// Unfortunately, conversion to uppercase does not work properly
// for the Georgian alphabet, which has strange rules about case
// conversion. So we need to make one last check before
// exiting.
if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
continue;
}
}
return false;
}
return true;
}
/**
* Tests if the substring of this string beginning at the
* specified index starts with the specified prefix.
*
* @param prefix the prefix.
* @param toffset where to begin looking in this string.
* @return {@code true} if the character sequence represented by the
* argument is a prefix of the substring of this object starting
* at index {@code toffset}; {@code false} otherwise.
* The result is {@code false} if {@code toffset} is
* negative or greater than the length of this
* {@code String} object; otherwise the result is the same
* as the result of the expression
* <pre>
* this.substring(toffset).startsWith(prefix)
* </pre>
*/
public boolean startsWith(String prefix, int toffset) {
char ta[] = value;
int to = toffset;
char pa[] = prefix.value;
int po = 0;
int pc = prefix.value.length;
// Note: toffset might be near -1>>>1.
if ((toffset < 0) || (toffset > value.length - pc)) {
return false;
}
while (--pc >= 0) {
if (ta[to++] != pa[po++]) {
return false;
}
}
return true;
}
/**
* Tests if this string starts with the specified prefix.
*
* @param prefix the prefix.
* @return {@code true} if the character sequence represented by the
* argument is a prefix of the character sequence represented by
* this string; {@code false} otherwise.
* Note also that {@code true} will be returned if the
* argument is an empty string or is equal to this
* {@code String} object as determined by the
* {@link #equals(Object)} method.
* @since 1. 0
*/
public boolean startsWith(String prefix) {
return startsWith(prefix, 0);
}
/**
* Tests if this string ends with the specified suffix.
*
* @param suffix the suffix.
* @return {@code true} if the character sequence represented by the
* argument is a suffix of the character sequence represented by
* this object; {@code false} otherwise. Note that the
* result will be {@code true} if the argument is the
* empty string or is equal to this {@code String} object
* as determined by the {@link #equals(Object)} method.
*/
public boolean endsWith(String suffix) {
return startsWith(suffix, value.length - suffix.value.length);
}
/**
* Returns a hash code for this string. The hash code for a
* {@code String} object is computed as
* <blockquote><pre>
* s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
* </pre></blockquote>
* using {@code int} arithmetic, where {@code s[i]} is the
* <i>i</i>th character of the string, {@code n} is the length of
* the string, and {@code ^} indicates exponentiation.
* (The hash value of the empty string is zero.)
*
* @return a hash code value for this object.
*/
public int hashCode() {
int h = hash;
if (h == 0 && value.length > 0) {
char val[] = value;
for (int i = 0; i < value.length; i++) {
h = 31 * h + val[i];
}
hash = h;
}
return h;
}
/**
* Returns the index within this string of the first occurrence of
* the specified character. If a character with value
* {@code ch} occurs in the character sequence represented by
* this {@code String} object, then the index (in Unicode
* code units) of the first such occurrence is returned. For
* values of {@code ch} in the range from 0 to 0xFFFF
* (inclusive), this is the smallest value <i>k</i> such that:
* <blockquote><pre>
* this.charAt(<i>k</i>) == ch
* </pre></blockquote>
* is true. For other values of {@code ch}, it is the
* smallest value <i>k</i> such that:
* <blockquote><pre>
* this.codePointAt(<i>k</i>) == ch
* </pre></blockquote>
* is true. In either case, if no such character occurs in this
* string, then {@code -1} is returned.
*
* @param ch a character (Unicode code point).
* @return the index of the first occurrence of the character in the
* character sequence represented by this object, or
* {@code -1} if the character does not occur.
*/
public int indexOf(int ch) {
return indexOf(ch, 0);
}
/**
* Returns the index within this string of the first occurrence of the
* specified character, starting the search at the specified index.
* <p>
* If a character with value {@code ch} occurs in the
* character sequence represented by this {@code String}
* object at an index no smaller than {@code fromIndex}, then
* the index of the first such occurrence is returned. For values
* of {@code ch} in the range from 0 to 0xFFFF (inclusive),
* this is the smallest value <i>k</i> such that:
* <blockquote><pre>
* (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
* </pre></blockquote>
* is true. For other values of {@code ch}, it is the
* smallest value <i>k</i> such that:
* <blockquote><pre>
* (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
* </pre></blockquote>
* is true. In either case, if no such character occurs in this
* string at or after position {@code fromIndex}, then
* {@code -1} is returned.
