/*
* @(#)String.java 1.159 03/01/23
*
* Copyright 2003 Sun Microsystems, Inc. All rights reserved.
* SUN PROPRIETARY/CONFIDENTIAL. Use is subject to license terms.
*/
package java.lang;
//*KML import java.io.ObjectStreamClass;
//*KML import java.io.ObjectStreamField;
//*KML import java.io.UnsupportedEncodingException;
//*KML import java.util.ArrayList;
//*KML import java.util.Comparator;
//*KML import java.util.Locale;
//*KML import java.util.regex.Matcher;
//*KML import java.util.regex.Pattern;
//*KML import java.util.regex.PatternSyntaxException;
/**
* The <code>String</code> class represents character strings. All
* string literals in Java programs, such as <code>"abc"</code>, are
* implemented as instances of this class.
* <p>
* 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:
* <p><blockquote><pre>
* String str = "abc";
* </pre></blockquote><p>
* is equivalent to:
* <p><blockquote><pre>
* char data[] = {'a', 'b', 'c'};
* String str = new String(data);
* </pre></blockquote><p>
* Here are some more examples of how strings can be used:
* <p><blockquote><pre>
* System.out.println("abc");
* String cde = "cde";
* System.out.println("abc" + cde);
* String c = "abc".substring(2,3);
* String d = cde.substring(1, 2);
* </pre></blockquote>
* <p>
* The class <code>String</code> 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 relies heavily on the information provided
* by the Unicode Consortium's Unicode 3.0 specification. The
* specification's UnicodeData.txt and SpecialCasing.txt files are
* used extensively to provide case mapping.
* <p>
* 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 <code>StringBuffer</code> class and its
* <code>append</code> method.
* String conversions are implemented through the method
* <code>toString</code>, defined by <code>Object</code> and
* inherited by all classes in Java. For additional information on
* string concatenation and conversion, see Gosling, Joy, and Steele,
* <i>The Java Language Specification</i>.
*
* <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor
* or method in this class will cause a {@link NullPointerException} to be
* thrown.
*
* @author Lee Boynton
* @author Arthur van Hoff
* @version 1.152, 02/01/03
* @see java.lang.Object#toString()
* @see java.lang.StringBuffer
* @see java.lang.StringBuffer#append(boolean)
* @see java.lang.StringBuffer#append(char)
* @see java.lang.StringBuffer#append(char[])
* @see java.lang.StringBuffer#append(char[], int, int)
* @see java.lang.StringBuffer#append(double)
* @see java.lang.StringBuffer#append(float)
* @see java.lang.StringBuffer#append(int)
* @see java.lang.StringBuffer#append(long)
* @see java.lang.StringBuffer#append(java.lang.Object)
* @see java.lang.StringBuffer#append(java.lang.String)
* @see java.nio.charset.Charset
* @since JDK1.0
*/
public final class String
implements java.io.Serializable, Comparable, CharSequence
{
/** The value is used for character storage. */
private char value[];
/** The offset is the first index of the storage that is used. */
private int offset;
/** The count is the number of characters in the String. */
private int count;
/** Cache the hash code for the string */
private int hash = 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 intially into an ObjectOutputStream in the
* following format:
* <pre>
* <code>TC_STRING</code> (utf String)
* </pre>
* The String is written by method <code>DataOutput.writeUTF</code>.
* A new handle is generated to refer to all future references to the
* string instance within the stream.
*/
/*KML
private static final ObjectStreamField[] serialPersistentFields =
new ObjectStreamField[0];
KML*/
/**
* Initializes a newly created <code>String</code> object so that it
* represents an empty character sequence. Note that use of this
* constructor is unnecessary since Strings are immutable.
*/
public String() {
value = new char[0];
}
/**
* Initializes a newly created <code>String</code> 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</code> is needed, use of this
* constructor is unnecessary since Strings are immutable.
*
* @param original a <code>String</code>.
