每天一份java源码--第二天--String类(筛选出了常用函数的源码)
String类源码结构：
源码部分：（不方便看的话，拷贝到IDE可能好一点)
package java.lang;
import java.io.ObjectStreamField;
import java.io.UnsupportedEncodingException;
import java.nio.charset.Charset;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Comparator;
import java.util.Formatter;
import java.util.Locale;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.regex.PatternSyntaxException;
/**
* The String class represents character strings. All
* string literals in Java programs, such as "abc", are
* implemented as instances of this class.
*
* Strings are constant; their values cannot be changed after they
* are created. String buffers support mutable strings.
* Because String objects are immutable they can be shared. For example:
*
* String str = "abc";
*
* is equivalent to:
*
* char data[] = {'a', 'b', 'c'};
* String str = new String(data);
*
* Here are some more examples of how strings can be used:
*
* System.out.println("abc");
* String cde = "cde";
* System.out.println("abc" + cde);
* String c = "abc".substring(2,3);
* String d = cde.substring(1, 2);
*
*
* The class String includes methods for examining
* individual characters of the sequence, for comparing strings, for
* searching strings, for extracting substrings, and for creating a
* copy of a string with all characters translated to uppercase or to
* lowercase. Case mapping is based on the Unicode Standard version
* specified by the {@link java.lang.Character Character} class.
*
* The Java language provides special support for the string
* concatenation operator ( + ), and for conversion of
* other objects to strings. String concatenation is implemented
* through the StringBuilder(or StringBuffer)
* class and its append method.
* String conversions are implemented through the method
* toString, defined by Object and
* inherited by all classes in Java. For additional information on
* string concatenation and conversion, see Gosling, Joy, and Steele,
* The Java Language Specification.
*
*
Unless otherwise noted, passing a null argument to a constructor
* or method in this class will cause a {@link NullPointerException} to be
* thrown.
*
*
A String represents a string in the UTF-16 format
* in which supplementary characters are represented by surrogate
* pairs (see the section Unicode
* Character Representations in the Character class for
* more information).
* Index values refer to char code units, so a supplementary
* character uses two positions in a String.
*
The String class provides methods for dealing with
* Unicode code points (i.e., characters), in addition to those for
* dealing with Unicode code units (i.e., char values).
*
* @author Lee Boynton
* @author Arthur van Hoff
* @author Martin Buchholz
* @author Ulf Zibis
* @see java.lang.Object#toString()
* @see java.lang.StringBuffer
* @see java.lang.StringBuilder
* @see java.nio.charset.Charset
* @since JDK1.0
*/
public final class String
implements java.io.Serializable, Comparable
/** 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 initially into an ObjectOutputStream in the
* following format:
*
*TC_STRING(utf String)
*
* The String is written by method
DataOutput.writeUTF.* A new handle is generated to refer to all future references to the
* string instance within the stream.
*/
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 = new char[0];
}
/**
* 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) {
throw new StringIndexOutOfBoundsException(count);
}
// 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 Unicode code point 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) {
throw new StringIndexOutOfBoundsException(count);
}
// 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;
}
/**
* Returns the length of this string.
* The length is equal to the number of Unicode
* code units in the string.
*
* @return the length of the sequence of characters represented by this
* object.
*/
public int length() {
return value.length;
}
/**
* Returns true if, and only if, {@link #length()} is 0.
*
* @return true if {@link #length()} is 0, otherwise
* false
*
* @since 1.6
*/
public boolean isEmpty() {
return value.length == 0;
}
/**
* Returns the char value at the
* specified index. An index ranges from 0 to
* length() - 1. The first char value of the sequence
* is at index 0, the next at index 1,
* and so on, as for array indexing.
*
*
If the char value specified by the index is a
* surrogate, the surrogate
* value is returned.
*
* @param index the index of the char value.
* @return the char value at the specified index of this string.
* The first char value is at index 0.
* @exception IndexOutOfBoundsException if the 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];
}
/**
* 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 {@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.
*
*
Two characters {@code c1} and {@code c2} are considered the same
* ignoring case if at least one of the following is true:
*
- The two characters are the same (as compared by the
* {@code ==} operator)
* - Applying the method {@link
* java.lang.Character#toUpperCase(char)} to each character
* produces the same result
* - Applying the method {@link
* java.lang.Character#toLowerCase(char)} to each character
* produces the same result
*
*
*
* @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
* String object is compared lexicographically to the
* character sequence represented by the argument string. The result is
* a negative integer if this String object
* lexicographically precedes the argument string. The result is a
* positive integer if this String object lexicographically
* follows the argument string. The result is zero if the strings
* are equal; compareTo returns 0 exactly when
* the {@link #equals(Object)} method would return true.
*
* 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 k be the smallest such index; then the string
* whose character at position k has the smaller value, as
* determined by using the < operator, lexicographically precedes the
* other string. In this case, compareTo returns the
* difference of the two character values at position k in
* the two string -- that is, the value:
*
* this.charAt(k)-anotherString.charAt(k)
*
* If there is no index position at which they differ, then the shorter
* string lexicographically precedes the longer string. In this case,
*
compareTo returns the difference of the lengths of the* strings -- that is, the value:
*
* this.length()-anotherString.length()
*
*
* @param anotherString the
String to be compared.* @return the value
0 if the argument string is equal to* this string; a value less than
0 if this string* is lexicographically less than the string argument; and a
* value greater than
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;
}
}