*
* <p>
* There is no restriction on the value of {@code fromIndex}. If it
* is negative, it has the same effect as if it were zero: this entire
* string may be searched. If it is greater than the length of this
* string, it has the same effect as if it were equal to the length of
* this string: {@code -1} is returned.
*
* <p>All indices are specified in {@code char} values
* (Unicode code units).
*
* @param ch a character (Unicode code point).
* @param fromIndex the index to start the search from.
* @return the index of the first occurrence of the character in the
* character sequence represented by this object that is greater
* than or equal to {@code fromIndex}, or {@code -1}
* if the character does not occur.
*/
public int indexOf(int ch, int fromIndex) {
final int max = value.length;
if (fromIndex < 0) {
fromIndex = 0;
} else if (fromIndex >= max) {
// Note: fromIndex might be near -1>>>1.
return -1;
}
if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
// handle most cases here (ch is a BMP code point or a
// negative value (invalid code point))
final char[] value = this.value;
for (int i = fromIndex; i < max; i++) {
if (value[i] == ch) {
return i;
}
}
return -1;
} else {
return indexOfSupplementary(ch, fromIndex);
}
}
/**
* Handles (rare) calls of indexOf with a supplementary character.
*/
private int indexOfSupplementary(int ch, int fromIndex) {
if (Character.isValidCodePoint(ch)) {
final char[] value = this.value;
final char hi = Character.highSurrogate(ch);
final char lo = Character.lowSurrogate(ch);
final int max = value.length - 1;
for (int i = fromIndex; i < max; i++) {
if (value[i] == hi && value[i + 1] == lo) {
return i;
}
}
}
return -1;
}
/**
* Returns the index within this string of the last occurrence of
* the specified character. For values of {@code ch} in the
* range from 0 to 0xFFFF (inclusive), the index (in Unicode code
* units) returned is the largest value <i>k</i> such that:
* <blockquote><pre>
* this.charAt(<i>k</i>) == ch
* </pre></blockquote>
* is true. For other values of {@code ch}, it is the
* largest value <i>k</i> such that:
* <blockquote><pre>
* this.codePointAt(<i>k</i>) == ch
* </pre></blockquote>
* is true. In either case, if no such character occurs in this
* string, then {@code -1} is returned. The
* {@code String} is searched backwards starting at the last
* character.
*
* @param ch a character (Unicode code point).
* @return the index of the last occurrence of the character in the
* character sequence represented by this object, or
* {@code -1} if the character does not occur.
*/
public int lastIndexOf(int ch) {
return lastIndexOf(ch, value.length - 1);
}
/**
* Returns the index within this string of the last occurrence of
* the specified character, searching backward starting at the
* specified index. For values of {@code ch} in the range
* from 0 to 0xFFFF (inclusive), the index returned is the largest
* value <i>k</i> such that:
* <blockquote><pre>
* (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
* </pre></blockquote>
* is true. For other values of {@code ch}, it is the
* largest value <i>k</i> such that:
* <blockquote><pre>
* (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
* </pre></blockquote>
* is true. In either case, if no such character occurs in this
* string at or before position {@code fromIndex}, then
* {@code -1} is returned.
*
* <p>All indices are specified in {@code char} values
* (Unicode code units).
*
* @param ch a character (Unicode code point).
* @param fromIndex the index to start the search from. There is no
* restriction on the value of {@code fromIndex}. If it is
* greater than or equal to the length of this string, it has
* the same effect as if it were equal to one less than the
* length of this string: this entire string may be searched.
* If it is negative, it has the same effect as if it were -1:
* -1 is returned.
* @return the index of the last occurrence of the character in the
* character sequence represented by this object that is less
* than or equal to {@code fromIndex}, or {@code -1}
* if the character does not occur before that point.
*/
public int lastIndexOf(int ch, int fromIndex) {
if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
// handle most cases here (ch is a BMP code point or a
// negative value (invalid code point))
final char[] value = this.value;
int i = Math.min(fromIndex, value.length - 1);
for (; i >= 0; i--) {
if (value[i] == ch) {
return i;
}
}
return -1;
} else {
return lastIndexOfSupplementary(ch, fromIndex);
}
}
/**
* Handles (rare) calls of lastIndexOf with a supplementary character.
