String类是一个字符串的包装类,下面我来给大家分析一下String类的源码。
public final class String
implements java.io.Serializable, Comparable<String>, CharSequence
可以看到String类是一个final类,不可以用来继承,Serializable接口(可序列化接口),Comparable<String>接口(泛型为String类型的比较器接口),CharSequence接口(char值的可读序列接口)。
下面是四个全局私有变量和常量:
/** 最终char类型数组 */
private final char value[];
/** hash值 */
private int hash; // Default to 0
/** 最终序列化值 */
private static final long serialVersionUID = -6849794470754667710L;
/**串行化字段数组*/
private static final ObjectStreamField[] serialPersistentFields =
new ObjectStreamField[0];
无参构造:
public String() {
this.value = "".value;
}
初始化构造函数:
public String(String original) {
this.value = original.value;
this.hash = original.hash;
}
char类型数组构造:
public String(char value[]) {
//复制value数组到this.value数组中
this.value = Arrays.copyOf(value, value.length);
}
多参数构造:
public String(char value[], int offset, int count) {
if (offset < 0) {
//如果offset小于0抛出字符串角标越界异常
throw new StringIndexOutOfBoundsException(offset);
}
if (count <= 0) {
if (count < 0) {
//如果count的值小于0抛出字符串角标越界异常
throw new StringIndexOutOfBoundsException(count);
}
if (offset <= value.length) {
//如果offset小于等于value数组的长度,this.value的值为空字符串的value值
this.value = "".value;
//返回
return;
}
}
// 如果offset的值大于value数组的长度减去总数
if (offset > value.length - count) {
// 抛出字符串角标越界异常
throw new StringIndexOutOfBoundsException(offset + count);
}
//截取角标从offset到offset+count的数组到this.value的数组
this.value = Arrays.copyOfRange(value, offset, offset+count);
}
public String(int[] codePoints, int offset, int count) {
if (offset < 0) {
//如果offset小于0抛出字符串角标越界异常
throw new StringIndexOutOfBoundsException(offset);
}
if (count <= 0) {
if (count < 0) {
//如果count小于0抛出字符串角标越界异常
throw new StringIndexOutOfBoundsException(count);
}
if (offset <= codePoints.length) {
//空字符的值赋值给this.value
this.value = "".value;
//返回
return;
}
}
// 如果offset大于codePoints的长度减去count
if (offset > codePoints.length - count) {
//抛出字符串角标越界异常
throw new StringIndexOutOfBoundsException(offset + count);
}
//最终变量 end值等于offset的值加上count的值
final int end = offset + count;
// count的值赋值给变量n
int n = count;
//循环 offset赋值给i,i小于end,i自增
for (int i = offset; i < end; i++) {
//把codePoints数组中角标为i的值赋值给int变量c
int c = codePoints[i];
//如果c字符在bmp中
if (Character.isBmpCodePoint(c))
//循环继续
continue;
//如果字符c是一个有效的Unicode值
else if (Character.isValidCodePoint(c))
//n自增
n++;
//否则抛出非法参数异常
else throw new IllegalArgumentException(Integer.toString(c));
}
// Pass 2: Allocate and fill in char[]
//new一个最终字符数组
final char[] v = new char[n];
//循环i等于offset j等于0 i小于end i自增 j自增
for (int i = offset, j = 0; i < end; i++, j++) {
//codePoints数组角标为i的值赋值给int类型变量c
int c = codePoints[i];
//如果变量c在bmp中
if (Character.isBmpCodePoint(c))
//变量c强转成char类型并且赋值给v数组中角标为j的值中
v[j] = (char)c;
else
//
Character.toSurrogates(c, v, j++);
}
this.value = v;
}
/*
*检查offset,count参数在字节数组中是否越界的工具方法
*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);
}
/**
* 通过StringCoding类的decode方法将指定的字节数组按照指定的字符集编码
* 解码为一个字符串对象
* 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);
}
/**
* 通过StringCoding类的decode方法将指定的字节数组按照指定的字符集编码
* 解码为一个字符串对象
* 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);
}
/**
* 通过StringCoding类的decode方法将指定的字节数组按照指定的字符集编码
* 解码为一个字符串对象(重载)
* 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);
}
/**
* 通过StringCoding类的decode方法将指定的字节数组按照指定的字符集编码
* 解码为一个字符串对象(重载)
* 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);
