JDK1.8源码学习--002、java.lang.String


/**
 * 说明:
 * 被 final 修饰符的修饰的类不允许被其他类继承。所以 String 是不能被我们继承的。
 */
public final class String
        implements java.io.Serializable, Comparable<String>, CharSequence {

    /**
     * 说明:char属性
     * 该值用于字符存储、
     * 从JDK9开始,String对象不再以char[]形式存储,而是以名为value的byte[]形式存储。
     */
    /** The value is used for character storage. */
    private final char value[];


    /**
     * 说明:hash属性
     * 缓存字符串的哈希码、
     */
    /** Cache the hash code for the string */
    private int hash; // Default to 0

    /**
     * 说明:serialVersionUID属性
     * 序列化ID
     */
    /** use serialVersionUID from JDK 1.0.2 for interoperability */
    private static final long serialVersionUID = -6849794470754667710L;

    /**
     * Class String is special cased within the Serialization Stream Protocol.
     *
     * A String instance is written into an ObjectOutputStream according to
     * <a href="{@docRoot}/../platform/serialization/spec/output.html">
     * Object Serialization Specification, Section 6.2, "Stream Elements"</a>
     */
    /**
     * 说明:
     * 用于指定哪些字段需要被默认序列化
     */
    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.
     */
    /**
     * 说明:String构造方法
     * 一共有16个、有二个标识为@Deprecated、就是不建议使用、因为String是不可变的。所以构造方法会很多
     * 下面这个构造作用:创建空字符序列
     */
    public String() {
        this.value = "".value;
    }

    /**
     * Initializes a newly created {@code String} object so that it represents
     * the same sequence of characters as the argument; in other words, the
     * newly created string is a copy of the argument string. Unless an
     * explicit copy of {@code original} is needed, use of this constructor is
     * unnecessary since Strings are immutable.
     *
     * @param  original
     *         A {@code String}
     */
    /**
     * 说明:作用
     * 使用字符串类型的对象来初始化
     * @param original
     */
    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
     */
    /**
     * 说明:字符数组构造方法、传一个字符数组、 Arrays.copyOf 方法或 Arrays.copyOfRange 方法。
     * 这两个方法是将原有的字符数组中的内容逐一的复制到 String 中的字符数组中。会创建一个新的字符串对象
     * 所以随后对于该字符数组的修改不会影响新创建的字符串
     * @param value
     */
    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
     */
    /**
     * 说明:功能同上、offset起始位置(起始偏移量)、count(长度)、
     * @param value
     * @param offset
     * @param count
     */
    public String(char value[], int offset, int count) {
        if (offset < 0) {
            throw new StringIndexOutOfBoundsException(offset);
        }
        if (count <= 0) {
            if (count < 0) {
                throw new StringIndexOutOfBoundsException(count);
            }
            if (offset <= value.length) {
                this.value = "".value;
                return;
            }
        }
        // Note: offset or count might be near -1>>>1.
        if (offset > value.length - count) {
            throw new StringIndexOutOfBoundsException(offset + count);
        }
        this.value = Arrays.copyOfRange(value, offset, offset+count);
    }


    /**
     * 说明:参数为int数组、起始位置、长度
     * @param codePoints
     * @param offset
     * @param count
     */
    public String(int[] codePoints, int offset, int count) {
        if (offset < 0) {
            throw new StringIndexOutOfBoundsException(offset);
        }
        if (count <= 0) {
            if (count < 0) {
                throw new StringIndexOutOfBoundsException(count);
            }
            if (offset <= codePoints.length) {
                this.value = "".value;
                return;
            }
        }
        // Note: offset or count might be near -1>>>1.
        if (offset > codePoints.length - count) {
            throw new StringIndexOutOfBoundsException(offset + count);
        }

        final int end = offset + count;

        // Pass 1: Compute precise size of char[]
        //计算数组长度
        int n = count;
        for (int i = offset; i < end; i++) {
            int c = codePoints[i];
            if (Character.isBmpCodePoint(c))
                continue;
            //代码点是否是一个有效的Unicode代码点值
            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];