*/
public String(String original) {
this.count = original.count;
if (original.value.length > this.count) {
// The array representing the String is bigger than the new
// String itself. Perhaps this constructor is being called
// in order to trim the baggage, so make a copy of the array.
this.value = new char[this.count];
System.arraycopy(original.value, original.offset,
this.value, 0, this.count);
} else {
// The array representing the String is the same
// size as the String, so no point in making a copy.
this.value = original.value;
}
}
/**
* Allocates a new <code>String</code> 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.count = value.length;
this.value = new char[count];
System.arraycopy(value, 0, this.value, 0, count);
}
/**
* Allocates a new <code>String</code> that contains characters from
* a subarray of the character array argument. The <code>offset</code>
* argument is the index of the first character of the subarray and
* the <code>count</code> 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.
* @exception IndexOutOfBoundsException if the <code>offset</code>
* and <code>count</code> arguments index characters outside
* the bounds of the <code>value</code> 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 = new char[count];
this.count = count;
System.arraycopy(value, offset, this.value, 0, count);
}
/**
* Allocates a new <code>String</code> constructed from a subarray
* of an array of 8-bit integer values.
* <p>
* The <code>offset</code> argument is the index of the first byte
* of the subarray, and the <code>count</code> argument specifies the
* length of the subarray.
* <p>
* Each <code>byte</code> in the subarray is converted to a
* <code>char</code> 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</code> constructors that take a 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 character.
* @param offset the initial offset.
* @param count the length.
* @exception IndexOutOfBoundsException if the <code>offset</code>
* or <code>count</code> argument is invalid.
* @see java.lang.String#String(byte[], int)
* @see java.lang.String#String(byte[], int, int, java.lang.String)
* @see java.lang.String#String(byte[], int, int)
* @see java.lang.String#String(byte[], java.lang.String)
* @see java.lang.String#String(byte[])
*/
public String(byte ascii[], int hibyte, int offset, int count) {
checkBounds(ascii, offset, count);
char value[] = new char[count];
this.count = count;
this.value = value;
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));
}
}
}
/**
* Allocates a new <code>String</code> 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:
* <p><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</code> constructors that take a 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 character.
* @see java.lang.String#String(byte[], int, int, java.lang.String)
* @see java.lang.String#String(byte[], int, int)
* @see java.lang.String#String(byte[], java.lang.String)
* @see java.lang.String#String(byte[])
*/
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 <tt>String</tt> by decoding the specified subarray of
* bytes using the specified charset. The length of the new
* <tt>String</tt> 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
* {@link java.nio.charset.Charset </code>charset<code>}
* @throws UnsupportedEncodingException
* if the named charset is not supported
* @throws IndexOutOfBoundsException
* if the <tt>offset</tt> and <tt>length</tt> arguments
* index characters outside the bounds of the <tt>bytes</tt>
* 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);
value = StringCoding.decode(charsetName, bytes, offset, length);
count = value.length;
}
/**
* Constructs a new <tt>String</tt> by decoding the specified array of
* bytes using the specified charset. The length of the new
* <tt>String</tt> 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
* {@link java.nio.charset.Charset </code>charset<code>}
*
* @exception 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 <tt>String</tt> by decoding the specified subarray of
* bytes using the platform's default charset. The length of the new
* <tt>String</tt> 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</code> and the <code>length</code>
* arguments index characters outside the bounds of the
* <code>bytes</code> array
* @since JDK1.1
*/
public String(byte bytes[], int offset, int length) {
checkBounds(bytes, offset, length);
value = StringCoding.decode(bytes, offset, length);
count = value.length;
}
/**
* Constructs a new <tt>String</tt> by decoding the specified array of
* bytes using the platform's default charset. The length of the new
* <tt>String</tt> 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</code>.
*/
public String (StringBuffer buffer) {
synchronized(buffer) {
buffer.setShared();
this.value = buffer.getValue();
this.offset = 0;
this.count = buffer.length();
}
}
// Package private constructor which shares value array for speed.
String(int offset, int count, char value[]) {
this.value = value;
this.offset = offset;
this.count = count;
}
/**
* Returns the length of this string.