}
/**
* 通过StringCoding类的decode方法将指定的字节数组按照系统平台
* 的默认字符集编码解码为一个字符串对象(重载)
* 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);
}
/**
* 通过StringCoding类的decode方法将指定的字节数组按照系统平台
* 的默认字符集编码解码为一个字符串对象(重载)
* 这里没有指定offset,count参数,则默认会直接截取[0,length() -1]范围内的字节即
* 默认会直接将整个字节数组解码为一个新的字符串对象
* 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);
}
/**
* 根据传入的StringBuffer对象构造一个新的String对象,内部会将StringBuffer对象
* 内的字符数组都复制到当前对象的value属性上,注意此方法是加锁的即线程安全的。
* 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());
}
}
/**
* 根据传入的StringBuilder对象构造一个新的String对象,内部会将StringBuilder对象
* 内的字符数组都复制到当前对象的value属性上,注意此方法不是线程安全的。
* 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;
}
/**
* 返回一个字符串的长度,此长度必须等于Unicode编码单元的长度。
* 一个Unicode编码单元为16个bit,而一个char字符占2个字节刚好16个bit,即
* 一个字符串的长度等于它包含的字符个数。
* 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;
}
/**
* 判断一个字符串是否为一个空字符串[""]
* 当且仅当字符串的length()等于零,此方法才返回true,否则返回false
* 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;
}
/**
* 返回字符串某个索引位置的字符
* 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];
}
/**
* index索引位置的字符往后偏移codePointOffset个索引位置,返回偏移后的索引位置
* 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);
}
/**
* 将当前字符串的字符复制到另一个目标字符数组中
* 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);
}
/**
* 将当前字符串的[srcBegin,srcEnd)区间内的字符复制到dst[]目标字符数组内
* dstbegin + (srcEnd-srcBegin) - 1
* 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);
}
/**
* 将字符串的包含字符复制到一个目标的字节数组中。每个字节接收对应字符的低8位,
* 而每个字符的高8位则不会被复制,也不会参与以任何方式的转换
* 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++];
}
}
/**
* 使用指定的字符集编码将String对象编码成一个字节数组
* 若charsetName参数未指定,那么内部会抛出NullPointerException异常
* 如果你想要更详细的控制字符编码的处理过程,那么你需要使用{@link
* java.nio.charset.CharsetEncoder}类
* 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);
}
/**
* 方法同上,只是字符集编码参数改成了通过Charset类来提供
* 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);
}
/**
* 同getBytes(String charsetName)方法类似,只是这里是采用系统平台默认的字符集编码
* 对字符串进行编码
* 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);
}
/**
* 比较两个对象是否相等,当且仅当anObject参数不为null且
* 它与当前字符串对象表示的是同一个字符序列,才会返回true
* 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;
}
/**
* 比较两个字符串的字母顺序
* 这个比较操作是基于字符串对象的字符序列中包含的每个字符的Unicode值进行比较。
* 如果当前字符串对象的字母顺序在字符串参数之前,那么返回结果为负数,
* 如果当前字符串对象的字母顺序在字符串参数之后,那么返回结果为正数,
* 如果当前字符串对象与字符串参数相等(即equals()返回true),那么返回结果为零
* 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;
}
/**
* 字符串忽略大小写比较器,此比较器实现了Serializable接口
* 注意:此接口并没有考虑语言环境,对于部分地区可能会导致不满意的顺序,
* java.text包下的Collators类提供了语言环境敏感的字符串顺序。
* 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; }
}
/**
* 忽略大小写前提下比较两个字符串的字母顺序
* 注意:此接口并没有考虑语言环境,对于部分地区可能会导致不满意的顺序,
* java.text包下的Collators类提供了语言环境敏感的字符串顺序。
* 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);
}
/**
* 比较两个字符串的指定区域内的字符序列是否相等
* 注意:此方法并没有忽略字符大小写
* 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;
}
/**
* 检测当前字符串是否以指定的前缀字符串开头
* 此方法等价于this.substring(toffset).startsWith(prefix)
* 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;
}
/**
* 检测当前字符串是否以指定的前缀字符串开头(重载)
* 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);
}
/**
* 检测当前字符串是否以指定的后缀字符串结尾
* 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);
}
/**
* 计算当前字符串的hashcode值,计算公式为:
* s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
* 上面的n表示字符串的长度,^表示求幂运算
* 空字符串""的hashcode值为零
* 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;
}
/**