        //如果unicode字符属于BMP、就存入字符数组、
        //如果unicode字符是增补字符、需要用两个char来表示 Character.toSurrogates(c, v, j++)
        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;
    }


    @Deprecated
    public String(byte ascii[], int hibyte, int offset, int count) {
        checkBounds(ascii, offset, count);
        char value[] = new char[count];

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


    @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.
     */

    /**
     * 说明:检查字节长度的合法性
     * StringIndexOutOfBoundsException :字符下标越界异常
     * @param bytes
     * @param offset
     * @param length
     */
    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);
    }


    /**
     * 说明:字节数组构造方法、字节数组转成字符串要进行转码
     * @param bytes
     * @param offset
     * @param length
     * @param charsetName
     * @throws UnsupportedEncodingException
     *
     * StringCoding.decode、解码
     * StringCoding.encode、编码
     */
    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);
    }


    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);
    }


    /**
     * 说明:
     * this():调用自已无参构造方法
     * @param bytes
     * @param charsetName
     * @throws UnsupportedEncodingException
     */
    public String(byte bytes[], String charsetName) throws UnsupportedEncodingException {
        this(bytes, 0, bytes.length, charsetName);
    }


    public String(byte bytes[], Charset charset) {
        this(bytes, 0, bytes.length, charset);
    }


    public String(byte bytes[], int offset, int length) {
        checkBounds(bytes, offset, length);
        this.value = StringCoding.decode(bytes, offset, length);
    }


    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}
     */
    /**
     * 说明:将StringBuffer转为String、线程安全
     * Arrays.copyOf功能是实现数组的复制,返回复制后的数组。参数是被复制的数组和复制的长度
     * @param buffer
     */
    public String(StringBuffer buffer) {
        synchronized(buffer) {
            this.value = Arrays.copyOf(buffer.getValue(), buffer.length());
        }
    }


    /**
     * 说明:将StringBuilder 转为String
     * @param builder
     */
    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;
    }

    /**
     * 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.
     */
    /**
     * 说明:方法length()、获取字符串的长度
     * @return
     */
    public int length() {
        return value.length;
    }

    /**
     * Returns {@code true} if, and only if, {@link #length()} is {@code 0}.
     *
     * @return {@code true} if {@link #length()} is {@code 0}, otherwise
     * {@code false}
     *
     * @since 1.6
     */
    /**
     * 说明:判断字符串长度是否为0
     * @return
     */
    public boolean isEmpty() {
        return value.length == 0;
    }


    /**
     * 说明:给定下标, 返回该下标对应的字符数据.
     * @param index
     * @return
     */
    public char charAt(int index) {
        if ((index < 0) || (index >= value.length)) {
            throw new StringIndexOutOfBoundsException(index);
        }
        return value[index];
    }


    /**
     * 返回指定索引处的字符(Unicode代码点)。
     * @param index
     * @return
     */
    public int codePointAt(int index) {
        if ((index < 0) || (index >= value.length)) {
            throw new StringIndexOutOfBoundsException(index);
        }
        return Character.codePointAtImpl(value, index, value.length);
    }


    /**
     * 返回指定索引之前的字符(Unicode代码点)。
     * @param index
     * @return
     */
    public int codePointBefore(int index) {
        int i = index - 1;
        if ((i < 0) || (i >= value.length)) {
            throw new StringIndexOutOfBoundsException(index);
        }
        return Character.codePointBeforeImpl(value, index, 0);
    }


    /**
     * 返回此 String 的指定文本范围中的 Unicode 代码点数。
     * @param beginIndex
     * @param endIndex
     * @return
     */
    public int codePointCount(int beginIndex, int endIndex) {
        if (beginIndex < 0 || endIndex > value.length || beginIndex > endIndex) {
            throw new IndexOutOfBoundsException();
        }
        return Character.codePointCountImpl(value, beginIndex, endIndex - beginIndex);
    }