*/
private int lastIndexOfSupplementary(int ch, int fromIndex) {
if (Character.isValidCodePoint(ch)) {
final char[] value = this.value;
char hi = Character.highSurrogate(ch);
char lo = Character.lowSurrogate(ch);
int i = Math.min(fromIndex, value.length - 2);
for (; i >= 0; i--) {
if (value[i] == hi && value[i + 1] == lo) {
return i;
}
}
}
return -1;
}
/**
* Returns the index within this string of the first occurrence of the
* specified substring.
*
* <p>The returned index is the smallest value <i>k</i> for which:
* <blockquote><pre>
* this.startsWith(str, <i>k</i>)
* </pre></blockquote>
* If no such value of <i>k</i> exists, then {@code -1} is returned.
*
* @param str the substring to search for.
* @return the index of the first occurrence of the specified substring,
* or {@code -1} if there is no such occurrence.
*/
public int indexOf(String str) {
return indexOf(str, 0);
}
/**
* Returns the index within this string of the first occurrence of the
* specified substring, starting at the specified index.
*
* <p>The returned index is the smallest value <i>k</i> for which:
* <blockquote><pre>
* <i>k</i> >= fromIndex {@code &&} this.startsWith(str, <i>k</i>)
* </pre></blockquote>
* If no such value of <i>k</i> exists, then {@code -1} is returned.
*
* @param str the substring to search for.
* @param fromIndex the index from which to start the search.
* @return the index of the first occurrence of the specified substring,
* starting at the specified index,
* or {@code -1} if there is no such occurrence.
*/
public int indexOf(String str, int fromIndex) {
return indexOf(value, 0, value.length,
str.value, 0, str.value.length, fromIndex);
}
/**
* Code shared by String and AbstractStringBuilder to do searches. The
* source is the character array being searched, and the target
* is the string being searched for.
*
* @param source the characters being searched.
* @param sourceOffset offset of the source string.
* @param sourceCount count of the source string.
* @param target the characters being searched for.
* @param fromIndex the index to begin searching from.
*/
static int indexOf(char[] source, int sourceOffset, int sourceCount,
String target, int fromIndex) {
return indexOf(source, sourceOffset, sourceCount,
target.value, 0, target.value.length,
fromIndex);
}
/**
* Code shared by String and StringBuffer to do searches. The
* source is the character array being searched, and the target
* is the string being searched for.
*
* @param source the characters being searched.
* @param sourceOffset offset of the source string.
* @param sourceCount count of the source string.
* @param target the characters being searched for.
* @param targetOffset offset of the target string.
* @param targetCount count of the target string.
* @param fromIndex the index to begin searching from.
*/
static int indexOf(char[] source, int sourceOffset, int sourceCount,
char[] target, int targetOffset, int targetCount,
int fromIndex) {
if (fromIndex >= sourceCount) {
return (targetCount == 0 ? sourceCount : -1);
}
if (fromIndex < 0) {
fromIndex = 0;
}
if (targetCount == 0) {
return fromIndex;
}
char first = target[targetOffset];
int max = sourceOffset + (sourceCount - targetCount);
for (int i = sourceOffset + fromIndex; i <= max; i++) {
/* Look for first character. */
if (source[i] != first) {
while (++i <= max && source[i] != first);
}
/* Found first character, now look at the rest of v2 */
if (i <= max) {
int j = i + 1;
int end = j + targetCount - 1;
for (int k = targetOffset + 1; j < end && source[j]
== target[k]; j++, k++);
if (j == end) {
/* Found whole string. */
return i - sourceOffset;
}
}
}
return -1;
}
/**
* Returns the index within this string of the last occurrence of the
* specified substring. The last occurrence of the empty string ""
* is considered to occur at the index value {@code this.length()}.
*
* <p>The returned index is the largest value <i>k</i> for which:
* <blockquote><pre>
* this.startsWith(str, <i>k</i>)
* </pre></blockquote>
* If no such value of <i>k</i> exists, then {@code -1} is returned.
*
* @param str the substring to search for.
* @return the index of the last occurrence of the specified substring,
* or {@code -1} if there is no such occurrence.