* 返回指定字符在当前字符串对象中第一次出现的索引位置
* 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);
}
/**
* 返回指定字符在当前字符串对象中第一次出现的索引位置
* 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);
}
}
/**
* 返回指定的代码点表示的字符在当前字符串中第一次出现的索引位置
* 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;
}
/**
* 返回指定代码点表示的字符在当前字符串对象中最后一次出现的索引位置
* 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);
}
/**
* 返回指定的代码点表示的字符在当前字符串中最后一次出现的索引位置
* 与indexOf方法类似
* @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);
}
}
/**
* indexOf方法的重载
*
* @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);
}
/**
* 返回指定字符串在当前字符串对象中第一次出现的索引位置
*
* @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);
}
/**
* 返回指定目标字符数组的[targetOffset,targetOffset + targetCount]区间内字符序列
* 在源字符数组的[sourceOffset,sourceOffset + sourceCount]区间内字符序列中
* 第一次出现的索引位置
*
* @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;
}
/**
* 返回指定字符串在当前字符串对象中的最后一次出现的索引位置
*
* @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);
}
/**
* 返回指定字符串在当前字符串对象中的最后一次出现的索引位置,
* 在当前字符串上从指定的fromIndex索引位置开始搜索
* @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);
}
/**
* 返回指定目标字符数组的[targetOffset,targetOffset + targetCount]区间内字符序列
* 在源字符数组的[sourceOffset,sourceOffset + sourceCount]区间内字符序列中
* 最后一次出现的索引位置
*
* @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;
}
}
/**
* 从beginIndex参数表示的索引位置开始截取当前字符串对象
* 若beginIndex=0,则直接返回当前字符串对象,否则截取生成一个子字符串对象
*
* @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);
}
/**
* 截取[beginIndex,endIndex)之间的字符串
* 最终生成的子字符串的长度为endIndex - beginIndex
*
* @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);
}
/**
* 截取[beginIndex,endIndex)之间的字符串,最终生成CharSequence对象
* 与substring(int beginIndex, int endIndex)方法类似,区别就是返回值类型不同
*
* @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);
}
/**
* 将指定的字符串拼接到当前字符串的末尾
* 若str参数表示的字符串的长度==0,那么直接返回this,否则会创建一个新的字符串对象,比如:
* "cares".concat("s") returns "caress"
* "to".concat("get").concat("her") returns "together"
*
* @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);
}
/**
* 替换当前字符串对象中所有出现的oldChar字符为newChar字符,最终
* 返回一个新的字符串对象
* 若当前字符串对象中不包含oldChar字符,那么直接return this,否则,
* 会生成一个新的字符串对象并返回
*
* @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;
}
/**
* 检测当前字符串是否符合给定的正则表达式
*
* @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);
}
/**
* 当且仅当当前字符串包含指定的字符序列才会返回true
* 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;
}
/**
* 根据给定的正则表达式替换当前字符串匹配到的第一个子字符串为参数replacement表示的字符串
* 注意:replacement参数中若包含反斜杠\和美元符号$可能会与直接将其当做纯文本替换字符串
* 返回的结果不一致.如果你需要抑制特殊字符的潜在含义,那么你可能会需要使用
* java.util.regex.Matcher类的quoteReplacement方法来实现当前方法的功能。默认情况下,
* 当前方法是采用java.util.regex.Matcher类的replaceFirst方法实现的.
* @param regex
* the regular expression to which this string is to be matched
* @param replacement
* the string to be substituted for the first match
*
* @return The resulting {@code String}
*
* @throws PatternSyntaxException
* if the regular expression's syntax is invalid
*
* @see java.util.regex.Pattern
*
* @since 1.4
* @spec JSR-51
*/
public String replaceFirst(String regex, String replacement) {
return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
}
/**
* 根据给定的正则表达式替换当前字符串匹配到的所有子字符串为参数replacement表示的字符串
* 注意:replacement参数中若包含反斜杠\和美元符号$可能会与直接将其当做纯文本替换字符串
* 返回的结果不一致.如果你需要抑制特殊字符的潜在含义,那么你可能会需要使用
* java.util.regex.Matcher类的quoteReplacement方法来实现当前方法的功能。默认情况下,
* 当前方法是采用java.util.regex.Matcher类的replaceAll方法实现的.