    /**
     * 返回此 String 中从给定的 index 处偏移 codePointOffset 个代码点的索引
     * @param index
     * @param codePointOffset
     * @return
     */
    public int offsetByCodePoints(int index, int codePointOffset) {
        if (index < 0 || index > value.length) {
            throw new IndexOutOfBoundsException();
        }
        return Character.offsetByCodePointsImpl(value, 0, value.length,
                index, codePointOffset);
    }

    /**
     * Copy characters from this string into dst starting at dstBegin.
     * This method doesn't perform any range checking.
     */
    /**
     * 说明:  将字符从此字符串复制到目标字符数组。
     * @param dst
     * @param dstBegin
     */
    void getChars(char dst[], int dstBegin) {
        System.arraycopy(value, 0, dst, dstBegin, value.length);
    }


    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);
    }


    @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++];
        }
    }


    /**
     * 说明: 使用指定的字符集将此 String 编码为 byte 序列,并将结果存储到一个新的 byte 数组中
     * @param charsetName
     * @return
     * @throws UnsupportedEncodingException
     */
    public byte[] getBytes(String charsetName)
            throws UnsupportedEncodingException {
        if (charsetName == null) throw new NullPointerException();
        return StringCoding.encode(charsetName, value, 0, value.length);
    }


    /**
     * 说明: 使用给定的 charset 将此 String 编码到 byte 序列,并将结果存储到新的 byte 数组
     * @param charset
     * @return
     */
    public byte[] getBytes(Charset charset) {
        if (charset == null) throw new NullPointerException();
        return StringCoding.encode(charset, value, 0, value.length);
    }

    /**
     * Encodes this {@code String} into a sequence of bytes using the
     * platform's default charset, storing the result into a new byte array.
     *
     * <p> The behavior of this method when this string cannot be encoded in
     * the default charset is unspecified.  The {@link
     * java.nio.charset.CharsetEncoder} class should be used when more control
     * over the encoding process is required.
     *
     * @return  The resultant byte array
     *
     * @since      JDK1.1
     */
    public byte[] getBytes() {
        return StringCoding.encode(value, 0, value.length);
    }

    /**
     * 说明: 将此字符串与指定的对象比较。
     * @param anObject
     * @return
     */
    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;
    }



    /**
     * 说明:将此字符串与指定的 StringBuffer 比较
     * @param sb
     * @return
     */
    public boolean contentEquals(StringBuffer sb) {
        return contentEquals((CharSequence)sb);
    }

    /**
     * 说明:私有类、比较二个字符串是否相同、先判字符数组长度是否相等,再逐一进行比较。
     * AbstractStringBuilder这个抽象类是StringBuilder和StringBuffer的直接父类
     * @param sb
     * @return
     */
    private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
        char v1[] = value;
        char v2[] = sb.getValue();
        int n = v1.length;
        if (n != sb.length()) {
            return false;
        }
        for (int i = 0; i < n; i++) {
            if (v1[i] != v2[i]) {
                return false;
            }
        }
        return true;
    }


    /**
     * 说明:将此字符串与指定的 CharSequence 比较
     * CharSequence是一个接口,它只包括length(), charAt(int index),
     * subSequence(int start,int end)这几个API接口。除了String实现了CharSequence之外,
     * StringBuffer和StringBuilder也实现了 CharSequence接口。
     * @param cs
     * @return
     */
    public boolean contentEquals(CharSequence cs) {
        // Argument is a StringBuffer, StringBuilder
        if (cs instanceof AbstractStringBuilder) {
            if (cs instanceof StringBuffer) {
                synchronized(cs) {
                    return nonSyncContentEquals((AbstractStringBuilder)cs);
                }
            } else {
                return nonSyncContentEquals((AbstractStringBuilder)cs);
            }
        }
        // Argument is a String
        if (cs instanceof String) {
            return equals(cs);
        }
        // Argument is a generic CharSequence
        char v1[] = value;
        int n = v1.length;
        if (n != cs.length()) {
            return false;
        }
        for (int i = 0; i < n; i++) {
            if (v1[i] != cs.charAt(i)) {
                return false;
            }
        }
        return true;
    }