*/
public int lastIndexOf(String str) {
return lastIndexOf(str, value.length);
}
/**
* Returns the index within this string of the last occurrence of the
* specified substring, searching backward starting at the specified index.
*
* <p>The returned index is the largest value <i>k</i> for which:
* <blockquote><pre>
* <i>k</i> {@code <=} fromIndex {@code &&} this.startsWith(str, <i>k</i>)
* </pre></blockquote>
* If no such value of <i>k</i> exists, then {@code -1} is returned.
*
* @param str the substring to search for.
* @param fromIndex the index to start the search from.
* @return the index of the last occurrence of the specified substring,
* searching backward from the specified index,
* or {@code -1} if there is no such occurrence.
*/
public int lastIndexOf(String str, int fromIndex) {
return lastIndexOf(value, 0, value.length,
str.value, 0, str.value.length, fromIndex);
}
/**
* Code shared by String and AbstractStringBuilder to do searches. The
* source is the character array being searched, and the target
* is the string being searched for.
*
* @param source the characters being searched.
* @param sourceOffset offset of the source string.
* @param sourceCount count of the source string.
* @param target the characters being searched for.
* @param fromIndex the index to begin searching from.
*/
static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
String target, int fromIndex) {
return lastIndexOf(source, sourceOffset, sourceCount,
target.value, 0, target.value.length,
fromIndex);
}
/**
* Code shared by String and StringBuffer to do searches. The
* source is the character array being searched, and the target
* is the string being searched for.
*
* @param source the characters being searched.
* @param sourceOffset offset of the source string.
* @param sourceCount count of the source string.
* @param target the characters being searched for.
* @param targetOffset offset of the target string.
* @param targetCount count of the target string.
* @param fromIndex the index to begin searching from.
*/
static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
char[] target, int targetOffset, int targetCount,
int fromIndex) {
/*
* Check arguments; return immediately where possible. For
* consistency, don't check for null str.
*/
int rightIndex = sourceCount - targetCount;
if (fromIndex < 0) {
return -1;
}
if (fromIndex > rightIndex) {
fromIndex = rightIndex;
}
/* Empty string always matches. */
if (targetCount == 0) {
return fromIndex;
}
int strLastIndex = targetOffset + targetCount - 1;
char strLastChar = target[strLastIndex];
int min = sourceOffset + targetCount - 1;
int i = min + fromIndex;
startSearchForLastChar:
while (true) {
while (i >= min && source[i] != strLastChar) {
i--;
}
if (i < min) {
return -1;
}
int j = i - 1;
int start = j - (targetCount - 1);
int k = strLastIndex - 1;
while (j > start) {
if (source[j--] != target[k--]) {
i--;
continue startSearchForLastChar;
}
}
return start - sourceOffset + 1;
}
}
/**
* Returns a string that is a substring of this string. The
* substring begins with the character at the specified index and
* extends to the end of this string. <p>
* Examples:
* <blockquote><pre>
* "unhappy".substring(2) returns "happy"
* "Harbison".substring(3) returns "bison"
* "emptiness".substring(9) returns "" (an empty string)
* </pre></blockquote>
*
* @param beginIndex the beginning index, inclusive.
* @return the specified substring.
* @exception IndexOutOfBoundsException if
* {@code beginIndex} is negative or larger than the
* length of this {@code String} object.
*/
public String substring(int beginIndex) {
if (beginIndex < 0) {
throw new StringIndexOutOfBoundsException(beginIndex);
}
int subLen = value.length - beginIndex;
if (subLen < 0) {
throw new StringIndexOutOfBoundsException(subLen);
}
return (beginIndex == 0) ? this : new String(value, beginIndex, subLen);
}
/**
* Returns a string that is a substring of this string. The
* substring begins at the specified {@code beginIndex} and
* extends to the character at index {@code endIndex - 1}.
* Thus the length of the substring is {@code endIndex-beginIndex}.
* <p>
* Examples:
* <blockquote><pre>
* "hamburger".substring(4, 8) returns "urge"
* "smiles".substring(1, 5) returns "mile"
* </pre></blockquote>
*
* @param beginIndex the beginning index, inclusive.
* @param endIndex the ending index, exclusive.
* @return the specified substring.
* @exception IndexOutOfBoundsException if the
* {@code beginIndex} is negative, or
* {@code endIndex} is larger than the length of
* this {@code String} object, or
* {@code beginIndex} is larger than
* {@code endIndex}.