* The length is equal to the number of 16-bit
* Unicode characters in the string.
*
* @return the length of the sequence of characters represented by this
* object.
*/
public int length() {
return count;
}
/**
* Returns the character at the specified index. An index ranges
* from <code>0</code> to <code>length() - 1</code>. The first character
* of the sequence is at index <code>0</code>, the next at index
* <code>1</code>, and so on, as for array indexing.
*
* @param index the index of the character.
* @return the character at the specified index of this string.
* The first character is at index <code>0</code>.
* @exception IndexOutOfBoundsException if the <code>index</code>
* argument is negative or not less than the length of this
* string.
*/
public char charAt(int index) {
if ((index < 0) || (index >= count)) {
throw new StringIndexOutOfBoundsException(index);
}
return value[index + offset];
}
/**
* Copies characters from this string into the destination character
* array.
* <p>
* The first character to be copied is at index <code>srcBegin</code>;
* the last character to be copied is at index <code>srcEnd-1</code>
* (thus the total number of characters to be copied is
* <code>srcEnd-srcBegin</code>). The characters are copied into the
* subarray of <code>dst</code> starting at index <code>dstBegin</code>
* and ending at index:
* <p><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</code> is negative.
* <li><code>srcBegin</code> is greater than <code>srcEnd</code>
* <li><code>srcEnd</code> is greater than the length of this
* string
* <li><code>dstBegin</code> is negative
* <li><code>dstBegin+(srcEnd-srcBegin)</code> is larger than
* <code>dst.length</code></ul>
*/
public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
if (srcBegin < 0) {
throw new StringIndexOutOfBoundsException(srcBegin);
}
if (srcEnd > count) {
throw new StringIndexOutOfBoundsException(srcEnd);
}
if (srcBegin > srcEnd) {
throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
}
System.arraycopy(value, offset + 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</code>;
* the last character to be copied is at index <code>srcEnd-1</code>.
* The total number of characters to be copied is
* <code>srcEnd-srcBegin</code>. The characters, converted to bytes,
* are copied into the subarray of <code>dst</code> starting at index
* <code>dstBegin</code> and ending at index:
* <p><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
* the <code>getBytes()</code> 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.
* @exception IndexOutOfBoundsException if any of the following
* is true:
* <ul><li><code>srcBegin</code> is negative
* <li><code>srcBegin</code> is greater than <code>srcEnd</code>
* <li><code>srcEnd</code> is greater than the length of this
* String
* <li><code>dstBegin</code> is negative
* <li><code>dstBegin+(srcEnd-srcBegin)</code> is larger than
* <code>dst.length</code></ul>
*/
public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
if (srcBegin < 0) {
throw new StringIndexOutOfBoundsException(srcBegin);
}
if (srcEnd > count) {
throw new StringIndexOutOfBoundsException(srcEnd);
}
if (srcBegin > srcEnd) {
throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
}
int j = dstBegin;
int n = offset + srcEnd;
int i = offset + srcBegin;
char[] val = value; /* avoid getfield opcode */
while (i < n) {
dst[j++] = (byte)val[i++];
}
}
/**
* Encodes this <tt>String</tt> 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
* {@link java.nio.charset.Charset </code>charset<code>}
*
* @return The resultant byte array
*
* @exception UnsupportedEncodingException
* If the named charset is not supported
*
* @since JDK1.1
*/
public byte[] getBytes(String charsetName)
throws UnsupportedEncodingException
{
return StringCoding.encode(charsetName, value, offset, count);
}
/**
* Encodes this <tt>String</tt> 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, offset, count);
}
/**
* Compares this string to the specified object.
* The result is <code>true</code> if and only if the argument is not
* <code>null</code> and is a <code>String</code> object that represents
* the same sequence of characters as this object.
*
* @param anObject the object to compare this <code>String</code>
* against.
* @return <code>true</code> if the <code>String </code>are equal;
* <code>false</code> otherwise.
