java String 类源代码

package java.lang;

import java.io.ObjectStreamClass;
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;

 

public final class String
    implements java.io.Serializable, Comparable<String>, CharSequence
{
    /** The value is used for character storage. */
    private final char value[];

    /** The offset is the first index of the storage that is used. */
    private final int offset;

    /** The count is the number of characters in the String. */
    private final int count;

    /** 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:
     * <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.
     */
    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.offset = 0;
    this.count = 0;
    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) {
    int size = original.count;
    char[] originalValue = original.value;
    char[] v;
      if (originalValue.length > size) {
         // 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.
            int off = original.offset;
            v = Arrays.copyOfRange(originalValue, off, off+size);
     } else {
         // The array representing the String is the same
         // size as the String, so no point in making a copy.
        v = originalValue;
     }
    this.offset = 0;
    this.count = size;
    this.value = v;
    }

    /**
     * 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[]) {
    int size = value.length;
    this.offset = 0;
    this.count = size;
    this.value = Arrays.copyOf(value, size);
    }

    /**
     * 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.offset = 0;
        this.count = 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);
        }

    int expansion = 0;
    int margin = 1;
    char[] v = new char[count + margin];
    int x = offset;
    int j = 0;
    for (int i = 0; i < count; i++) {
        int c = codePoints[x++];
        if (c < 0) {
        throw new IllegalArgumentException();
        }
        if (margin <= 0 && (j+1) >= v.length) {
        if (expansion == 0) {
            expansion = (((-margin + 1) * count) << 10) / i;
            expansion >>= 10;
            if (expansion <= 0) {
            expansion = 1;
            }
        } else {
            expansion *= 2;
        }
                int newLen = Math.min(v.length+expansion, count*2);
        margin = (newLen - v.length) - (count - i);
                v = Arrays.copyOf(v, newLen);
        }
        if (c < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
        v[j++] = (char) c;
        } else if (c <= Character.MAX_CODE_POINT) {
        Character.toSurrogates(c, v, j);
        j += 2;
        margin--;
        } else {
        throw new IllegalArgumentException();
        }
    }
    this.offset = 0;
    this.value = v;
    this.count = j;
    }

    /**
     * Allocates a new {@code String} constructed from a subarray of an array
     * of 8-bit integer values.
     *
     * <p> The {@code offset} argument is the index of the first byte of the
     * subarray, and the {@code count} argument specifies the length of the
     * subarray.
     *
     * <p> Each {@code byte} in the subarray is converted to a {@code char} as
     * specified in the method above.
     *
     * @deprecated This method does not properly convert bytes into characters.
     * As of JDK&nbsp;1.1, the preferred way to do this is via the
     * {@code String} constructors that take a {@link
     * java.nio.charset.Charset}, charset name, or that use the platform's
     * default charset.
     *
     * @param  ascii
     *         The bytes to be converted to characters
     *
     * @param  hibyte
     *         The top 8 bits of each 16-bit Unicode code unit
     *
     * @param  offset
     *         The initial offset
     * @param  count
     *         The length
     *
     * @throws  IndexOutOfBoundsException
     *          If the {@code offset} or {@code count} argument is invalid
     *
     * @see  #String(byte[], int)
     * @see  #String(byte[], int, int, java.lang.String)
     * @see  #String(byte[], int, int, java.nio.charset.Charset)
     * @see  #String(byte[], int, int)
     * @see  #String(byte[], java.lang.String)
     * @see  #String(byte[], java.nio.charset.Charset)
     * @see  #String(byte[])
     */
    @Deprecated
    public String(byte ascii[], int hibyte, int offset, int count) {
    checkBounds(ascii, offset, count);
        char value[] = new char[count];

        if (hibyte == 0) {
            for (int i = count ; i-- > 0 ;) {
                value[i] = (char) (ascii[i + offset] & 0xff);
            }
        } else {
            hibyte <<= 8;
            for (int i = count ; i-- > 0 ;) {
                value[i] = (char) (hibyte | (ascii[i + offset] & 0xff));
            }
        }
    this.offset = 0;
    this.count = count;
    this.value = value;
    }

    /**
     * Allocates a new {@code String} containing characters constructed from
     * an array of 8-bit integer values. Each character <i>c</i>in the
     * resulting string is constructed from the corresponding component
     * <i>b</i> in the byte array such that:
     *
     * <blockquote><pre>
     *     <b><i>c</i></b> == (char)(((hibyte &amp; 0xff) &lt;&lt; 8)
     *                         | (<b><i>b</i></b> &amp; 0xff))
     * </pre></blockquote>
     *
     * @deprecated  This method does not properly convert bytes into
     * characters.  As of JDK&nbsp;1.1, the preferred way to do this is via the
     * {@code String} constructors that take a {@link
     * java.nio.charset.Charset}, charset name, or that use the platform's
     * default charset.
     *
     * @param  ascii
     *         The bytes to be converted to characters
     *
     * @param  hibyte
     *         The top 8 bits of each 16-bit Unicode code unit
     *
     * @see  #String(byte[], int, int, java.lang.String)
     * @see  #String(byte[], int, int, java.nio.charset.Charset)
     * @see  #String(byte[], int, int)
     * @see  #String(byte[], java.lang.String)
     * @see  #String(byte[], java.nio.charset.Charset)
     * @see  #String(byte[])
     */
    @Deprecated
    public String(byte ascii[], int hibyte) {
        this(ascii, hibyte, 0, ascii.length);
    }

    /* Common private utility method used to bounds check the byte array
     * and requested offset & length values used by the String(byte[],..)
     * constructors.
     */
    private static void checkBounds(byte[] bytes, int offset, int length) {
    if (length < 0)
        throw new StringIndexOutOfBoundsException(length);
    if (offset < 0)
        throw new StringIndexOutOfBoundsException(offset);
    if (offset > bytes.length - length)
        throw new StringIndexOutOfBoundsException(offset + length);
    }