*/
public String substring(int beginIndex, int endIndex) {
if (beginIndex < 0) {
throw new StringIndexOutOfBoundsException(beginIndex);
}
if (endIndex > value.length) {
throw new StringIndexOutOfBoundsException(endIndex);
}
int subLen = endIndex - beginIndex;
if (subLen < 0) {
throw new StringIndexOutOfBoundsException(subLen);
}
return ((beginIndex == 0) && (endIndex == value.length)) ? this
: new String(value, beginIndex, subLen);
}
/**
* Returns a character sequence that is a subsequence of this sequence.
*
* <p> An invocation of this method of the form
*
* <blockquote><pre>
* str.subSequence(begin, end)</pre></blockquote>
*
* behaves in exactly the same way as the invocation
*
* <blockquote><pre>
* str.substring(begin, end)</pre></blockquote>
*
* @apiNote
* This method is defined so that the {@code String} class can implement
* the {@link CharSequence} interface.
*
* @param beginIndex the begin index, inclusive.
* @param endIndex the end index, exclusive.
* @return the specified subsequence.
*
* @throws IndexOutOfBoundsException
* if {@code beginIndex} or {@code endIndex} is negative,
* if {@code endIndex} is greater than {@code length()},
* or if {@code beginIndex} is greater than {@code endIndex}
*
* @since 1.4
* @spec JSR-51
*/
public CharSequence subSequence(int beginIndex, int endIndex) {
return this.substring(beginIndex, endIndex);
}
/**
* Concatenates the specified string to the end of this string.
* <p>
* If the length of the argument string is {@code 0}, then this
* {@code String} object is returned. Otherwise, a
* {@code String} object is returned that represents a character
* sequence that is the concatenation of the character sequence
* represented by this {@code String} object and the character
* sequence represented by the argument string.<p>
* Examples:
* <blockquote><pre>
* "cares".concat("s") returns "caress"
* "to".concat("get").concat("her") returns "together"
* </pre></blockquote>
*
* @param str the {@code String} that is concatenated to the end
* of this {@code String}.
* @return a string that represents the concatenation of this object's
* characters followed by the string argument's characters.
*/
public String concat(String str) {
int otherLen = str.length();
if (otherLen == 0) {
return this;
}
int len = value.length;
char buf[] = Arrays.copyOf(value, len + otherLen);
str.getChars(buf, len);
return new String(buf, true);
}
/**
* Returns a string resulting from replacing all occurrences of
* {@code oldChar} in this string with {@code newChar}.
* <p>
* If the character {@code oldChar} does not occur in the
* character sequence represented by this {@code String} object,
* then a reference to this {@code String} object is returned.
* Otherwise, a {@code String} object is returned that
* represents a character sequence identical to the character sequence
* represented by this {@code String} object, except that every
* occurrence of {@code oldChar} is replaced by an occurrence
* of {@code newChar}.
* <p>
* Examples:
* <blockquote><pre>
* "mesquite in your cellar".replace('e', 'o')
* returns "mosquito in your collar"
* "the war of baronets".replace('r', 'y')
* returns "the way of bayonets"
* "sparring with a purple porpoise".replace('p', 't')
* returns "starring with a turtle tortoise"
* "JonL".replace('q', 'x') returns "JonL" (no change)
* </pre></blockquote>
*
* @param oldChar the old character.
* @param newChar the new character.
* @return a string derived from this string by replacing every
* occurrence of {@code oldChar} with {@code newChar}.
*/
public String replace(char oldChar, char newChar) {
if (oldChar != newChar) {
int len = value.length;
int i = -1;
char[] val = value; /* avoid getfield opcode */
while (++i < len) {
if (val[i] == oldChar) {
break;
}
}
if (i < len) {
char buf[] = new char[len];
for (int j = 0; j < i; j++) {
buf[j] = val[j];
}
while (i < len) {
char c = val[i];
buf[i] = (c == oldChar) ? newChar : c;
i++;
}
return new String(buf, true);
}
}
return this;
}
/**
* Tells whether or not this string matches the given <a
* href="../util/regex/Pattern.html#sum">regular expression</a>.