* @see java.lang.String#compareTo(java.lang.String)
* @see java.lang.String#equalsIgnoreCase(java.lang.String)
*/
public boolean equals(Object anObject) {
if (this == anObject) {
return true;
}
if (anObject instanceof String) {
String anotherString = (String)anObject;
int n = count;
if (n == anotherString.count) {
char v1[] = value;
char v2[] = anotherString.value;
int i = offset;
int j = anotherString.offset;
while (n-- != 0) {
if (v1[i++] != v2[j++])
return false;
}
return true;
}
}
return false;
}
/**
* Returns <tt>true</tt> if and only if this <tt>String</tt> represents
* the same sequence of characters as the specified <tt>StringBuffer</tt>.
*
* @param sb the <tt>StringBuffer</tt> to compare to.
* @return <tt>true</tt> if and only if this <tt>String</tt> represents
* the same sequence of characters as the specified
* <tt>StringBuffer</tt>, otherwise <tt>false</tt>.
* @since 1.4
*/
public boolean contentEquals(StringBuffer sb) {
synchronized(sb) {
if (count != sb.length())
return false;
char v1[] = value;
char v2[] = sb.getValue();
int i = offset;
int j = 0;
int n = count;
while (n-- != 0) {
if (v1[i++] != v2[j++])
return false;
}
}
return true;
}
/**
* Compares this <code>String</code> to another <code>String</code>,
* 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</code> and <code>c2</code> 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>==</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</code> to compare this
* <code>String</code> against.
* @return <code>true</code> if the argument is not <code>null</code>
* and the <code>String</code>s are equal,
* ignoring case; <code>false</code> otherwise.
* @see #equals(Object)
* @see java.lang.Character#toLowerCase(char)
* @see java.lang.Character#toUpperCase(char)
*/
public boolean equalsIgnoreCase(String anotherString) {
return (this == anotherString) ? true :
(anotherString != null) && (anotherString.count == count) &&
regionMatches(true, 0, anotherString, 0, count);
}
/**
* 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</code> object is compared lexicographically to the
* character sequence represented by the argument string. The result is
* a negative integer if this <code>String</code> object
* lexicographically precedes the argument string. The result is a
* positive integer if this <code>String</code> object lexicographically
* follows the argument string. The result is zero if the strings
* are equal; <code>compareTo</code> returns <code>0</code> exactly when
* the {@link #equals(Object)} method would return <code>true</code>.
* <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</code> returns the
* difference of the two character values at position <code>k</code> 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</code> 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</code> to be compared.
* @return the value <code>0</code> if the argument string is equal to
* this string; a value less than <code>0</code> if this string
* is lexicographically less than the string argument; and a
* value greater than <code>0</code> if this string is
* lexicographically greater than the string argument.
*/
public int compareTo(String anotherString) {
int len1 = count;
int len2 = anotherString.count;
int n = Math.min(len1, len2);
char v1[] = value;
char v2[] = anotherString.value;
int i = offset;
int j = anotherString.offset;
if (i == j) {
int k = i;
int lim = n + i;
while (k < lim) {
char c1 = v1[k];
char c2 = v2[k];
if (c1 != c2) {
return c1 - c2;
}
k++;
}
} else {
while (n-- != 0) {
char c1 = v1[i++];
char c2 = v2[j++];
if (c1 != c2) {
return c1 - c2;
}
}
}
return len1 - len2;
}
/**
* Compares this String to another Object. If the Object is a String,
* this function behaves like <code>compareTo(String)</code>. Otherwise,
* it throws a <code>ClassCastException</code> (as Strings are comparable
* only to other Strings).
*
* @param o the <code>Object</code> to be compared.
* @return the value <code>0</code> if the argument is a string
* lexicographically equal to this string; a value less than
* <code>0</code> if the argument is a string lexicographically
* greater than this string; and a value greater than
* <code>0</code> if the argument is a string lexicographically
* less than this string.
* @exception <code>ClassCastException</code> if the argument is not a
* <code>String</code>.