* @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);
}
/**
* 将当前字符串中第一次出现的target字符序列替换为replacement字符序列
* 注意:若target或replacement参数中包含了正则表达式中的特殊字符,会一律
* 按照纯文本字符去理解,不会被理解为它在正则表达式中表达的含义,
* 即当前方法不支持正则表达式.
*
* @param target The sequence of char values to be replaced
* @param replacement The replacement sequence of char values
* @return The resulting string
* @since 1.5
*/
public String replace(CharSequence target, CharSequence replacement) {
return Pattern.compile(target.toString(), Pattern.LITERAL).matcher(
this).replaceAll(Matcher.quoteReplacement(replacement.toString()));
}
/**
* 分3种情况处理:
* 1. regex参数只有一个字符且该字符串不是正则表达式中的特殊字符 .$|()[{^?*+\ 或者
* 2. regex参数为2个字符,第一个字符是一个反斜杠\,第二个字符为非ASCII码字母或非ASCII码数字
* 3. regex参数超过2个字符并且为合法的正则表达式
* 前2种情况采用fastpath方式进行处理,后面第3种情况采用Pattern.split(this, limit)方法实现
* @param regex
* the delimiting regular expression
*
* @param limit
* the result threshold, as described above
*
* @return the array of strings computed by splitting this string
* around matches of the given regular expression
*
* @throws PatternSyntaxException
* if the regular expression's syntax is invalid
*
* @see java.util.regex.Pattern
*
* @since 1.4
* @spec JSR-51
*/
public String[] split(String regex, int limit) {
/* fastpath if the regex is a
(1)one-char String and this character is not one of the
RegEx's meta characters ".$|()[{^?*+\\", 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);
}
/**
* split(String regex, int limit)方法的重载,limit参数默认值为零
*
* @param regex
* the delimiting regular expression
*
* @return the array of strings computed by splitting this string
* around matches of 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 String[] split(String regex) {
return split(regex, 0);
}
/**
*
* @param delimiter the delimiter that separates each element
* @param elements the elements to join together.
*
* @return a new {@code String} that is composed of the {@code elements}
* separated by the {@code delimiter}
*
* @throws NullPointerException If {@code delimiter} or {@code elements}
* is {@code null}
*
* @see java.util.StringJoiner
* @since 1.8
*/
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();
}
/**
* Returns a new {@code String} composed of copies of the
* {@code CharSequence elements} joined together with a copy of the
* specified {@code delimiter}.
*
* <blockquote>For example,
* <pre>{@code
* List<String> strings = new LinkedList<>();
* strings.add("Java");strings.add("is");
* strings.add("cool");
* String message = String.join(" ", strings);
* //message returned is: "Java is cool"
*
* Set<String> strings = new LinkedHashSet<>();
* strings.add("Java"); strings.add("is");
* strings.add("very"); strings.add("cool");
* String message = String.join("-", strings);
* //message returned is: "Java-is-very-cool"
* }</pre></blockquote>
*
* Note that if an individual element is {@code null}, then {@code "null"} is added.
*
* @param delimiter a sequence of characters that is used to separate each
* of the {@code elements} in the resulting {@code String}
* @param elements an {@code Iterable} that will have its {@code elements}
* joined together.
*
* @return a new {@code String} that is composed from the {@code elements}
* argument
*
* @throws NullPointerException If {@code delimiter} or {@code elements}
* is {@code null}
*
* @see #join(CharSequence,CharSequence...)
* @see java.util.StringJoiner
* @since 1.8
*/
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();
}
/**
* 使用给定Local的大小写形式的转换规则将当前字符串对象的字符序列中包含的每个字符转换成小写形式
* 由于大小写映射并不总是以1:1的形式进行字符映射,因此可能会导致转换后的字符串长度与原字符串的长度
* 不一致.
* @param locale use the case transformation rules for this locale
* @return the {@code String}, converted to lowercase.
* @see java.lang.String#toLowerCase()
* @see java.lang.String#toUpperCase()
* @see java.lang.String#toUpperCase(Locale)
* @since 1.1
*/
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);
}
/**
* toLowerCase(Locale locale)方法的重载,
* Local默认值为Locale.getDefault(),默认的Local跟你
* 当前JVM实例运行的主机系统平台环境有关
* @return the {@code String}, converted to lowercase.