    /**
     * 说明:将此 String 与另一个 String 比较,不考虑大小写。
     * @param anotherString
     * @return
     */
    public boolean equalsIgnoreCase(String anotherString) {
        return (this == anotherString) ? true
                : (anotherString != null)
                && (anotherString.value.length == value.length)
                && regionMatches(true, 0, anotherString, 0, value.length);
    }

    /**
     * 说明: 按字典顺序比较两个字符串
     * @param anotherString
     * @return
     * 首先取出两个字符串的长度,比较较小的长度内,两者是否相等。
     * 若不相等,则直接返回该位置字符的ASCII码相减后的值。
     * 若各位置都相等,则将两个字符串长度的差值返回。
     */
    public int compareTo(String anotherString) {
        int len1 = value.length;
        int len2 = anotherString.value.length;
        int lim = Math.min(len1, len2);
        char v1[] = value;
        char v2[] = anotherString.value;

        int k = 0;
        while (k < lim) {
            char c1 = v1[k];
            char c2 = v2[k];
            if (c1 != c2) {
                return c1 - c2;
            }
            k++;
        }
        return len1 - len2;
    }

    /**
     * A Comparator that orders {@code String} objects as by
     * {@code compareToIgnoreCase}. This comparator is serializable.
     * <p>
     * Note that this Comparator does <em>not</em> take locale into account,
     * and will result in an unsatisfactory ordering for certain locales.
     * The java.text package provides <em>Collators</em> to allow
     * locale-sensitive ordering.
     *
     * @see     java.text.Collator#compare(String, String)
     * @since   1.2
     */
    public static final Comparator<String> CASE_INSENSITIVE_ORDER = new CaseInsensitiveComparator();

    private static class CaseInsensitiveComparator implements Comparator<String>, java.io.Serializable {


        // use serialVersionUID from JDK 1.2.2 for interoperability
        /**
         * 说明:serialVersionUID属性
         * Java的序列化机制是通过在运行时判断类的serialVersionUID来验证版本一致性的。在进行反序列化时,
         * JVM会把传来的字节流中的serialVersionUID与本地相应实体(类)的serialVersionUID进行比较,
         * 如果相同就认为是一致的,可以进行反序列化,否则就会出现序列化版本不一致的异常。(InvalidCastException)
         */
        private static final long serialVersionUID = 8575799808933029326L;

        /**
         * 说明:忽略大小写比较器、根据源字符串是小于、等于或大于目标字符串来返回负整数、零或正整数
         * Java为了针对Georgian(格鲁吉亚)字母表奇怪的大小写转换规则而专门又增加了一步判断,就是转换成小写再比较一次
         * @param s1
         * @param s2
         * @return
         */
        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; }
    }


    /**
     * 说明:按字典顺序比较两个字符串、忽略大小写
     * @param str
     * @return
     */
    public int compareToIgnoreCase(String str) {
        return CASE_INSENSITIVE_ORDER.compare(this, str);
    }


    /**
     * 说明:测试两个字符串区域是否相等
     * @param toffset
     * @param other
     * @param ooffset
     * @param len
     * @return
     */
    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;
    }


    public boolean regionMatches(boolean ignoreCase, int toffset,
                                 String other, int ooffset, int len) {
        char ta[] = value;
        int to = toffset;
        char pa[] = other.value;
        int po = ooffset;
        // Note: toffset, ooffset, or len might be near -1>>>1.
        if ((ooffset < 0) || (toffset < 0)
                || (toffset > (long)value.length - len)
                || (ooffset > (long)other.value.length - len)) {
            return false;
        }
        while (len-- > 0) {
            char c1 = ta[to++];
            char c2 = pa[po++];
            if (c1 == c2) {
                continue;
            }
            if (ignoreCase) {
                // If characters don't match but case may be ignored,
                // try converting both characters to uppercase.
                // If the results match, then the comparison scan should
                // continue.
                char u1 = Character.toUpperCase(c1);
                char u2 = Character.toUpperCase(c2);
                if (u1 == u2) {
                    continue;
                }
                // Unfortunately, conversion to uppercase does not work properly
                // for the Georgian alphabet, which has strange rules about case
                // conversion.  So we need to make one last check before
                // exiting.
                if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
                    continue;
                }
            }
            return false;
        }
        return true;
    }