*
* <p> An invocation of this method of the form
* <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the
* same result as the expression
*
* <blockquote>
* {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence)
* matches(<i>regex</i>, <i>str</i>)}
* </blockquote>
*
* @param regex
* the regular expression to which this string is to be matched
*
* @return {@code true} if, and only if, this string matches the
* given regular expression
*
* @throws PatternSyntaxException
* if the regular expression's syntax is invalid
*
* @see java.util.regex.Pattern
*
* @since 1.4
* @spec JSR-51
*/
public boolean matches(String regex) {
return Pattern.matches(regex, this);
}
/**
* Returns true if and only if this string contains the specified
* sequence of char values.
*
* @param s the sequence to search for
* @return true if this string contains {@code s}, false otherwise
* @since 1.5
*/
public boolean contains(CharSequence s) {
return indexOf(s.toString()) > -1;
}
/**
* Replaces the first substring of this string that matches the given <a
* href="../util/regex/Pattern.html#sum">regular expression</a> with the
* given replacement.
*
* <p> An invocation of this method of the form
* <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
* yields exactly the same result as the expression
*
* <blockquote>
* <code>
* {@link java.util.regex.Pattern}.{@link
* java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
* java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
* java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>)
* </code>
* </blockquote>
*
*<p>
* Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
* replacement string may cause the results to be different than if it were
* being treated as a literal replacement string; see
* {@link java.util.regex.Matcher#replaceFirst}.
* Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
* meaning of these characters, if desired.
*
* @param regex
* the regular expression to which this string is to be matched
* @param replacement
* the string to be substituted for the first match
*
* @return The resulting {@code String}
*
* @throws PatternSyntaxException
* if the regular expression's syntax is invalid
*
* @see java.util.regex.Pattern
*
* @since 1.4
* @spec JSR-51
*/
public String replaceFirst(String regex, String replacement) {
return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
}
/**
* Replaces each substring of this string that matches the given <a
* href="../util/regex/Pattern.html#sum">regular expression</a> with the
* given replacement.
*
* <p> An invocation of this method of the form
* <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
* yields exactly the same result as the expression
*
* <blockquote>
* <code>
* {@link java.util.regex.Pattern}.{@link
* java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
* java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
* java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>)
* </code>
* </blockquote>
*
*<p>
* Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
* replacement string may cause the results to be different than if it were
* being treated as a literal replacement string; see
* {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
* Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
* meaning of these characters, if desired.
*
* @param regex
* the regular expression to which this string is to be matched
* @param replacement
* the string to be substituted for each match
*
* @return The resulting {@code String}
*
* @throws PatternSyntaxException
* if the regular expression's syntax is invalid
*
* @see java.util.regex.Pattern
*
* @since 1.4
* @spec JSR-51
*/
public String replaceAll(String regex, String replacement) {
return Pattern.compile(regex).matcher(this).replaceAll(replacement);
}
public String replace(CharSequence target, CharSequence replacement) {
return Pattern.compile(target.toString(), Pattern.LITERAL).matcher(
this).replaceAll(Matcher.quoteReplacement(replacement.toString()));
}
public String[] split(String regex, int limit) {
/* fastpath if the regex is a
(1)one-char String and this character is not one of the
RegEx's meta characters ".$|()[{^?*+\\", or
(2)two-char String and the first char is the backslash and
the second is not the ascii digit or ascii letter.
*/
char ch = 0;
if (((regex.value.length == 1 &&
".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
(regex.length() == 2 &&
regex.charAt(0) == '\\' &&
(((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
((ch-'a')|('z'-ch)) < 0 &&
((ch-'A')|('Z'-ch)) < 0)) &&
(ch < Character.MIN_HIGH_SURROGATE ||
ch > Character.MAX_LOW_SURROGATE))
{
int off = 0;
int next = 0;
boolean limited = limit > 0;
ArrayList<String> list = new ArrayList<>();
while ((next = indexOf(ch, off)) != -1) {
if (!limited || list.size() < limit - 1) {
list.add(substring(off, next));
off = next + 1;
} else { // last one
//assert (list.size() == limit - 1);
list.add(substring(off, value.length));
off = value.length;
break;
}
}
// If no match was found, return this
if (off == 0)
return new String[]{this};
// Add remaining segment
if (!limited || list.size() < limit)
list.add(substring(off, value.length));
// Construct result
int resultSize = list.size();
if (limit == 0) {
while (resultSize > 0 && list.get(resultSize - 1).length() == 0) {
resultSize--;
}
}
String[] result = new String[resultSize];
return list.subList(0, resultSize).toArray(result);
}
return Pattern.compile(regex).split(this, limit);
}
public String[] split(String regex) {
return split(regex, 0);
}
public static String join(CharSequence delimiter, CharSequence... elements) {
Objects.requireNonNull(delimiter);
Objects.requireNonNull(elements);
// Number of elements not likely worth Arrays.stream overhead.