* @see java.lang.Comparable
* @since 1.2
*/
public int compareTo(Object o) {
return compareTo((String)o);
}
/**
* A Comparator that orders <code>String</code> objects as by
* <code>compareToIgnoreCase</code>. 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
*/
/* KML
public static final Comparator CASE_INSENSITIVE_ORDER
= new CaseInsensitiveComparator();
private static class CaseInsensitiveComparator
implements Comparator, java.io.Serializable {
// use serialVersionUID from JDK 1.2.2 for interoperability
private static final long serialVersionUID = 8575799808933029326L;
public int compare(Object o1, Object o2) {
String s1 = (String) o1;
String s2 = (String) o2;
int n1=s1.length(), n2=s2.length();
for (int i1=0, i2=0; i1<n1 && i2<n2; i1++, i2++) {
char c1 = s1.charAt(i1);
char c2 = s2.charAt(i2);
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) {
return c1 - c2;
}
}
}
}
return n1 - n2;
}
}
KML*/
/**
* Compares two strings lexicographically, ignoring case
* differences. This method returns an integer whose sign is that of
* calling <code>compareTo</code> with normalized versions of the strings
* where case differences have been eliminated by calling
* <code>Character.toLowerCase(Character.toUpperCase(character))</code> 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</code> to be compared.
* @return a negative integer, zero, or a positive integer as the
* 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 <tt>String</tt> 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
* <tt>String</tt> object to be compared begins at index <tt>toffset</tt>
* and has length <tt>len</tt>. The substring of other to be compared
* begins at index <tt>ooffset</tt> and has length <tt>len</tt>. The
* result is <tt>false</tt> if and only if at least one of the following
* is true:
* <ul><li><tt>toffset</tt> is negative.
* <li><tt>ooffset</tt> is negative.
* <li><tt>toffset+len</tt> is greater than the length of this
* <tt>String</tt> object.
* <li><tt>ooffset+len</tt> is greater than the length of the other
* argument.
* <li>There is some nonnegative integer <i>k</i> less than <tt>len</tt>
* such that:
* <tt>this.charAt(toffset+<i>k</i>) != other.charAt(ooffset+<i>k</i>)</tt>
* </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</code> if the specified subregion of this string
* exactly matches the specified subregion of the string argument;
* <code>false</code> otherwise.
*/
public boolean regionMatches(int toffset, String other, int ooffset,
int len) {
char ta[] = value;
int to = offset + toffset;
char pa[] = other.value;
int po = other.offset + ooffset;
// Note: toffset, ooffset, or len might be near -1>>>1.
if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len)
|| (ooffset > (long)other.count - 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 <tt>String</tt> object is compared to a substring
* of the argument <tt>other</tt>. The result is <tt>true</tt> if these
* substrings represent character sequences that are the same, ignoring
* case if and only if <tt>ignoreCase</tt> is true. The substring of
* this <tt>String</tt> object to be compared begins at index
* <tt>toffset</tt> and has length <tt>len</tt>. The substring of
* <tt>other</tt> to be compared begins at index <tt>ooffset</tt> and
* has length <tt>len</tt>. The result is <tt>false</tt> if and only if
* at least one of the following is true:
* <ul><li><tt>toffset</tt> is negative.
* <li><tt>ooffset</tt> is negative.
* <li><tt>toffset+len</tt> is greater than the length of this
* <tt>String</tt> object.
* <li><tt>ooffset+len</tt> is greater than the length of the other
* argument.
* <li><tt>ignoreCase</tt> is <tt>false</tt> and there is some nonnegative
* integer <i>k</i> less than <tt>len</tt> such that:
* <blockquote><pre>
* this.charAt(toffset+k) != other.charAt(ooffset+k)
* </pre></blockquote>
* <li><tt>ignoreCase</tt> is <tt>true</tt> and there is some nonnegative
* integer <i>k</i> less than <tt>len</tt> 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</code>, 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</code> if the specified subregion of this string
* matches the specified subregion of the string argument;
* <code>false</code> otherwise. Whether the matching is exact
* or case insensitive depends on the <code>ignoreCase</code>
* argument.