    /**
     * 说明: 测试此字符串从指定索引开始的子字符串是否以指定前缀开始。
     * @param prefix
     * @param toffset
     * @return
     */
    public boolean startsWith(String prefix, int toffset) {
        char ta[] = value;
        int to = toffset;
        char pa[] = prefix.value;
        int po = 0;
        int pc = prefix.value.length;
        // Note: toffset might be near -1>>>1.
        if ((toffset < 0) || (toffset > value.length - pc)) {
            return false;
        }
        while (--pc >= 0) {
            if (ta[to++] != pa[po++]) {
                return false;
            }
        }
        return true;
    }

    /**
     * Tests if this string starts with the specified prefix.
     *
     * @param   prefix   the prefix.
     * @return  {@code true} if the character sequence represented by the
     *          argument is a prefix of the character sequence represented by
     *          this string; {@code false} otherwise.
     *          Note also that {@code true} will be returned if the
     *          argument is an empty string or is equal to this
     *          {@code String} object as determined by the
     *          {@link #equals(Object)} method.
     * @since   1. 0
     */
    /**
     * 说明:测试此字符串是否以指定的前缀开始。
     * @param prefix
     * @return
     */
    public boolean startsWith(String prefix) {
        return startsWith(prefix, 0);
    }

    /**
     * Tests if this string ends with the specified suffix.
     *
     * @param   suffix   the suffix.
     * @return  {@code true} if the character sequence represented by the
     *          argument is a suffix of the character sequence represented by
     *          this object; {@code false} otherwise. Note that the
     *          result will be {@code true} if the argument is the
     *          empty string or is equal to this {@code String} object
     *          as determined by the {@link #equals(Object)} method.
     */

    /**
     *说明:测试此字符串是否以指定的后缀结束。
     * @param suffix
     * @return
     */
    public boolean endsWith(String suffix) {
        return startsWith(suffix, value.length - suffix.value.length);
    }



    /**
     * 说明:返回字符串的哈希码
     * 可以看到为了避免频繁计算哈希的开销,此处使用了 String 类的hash 属性作为缓存。
     * 在 Java 中,整型数是 32 位的,大小范围为Integer.MIN_VALUE<-->Integer.MAX_VALUE(-2147483648<–>2147483647)
     * 所以一定会有碰撞产生,即不同的字符串对应相同的哈希值。
     * @return
     */
    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;
    }


    /**
     * 说明:返回指定字符在此字符串中第一次出现处的索引
     * @param ch
     * @return
     */
    public int indexOf(int ch) {
        return indexOf(ch, 0);
    }


    public int indexOf(int ch, int fromIndex) {
        final int max = value.length;
        if (fromIndex < 0) {
            fromIndex = 0;
        } else if (fromIndex >= max) {
            // Note: fromIndex might be near -1>>>1.
            return -1;
        }

        if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
            // handle most cases here (ch is a BMP code point or a
            // negative value (invalid code point))
            final char[] value = this.value;
            for (int i = fromIndex; i < max; i++) {
                if (value[i] == ch) {
                    return i;
                }
            }
            return -1;
        } else {
            return indexOfSupplementary(ch, fromIndex);
        }
    }

    /**
     * Handles (rare) calls of indexOf with a supplementary character.
     */
    private int indexOfSupplementary(int ch, int fromIndex) {
        if (Character.isValidCodePoint(ch)) {
            final char[] value = this.value;
            final char hi = Character.highSurrogate(ch);
            final char lo = Character.lowSurrogate(ch);
            final int max = value.length - 1;
            for (int i = fromIndex; i < max; i++) {
                if (value[i] == hi && value[i + 1] == lo) {
                    return i;
                }
            }
        }
        return -1;
    }


    public int lastIndexOf(int ch) {
        return lastIndexOf(ch, value.length - 1);
    }


    public int lastIndexOf(int ch, int fromIndex) {
        if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
            // handle most cases here (ch is a BMP code point or a
            // negative value (invalid code point))
            final char[] value = this.value;
            int i = Math.min(fromIndex, value.length - 1);
            for (; i >= 0; i--) {
                if (value[i] == ch) {
                    return i;
                }
            }
            return -1;
        } else {
            return lastIndexOfSupplementary(ch, fromIndex);
        }
    }