StringJoiner joiner = new StringJoiner(delimiter);
for (CharSequence cs: elements) {
joiner.add(cs);
}
return joiner.toString();
}
public static String join(CharSequence delimiter,
Iterable<? extends CharSequence> elements) {
Objects.requireNonNull(delimiter);
Objects.requireNonNull(elements);
StringJoiner joiner = new StringJoiner(delimiter);
for (CharSequence cs: elements) {
joiner.add(cs);
}
return joiner.toString();
}
public String toLowerCase(Locale locale) {
if (locale == null) {
throw new NullPointerException();
}
int firstUpper;
final int len = value.length;
/* Now check if there are any characters that need to be changed. */
scan: {
for (firstUpper = 0 ; firstUpper < len; ) {
char c = value[firstUpper];
if ((c >= Character.MIN_HIGH_SURROGATE)
&& (c <= Character.MAX_HIGH_SURROGATE)) {
int supplChar = codePointAt(firstUpper);
if (supplChar != Character.toLowerCase(supplChar)) {
break scan;
}
firstUpper += Character.charCount(supplChar);
} else {
if (c != Character.toLowerCase(c)) {
break scan;
}
firstUpper++;
}
}
return this;
}
char[] result = new char[len];
int resultOffset = 0; /* result may grow, so i+resultOffset
* is the write location in result */
/* Just copy the first few lowerCase characters. */
System.arraycopy(value, 0, result, 0, firstUpper);
String lang = locale.getLanguage();
boolean localeDependent =
(lang == "tr" || lang == "az" || lang == "lt");
char[] lowerCharArray;
int lowerChar;
int srcChar;
int srcCount;
for (int i = firstUpper; i < len; i += srcCount) {
srcChar = (int)value[i];
if ((char)srcChar >= Character.MIN_HIGH_SURROGATE
&& (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
srcChar = codePointAt(i);
srcCount = Character.charCount(srcChar);
} else {
srcCount = 1;
}
if (localeDependent ||
srcChar == '\u03A3' || // GREEK CAPITAL LETTER SIGMA
srcChar == '\u0130') { // LATIN CAPITAL LETTER I WITH DOT ABOVE
lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale);
} else {
lowerChar = Character.toLowerCase(srcChar);
}
if ((lowerChar == Character.ERROR)
|| (lowerChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
if (lowerChar == Character.ERROR) {
lowerCharArray =
ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale);
} else if (srcCount == 2) {
resultOffset += Character.toChars(lowerChar, result, i + resultOffset) - srcCount;
continue;
} else {
lowerCharArray = Character.toChars(lowerChar);
}
/* Grow result if needed */
int mapLen = lowerCharArray.length;
if (mapLen > srcCount) {
char[] result2 = new char[result.length + mapLen - srcCount];
System.arraycopy(result, 0, result2, 0, i + resultOffset);
result = result2;
}
for (int x = 0; x < mapLen; ++x) {
result[i + resultOffset + x] = lowerCharArray[x];
}
resultOffset += (mapLen - srcCount);
} else {
result[i + resultOffset] = (char)lowerChar;
}
}
return new String(result, 0, len + resultOffset);
}
public String toLowerCase() {
return toLowerCase(Locale.getDefault());
}
public String toUpperCase(Locale locale) {
if (locale == null) {
throw new NullPointerException();
}
int firstLower;
final int len = value.length;
/* Now check if there are any characters that need to be changed. */
scan: {
for (firstLower = 0 ; firstLower < len; ) {
int c = (int)value[firstLower];
int srcCount;
if ((c >= Character.MIN_HIGH_SURROGATE)
&& (c <= Character.MAX_HIGH_SURROGATE)) {
c = codePointAt(firstLower);
srcCount = Character.charCount(c);
} else {
srcCount = 1;
}
int upperCaseChar = Character.toUpperCaseEx(c);
if ((upperCaseChar == Character.ERROR)
|| (c != upperCaseChar)) {
break scan;
}
firstLower += srcCount;
}
return this;
}
System.arraycopy(value, 0, result, 0, firstLower);
String lang = locale.getLanguage();