*/
public boolean regionMatches(boolean ignoreCase, int toffset,
String other, int ooffset, int len) {
char ta[] = value;
int to = offset + toffset;
char pa[] = other.value;
int po = other.offset + ooffset;
// Note: toffset, ooffset, or len might be near -1>>>1.
if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len) ||
(ooffset > (long)other.count - 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 this string starts with the specified prefix beginning
* a specified index.
*
* @param prefix the prefix.
* @param toffset where to begin looking in the string.
* @return <code>true</code> if the character sequence represented by the
* argument is a prefix of the substring of this object starting
* at index <code>toffset</code>; <code>false</code> otherwise.
* The result is <code>false</code> if <code>toffset</code> is
* negative or greater than the length of this
* <code>String</code> 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 = offset + toffset;
char pa[] = prefix.value;
int po = prefix.offset;
int pc = prefix.count;
// Note: toffset might be near -1>>>1.
if ((toffset < 0) || (toffset > count - 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</code> if the character sequence represented by the
* argument is a prefix of the character sequence represented by
* this string; <code>false</code> otherwise.
* Note also that <code>true</code> will be returned if the
* argument is an empty string or is equal to this
* <code>String</code> 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</code> if the character sequence represented by the
* argument is a suffix of the character sequence represented by
* this object; <code>false</code> otherwise. Note that the
* result will be <code>true</code> if the argument is the
* empty string or is equal to this <code>String</code> object
* as determined by the {@link #equals(Object)} method.
*/
public boolean endsWith(String suffix) {
return startsWith(suffix, count - suffix.count);
}
/**
* Returns a hash code for this string. The hash code for a
* <code>String</code> object is computed as
* <blockquote><pre>
* s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
* </pre></blockquote>
* using <code>int</code> arithmetic, where <code>s[i]</code> is the
* <i>i</i>th character of the string, <code>n</code> is the length of
* the string, and <code>^</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) {
int off = offset;
char val[] = value;
int len = count;
for (int i = 0; i < len; i++) {
h = 31*h + val[off++];
}
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</code> occurs
* in the character sequence represented by this <code>String</code>
* object, then the index of the first such occurrence is returned --
* that is, the smallest value <i>k</i> such that:
* <blockquote><pre>
* this.charAt(<i>k</i>) == ch
* </pre></blockquote>
* is <code>true</code>. If no such character occurs in this string,
* then <code>-1</code> is returned.
*
* @param ch a character.
* @return the index of the first occurrence of the character in the
* character sequence represented by this object, or
* <code>-1</code> 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</code> occurs in the character
* sequence represented by this <code>String</code> object at an index
* no smaller than <code>fromIndex</code>, then the index of the first
* such occurrence is returned--that is, the smallest value <i>k</i>
* such that:
* <blockquote><pre>
* (this.charAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
* </pre></blockquote>
* is true. If no such character occurs in this string at or after
* position <code>fromIndex</code>, then <code>-1</code> is returned.
* <p>
* There is no restriction on the value of <code>fromIndex</code>. 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</code> is returned.
*
* @param ch a character.
* @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</code>, or <code>-1</code>
* if the character does not occur.
*/
public int indexOf(int ch, int fromIndex) {
int max = offset + count;
char v[] = value;
if (fromIndex < 0) {
fromIndex = 0;
} else if (fromIndex >= count) {
// Note: fromIndex might be near -1>>>1.
return -1;
}
for (int i = offset + fromIndex ; i < max ; i++) {
if (v[i] == ch) {
return i - offset;
}
}
return -1;
}
/**
* Returns the index within this string of the last occurrence of the
* specified character. That is, the index returned is the largest
* value <i>k</i> such that:
* <blockquote><pre>
* this.charAt(<i>k</i>) == ch
* </pre></blockquote>
* is true.
* The String is searched backwards starting at the last character.