    /**
     * Handles (rare) calls of lastIndexOf with a supplementary character.
     */
    private int lastIndexOfSupplementary(int ch, int fromIndex) {
        if (Character.isValidCodePoint(ch)) {
            final char[] value = this.value;
            char hi = Character.highSurrogate(ch);
            char lo = Character.lowSurrogate(ch);
            int i = Math.min(fromIndex, value.length - 2);
            for (; i >= 0; i--) {
                if (value[i] == hi && value[i + 1] == lo) {
                    return i;
                }
            }
        }
        return -1;
    }


    public int indexOf(String str) {
        return indexOf(str, 0);
    }


    public int indexOf(String str, int fromIndex) {
        return indexOf(value, 0, value.length,
                str.value, 0, str.value.length, fromIndex);
    }


    static int indexOf(char[] source, int sourceOffset, int sourceCount,
                       String target, int fromIndex) {
        return indexOf(source, sourceOffset, sourceCount,
                target.value, 0, target.value.length,
                fromIndex);
    }


    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;
    }


    public int lastIndexOf(String str) {
        return lastIndexOf(str, value.length);
    }


    public int lastIndexOf(String str, int fromIndex) {
        return lastIndexOf(value, 0, value.length,
                str.value, 0, str.value.length, fromIndex);
    }


    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);
    }


    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;
        }
    }


    /**
     * 说明:返回一个从beginIndex开始的子字符串
     * @param beginIndex
     * @return
     */
    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);
    }


    /**
     * 说明:返回从beginIndex到endIndex的字符串
     * @param beginIndex
     * @param endIndex
     * @return
     */
    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);
    }


    /**
     * 说明:返回一个新的字符序列,它是此序列的一个子序列
     * @param beginIndex
     * @param endIndex
     * @return
     */
    public CharSequence subSequence(int beginIndex, int endIndex) {
        return this.substring(beginIndex, endIndex);
    }

    /**
     * 说明:将指定的字符串连接到该字符串的末尾。
     * @param str
     * @return
     */
    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);
    }


    /**
     *说明:在字符串中用newChar字符替代oldChar字符,返回一个新的字符串
     * @param oldChar
     * @param newChar
     * @return
     */
    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;
    }


    /**
     * 说明:告诉这个字符串是否匹配给定的 regular expression
     * @param regex
     * @return
     */
    public boolean matches(String regex) {
        return Pattern.matches(regex, this);
    }


    /**
     * 说明:此字符串包含指定的char值序列时,返回true
     * @param s
     * @return
     */
    public boolean contains(CharSequence s) {
        return indexOf(s.toString()) > -1;
    }


    public String replaceFirst(String regex, String replacement) {
        return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
    }

    public String replaceAll(String regex, String replacement) {
        return Pattern.compile(regex).matcher(this).replaceAll(replacement);
    }


    public String replace(CharSequence target, CharSequence replacement) {
        return Pattern.compile(target.toString(), Pattern.LITERAL).matcher(
                this).replaceAll(Matcher.quoteReplacement(replacement.toString()));
    }


    public String[] split(String regex, int limit) {
        /* fastpath if the regex is a
         (1)one-char String and this character is not one of the
            RegEx's meta characters ".$|()[{^?*+\\", or
         (2)two-char String and the first char is the backslash and
            the second is not the ascii digit or ascii letter.
         */
        char ch = 0;
        if (((regex.value.length == 1 &&
                ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
                (regex.length() == 2 &&
                        regex.charAt(0) == '\\' &&
                        (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
                        ((ch-'a')|('z'-ch)) < 0 &&
                        ((ch-'A')|('Z'-ch)) < 0)) &&
                (ch < Character.MIN_HIGH_SURROGATE ||
                        ch > Character.MAX_LOW_SURROGATE))
        {
            int off = 0;
            int next = 0;
            boolean limited = limit > 0;
            ArrayList<String> list = new ArrayList<>();
            while ((next = indexOf(ch, off)) != -1) {
                if (!limited || list.size() < limit - 1) {
                    list.add(substring(off, next));
                    off = next + 1;
                } else {    // last one
                    //assert (list.size() == limit - 1);
                    list.add(substring(off, value.length));
                    off = value.length;
                    break;
                }
            }
            // If no match was found, return this
            if (off == 0)
                return new String[]{this};