boolean localeDependent =
(lang == "tr" || lang == "az" || lang == "lt");
char[] upperCharArray;
int upperChar;
int srcChar;
int srcCount;
for (int i = firstLower; i < len; i += srcCount) {
srcChar = (int)value[i];
if ((char)srcChar >= Character.MIN_HIGH_SURROGATE &&
(char)srcChar <= Character.MAX_HIGH_SURROGATE) {
srcChar = codePointAt(i);
srcCount = Character.charCount(srcChar);
} else {
srcCount = 1;
}
if (localeDependent) {
upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale);
} else {
upperChar = Character.toUpperCaseEx(srcChar);
}
if ((upperChar == Character.ERROR)
|| (upperChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
if (upperChar == Character.ERROR) {
if (localeDependent) {
upperCharArray =
ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale);
} else {
upperCharArray = Character.toUpperCaseCharArray(srcChar);
}
} else if (srcCount == 2) {
resultOffset += Character.toChars(upperChar, result, i + resultOffset) - srcCount;
continue;
} else {
upperCharArray = Character.toChars(upperChar);
}
/* Grow result if needed */
int mapLen = upperCharArray.length;
if (mapLen > srcCount) {
char[] result2 = new char[result.length + mapLen - srcCount];
System.arraycopy(result, 0, result2, 0, i + resultOffset);
result = result2;
}
for (int x = 0; x < mapLen; ++x) {
result[i + resultOffset + x] = upperCharArray[x];
}
resultOffset += (mapLen - srcCount);
} else {
result[i + resultOffset] = (char)upperChar;
}
}
return new String(result, 0, len + resultOffset);
}
public String toUpperCase() {
return toUpperCase(Locale.getDefault());
}
public String trim() {
int len = value.length;
int st = 0;
char[] val = value; /* avoid getfield opcode */
while ((st < len) && (val[st] <= ' ')) {
st++;
}
while ((st < len) && (val[len - 1] <= ' ')) {
len--;
}
return ((st > 0) || (len < value.length)) ? substring(st, len) : this;
}
public String toString() {
return this;
}
public char[] toCharArray() {
// Cannot use Arrays.copyOf because of class initialization order issues
char result[] = new char[value.length];
System.arraycopy(value, 0, result, 0, value.length);
return result;
}
public static String format(String format, Object... args) {
return new Formatter().format(format, args).toString();
}
public static String format(Locale l, String format, Object... args) {
return new Formatter(l).format(format, args).toString();
}
public static String valueOf(Object obj) {
return (obj == null) ? "null" : obj.toString();
}
public static String valueOf(char data[]) {
return new String(data);
}
public static String valueOf(char data[], int offset, int count) {
return new String(data, offset, count);
}
public static String copyValueOf(char data[], int offset, int count) {
return new String(data, offset, count);
}
public static String copyValueOf(char data[]) {
return new String(data);
}
public static String valueOf(boolean b) {
return b ? "true" : "false";
}
public static String valueOf(char c) {
char data[] = {c};
return new String(data, true);
}
public static String valueOf(int i) {
return Integer.toString(i);
}
public static String valueOf(long l) {
return Long.toString(l);
}
public static String valueOf(float f) {
return Float.toString(f);
}
public static String valueOf(double d) {
return Double.toString(d);
}
public native String intern();
String 被 修饰符 final 修饰，是无法被继承的，不可变类
String 实现 Serializable 接口，可以被序列化
String 实现 Comparable 接口，可以用于比较大小
String 实现 CharSequence 接口，表示一直有序字符序列，实现了通用的字符序列方法
String 是一个字符序列，内部数据结构其实是一个字符数组，所有的操作方法都是围绕这个字符数组的操作。
String 中频繁使用到了 System 类的 arraycopy 方法，目的是拷贝字符数组
String 内部本质就是操作字符数组 value[]
因为本质就是操作字符数组，内部用到了大量的Arrays.copyOf,以及System.arraycopy方法
参考：
String 源码浅析(一)