* @see java.lang.String#toLowerCase(Locale)
*/
public String toLowerCase() {
return toLowerCase(Locale.getDefault());
}
/**
* 使用给定Local的大小写形式的转换规则将当前字符串对象的字符序列中包含的每个字符转换成大写形式
* 由于大小写映射并不总是以1:1的形式进行字符映射,因此可能会导致转换后的字符串长度与原字符串的长度
* 不一致.
* @param locale use the case transformation rules for this locale
* @return the {@code String}, converted to uppercase.
* @see java.lang.String#toUpperCase()
* @see java.lang.String#toLowerCase()
* @see java.lang.String#toLowerCase(Locale)
* @since 1.1
*/
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;
}
/* result may grow, so i+resultOffset is the write location in result */
int resultOffset = 0;
char[] result = new char[len]; /* may grow */
/* Just copy the first few upperCase characters. */
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);
}
/**
* toUpperCase(Locale locale)方法的重载,Local参数默认值为Locale.getDefault(),
* 默认的Local跟你当前JVM实例运行的主机系统平台环境有关
* @return the {@code String}, converted to uppercase.
* @see java.lang.String#toUpperCase(Locale)
*/
public String toUpperCase() {
return toUpperCase(Locale.getDefault());
}
/**
* 剔除掉当前字符串对象的两头连续的空格字符,并返回一个新的字符串对象
* @return A string whose value is this string, with any leading and trailing white
* space removed, or this string if it has no leading or
* trailing white space.
*/
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;
}
/**
* 因为当前字符串对象已经是String类型,因此这里直接return this.
*
* @return the string itself.
*/
public String toString() {
return this;
}
/**
* 将当前字符串对象转换成一个字符数组
*
* @return a newly allocated character array whose length is the length
* of this string and whose contents are initialized to contain
* the character sequence represented by this string.
*/
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;
}
/**
* 使用指定的字符串格式和参数返回一个格式化后的字符串
*
* @param format
* A <a href="../util/Formatter.html#syntax">format string</a>
*
* @param args
* Arguments referenced by the format specifiers in the format
* string. If there are more arguments than format specifiers, the
* extra arguments are ignored. The number of arguments is
* variable and may be zero. The maximum number of arguments is
* limited by the maximum dimension of a Java array as defined by
* <cite>The Java™ Virtual Machine Specification</cite>.
* The behaviour on a
* {@code null} argument depends on the <a
* href="../util/Formatter.html#syntax">conversion</a>.
*
* @throws java.util.IllegalFormatException
* If a format string contains an illegal syntax, a format
* specifier that is incompatible with the given arguments,
* insufficient arguments given the format string, or other
* illegal conditions. For specification of all possible
* formatting errors, see the <a
* href="../util/Formatter.html#detail">Details</a> section of the
* formatter class specification.
*
* @return A formatted string
*
* @see java.util.Formatter
* @since 1.5
*/
public static String format(String format, Object... args) {
return new Formatter().format(format, args).toString();
}
/**
* 使用指定的字符串格式和参数在指定的语言环境下返回一个格式化后的字符串
*
* @param l
* The {@linkplain java.util.Locale locale} to apply during
* formatting. If {@code l} is {@code null} then no localization
* is applied.
*
* @param format
* A <a href="../util/Formatter.html#syntax">format string</a>
*
* @param args
* Arguments referenced by the format specifiers in the format
* string. If there are more arguments than format specifiers, the
* extra arguments are ignored. The number of arguments is
* variable and may be zero. The maximum number of arguments is
* limited by the maximum dimension of a Java array as defined by
* <cite>The Java™ Virtual Machine Specification</cite>.
* The behaviour on a
* {@code null} argument depends on the
* <a href="../util/Formatter.html#syntax">conversion</a>.
*
* @throws java.util.IllegalFormatException
* If a format string contains an illegal syntax, a format
* specifier that is incompatible with the given arguments,
* insufficient arguments given the format string, or other
* illegal conditions. For specification of all possible
* formatting errors, see the <a
* href="../util/Formatter.html#detail">Details</a> section of the
* formatter class specification
*
* @return A formatted string
*
* @see java.util.Formatter
* @since 1.5
*/
public static String format(Locale l, String format, Object... args) {
return new Formatter(l).format(format, args).toString();
}
/**
* 将指定的obj对象转换成String对象
*
* @param obj an {@code Object}.