*
* @param ch a character.
* @return the index of the last occurrence of the character in the
* character sequence represented by this object, or
* <code>-1</code> if the character does not occur.
*/
public int lastIndexOf(int ch) {
return lastIndexOf(ch, count - 1);
}
/**
* Returns the index within this string of the last occurrence of the
* specified character, searching backward starting at the specified
* index. That is, the index returned is the largest value <i>k</i>
* such that:
* <blockquote><pre>
* this.charAt(k) == ch) && (k <= fromIndex)
* </pre></blockquote>
* is true.
*
* @param ch a character.
* @param fromIndex the index to start the search from. There is no
* restriction on the value of <code>fromIndex</code>. 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</code>, or <code>-1</code>
* if the character does not occur before that point.
*/
public int lastIndexOf(int ch, int fromIndex) {
int min = offset;
char v[] = value;
for (int i = offset + ((fromIndex >= count) ? count - 1 : fromIndex) ; i >= min ; i--) {
if (v[i] == ch) {
return i - offset;
}
}
return -1;
}
/**
* Returns the index within this string of the first occurrence of the
* specified substring. The integer returned is the smallest value
* <i>k</i> such that:
* <blockquote><pre>
* this.startsWith(str, <i>k</i>)
* </pre></blockquote>
* is <code>true</code>.
*
* @param str any string.
* @return if the string argument occurs as a substring within this
* object, then the index of the first character of the first
* such substring is returned; if it does not occur as a
* substring, <code>-1</code> is returned.
*/
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. The integer
* returned is the smallest value <tt>k</tt> for which:
* <blockquote><pre>
* k >= Math.min(fromIndex, str.length()) && this.startsWith(str, k)
* </pre></blockquote>
* If no such value of <i>k</i> exists, then -1 is returned.
*
* @param str the substring for which to search.
* @param fromIndex the index from which to start the search.
* @return the index within this string of the first occurrence of the
* specified substring, starting at the specified index.
*/
public int indexOf(String str, int fromIndex) {
return indexOf(value, offset, count,
str.value, str.offset, str.count, 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 i = sourceOffset + fromIndex;
int max = sourceOffset + (sourceCount - targetCount);
startSearchForFirstChar:
while (true) {
/* Look for first character. */
while (i <= max && source[i] != first) {
i++;
}
if (i > max) {
return -1;
}
/* Found first character, now look at the rest of v2 */
int j = i + 1;
int end = j + targetCount - 1;
int k = targetOffset + 1;
while (j < end) {
if (source[j++] != target[k++]) {
i++;
/* Look for str's first char again. */
continue startSearchForFirstChar;
}
}
return i - sourceOffset; /* Found whole string. */
}
}
/**
* Returns the index within this string of the rightmost occurrence
* of the specified substring. The rightmost empty string "" is
* considered to occur at the index value <code>this.length()</code>.
* The returned index is the largest value <i>k</i> such that
* <blockquote><pre>
* this.startsWith(str, k)
* </pre></blockquote>
* is true.
*
* @param str the substring to search for.
* @return if the string argument occurs one or more times as a substring
* within this object, then the index of the first character of
* the last such substring is returned. If it does not occur as
* a substring, <code>-1</code> is returned.
*/
public int lastIndexOf(String str) {
return lastIndexOf(str, count);
}
/**
* Returns the index within this string of the last occurrence of the
* specified substring, searching backward starting at the specified index.
* The integer returned is the largest value <i>k</i> such that:
* <blockquote><pre>
* k <= Math.min(fromIndex, str.length()) && this.startsWith(str, k)
* </pre></blockquote>
* If no such value of <i>k</i> exists, then -1 is returned.
*
* @param str the substring to search for.
* @param fromIndex the index to start the search from.
* @return the index within this string of the last occurrence of the
* specified substring.
*/
public int lastIndexOf(String str, int fromIndex) {
return lastIndexOf(value, offset, count,
str.value, str.offset, str.count, 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) {
/*