* @return if the argument is {@code null}, then a string equal to
* {@code "null"}; otherwise, the value of
* {@code obj.toString()} is returned.
* @see java.lang.Object#toString()
*/
public static String valueOf(Object obj) {
return (obj == null) ? "null" : obj.toString();
}
/**
* 将指定的字符数组对象转换成String对象
*
* @param data the character array.
* @return a {@code String} that contains the characters of the
* character array.
*/
public static String valueOf(char data[]) {
return new String(data);
}
/**
* 将指定的字符数组的[offset,offset + count]区间内的字符序列转换成一个字符串对象
*
* @param data the character array.
* @param offset initial offset of the subarray.
* @param count length of the subarray.
* @return a {@code String} that contains the characters of the
* specified subarray of the character array.
* @exception IndexOutOfBoundsException if {@code offset} is
* negative, or {@code count} is negative, or
* {@code offset+count} is larger than
* {@code data.length}.
*/
public static String valueOf(char data[], int offset, int count) {
return new String(data, offset, count);
}
/**
* 将指定的字符数组的[offset,offset + count]区间内的字符序列转换成一个字符串对象
* 同valueOf(char data[], int offset, int count)方法实现细节一模一样,仅仅只是方法名称不同
*
* @param data the character array.
* @param offset initial offset of the subarray.
* @param count length of the subarray.
* @return a {@code String} that contains the characters of the
* specified subarray of the character array.
* @exception IndexOutOfBoundsException if {@code offset} is
* negative, or {@code count} is negative, or
* {@code offset+count} is larger than
* {@code data.length}.
*/
public static String copyValueOf(char data[], int offset, int count) {
return new String(data, offset, count);
}
/**
* 将指定的字符数组转换成一个字符串对象
* 同valueOf(char data[])方法的具体实现细节一模一样,仅仅只是方法名称不同
*
* @param data the character array.
* @return a {@code String} that contains the characters of the
* character array.
*/
public static String copyValueOf(char data[]) {
return new String(data);
}
/**
* 将boolean变量值转换成一个字符串对象
*
* @param b a {@code boolean}.
* @return if the argument is {@code true}, a string equal to
* {@code "true"} is returned; otherwise, a string equal to
* {@code "false"} is returned.
*/
public static String valueOf(boolean b) {
return b ? "true" : "false";
}
/**
* 将单个字符转换成一个字符串对象
*
* @param c a {@code char}.
* @return a string of length {@code 1} containing
* as its single character the argument {@code c}.
*/
public static String valueOf(char c) {
char data[] = {c};
return new String(data, true);
}
/**
* 将int数字转换成一个字符串对象
* 内部实际是调用Integer.toString()方法实现的
*
* @param i an {@code int}.
* @return a string representation of the {@code int} argument.
* @see java.lang.Integer#toString(int, int)
*/
public static String valueOf(int i) {
return Integer.toString(i);
}
/**
* 将long数字转换成一个字符串对象
* 内部实际是调用Long.toString()方法实现的
*
* @param l a {@code long}.
* @return a string representation of the {@code long} argument.
* @see java.lang.Long#toString(long)
*/
public static String valueOf(long l) {
return Long.toString(l);
}
/**
* 将float数字转换成一个字符串对象
* 内部实际是调用Float.toString()方法实现的
*
* @param f a {@code float}.
* @return a string representation of the {@code float} argument.
* @see java.lang.Float#toString(float)
*/
public static String valueOf(float f) {
return Float.toString(f);
}
/**
* 将double数字转换成一个字符串对象
* 内部实际是调用Double.toString()方法实现的
*
* @param d a {@code double}.
* @return a string representation of the {@code double} argument.
* @see java.lang.Double#toString(double)
*/
public static String valueOf(double d) {
return Double.toString(d);
}
/**
* 返回字符串对象的规范化表示形式
* 字符串常量池初始化默认是空的,它由String类私下管理维护
* 当intern方法被执行,如果字符串常量池已经包含了与当前字符串对象equals的字符串,
* 那么直接从字符串常量池里返回该字符串对象即可,否则会将该字符串对象添加到常量池中
* 并返回.
* 因此对于任意的两个字符串s和t,
* 当且仅当s.equals(t) == true,
* s.intern() == t.intern()才会返回true.
* 所有的字符串字面量以及基于String的常量表达式都会被字符串常量池集中管理和返回.
*/
public native String intern();