            // Add remaining segment
            if (!limited || list.size() < limit)
                list.add(substring(off, value.length));

            // Construct result
            int resultSize = list.size();
            if (limit == 0) {
                while (resultSize > 0 && list.get(resultSize - 1).length() == 0) {
                    resultSize--;
                }
            }
            String[] result = new String[resultSize];
            return list.subList(0, resultSize).toArray(result);
        }
        return Pattern.compile(regex).split(this, limit);
    }


    public String[] split(String regex) {
        return split(regex, 0);
    }


    public static String join(CharSequence delimiter, CharSequence... elements) {
        Objects.requireNonNull(delimiter);
        Objects.requireNonNull(elements);
        // Number of elements not likely worth Arrays.stream overhead.
        StringJoiner joiner = new StringJoiner(delimiter);
        for (CharSequence cs: elements) {
            joiner.add(cs);
        }
        return joiner.toString();
    }


    public static String join(CharSequence delimiter,
                              Iterable<? extends CharSequence> elements) {
        Objects.requireNonNull(delimiter);
        Objects.requireNonNull(elements);
        StringJoiner joiner = new StringJoiner(delimiter);
        for (CharSequence cs: elements) {
            joiner.add(cs);
        }
        return joiner.toString();
    }


    public String toLowerCase(Locale locale) {
        if (locale == null) {
            throw new NullPointerException();
        }

        int firstUpper;
        final int len = value.length;

        /* Now check if there are any characters that need to be changed. */
        scan: {
            for (firstUpper = 0 ; firstUpper < len; ) {
                char c = value[firstUpper];
                if ((c >= Character.MIN_HIGH_SURROGATE)
                        && (c <= Character.MAX_HIGH_SURROGATE)) {
                    int supplChar = codePointAt(firstUpper);
                    if (supplChar != Character.toLowerCase(supplChar)) {
                        break scan;
                    }
                    firstUpper += Character.charCount(supplChar);
                } else {
                    if (c != Character.toLowerCase(c)) {
                        break scan;
                    }
                    firstUpper++;
                }
            }
            return this;
        }

        char[] result = new char[len];
        int resultOffset = 0;  /* result may grow, so i+resultOffset
         * is the write location in result */

        /* Just copy the first few lowerCase characters. */
        System.arraycopy(value, 0, result, 0, firstUpper);

        String lang = locale.getLanguage();
        boolean localeDependent =
                (lang == "tr" || lang == "az" || lang == "lt");
        char[] lowerCharArray;
        int lowerChar;
        int srcChar;
        int srcCount;
        for (int i = firstUpper; i < len; i += srcCount) {
            srcChar = (int)value[i];
            if ((char)srcChar >= Character.MIN_HIGH_SURROGATE
                    && (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
                srcChar = codePointAt(i);
                srcCount = Character.charCount(srcChar);
            } else {
                srcCount = 1;
            }
            if (localeDependent ||
                    srcChar == '\u03A3' || // GREEK CAPITAL LETTER SIGMA
                    srcChar == '\u0130') { // LATIN CAPITAL LETTER I WITH DOT ABOVE
                lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale);
            } else {
                lowerChar = Character.toLowerCase(srcChar);
            }
            if ((lowerChar == Character.ERROR)
                    || (lowerChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
                if (lowerChar == Character.ERROR) {
                    lowerCharArray =
                            ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale);
                } else if (srcCount == 2) {
                    resultOffset += Character.toChars(lowerChar, result, i + resultOffset) - srcCount;
                    continue;
                } else {
                    lowerCharArray = Character.toChars(lowerChar);
                }

                /* Grow result if needed */
                int mapLen = lowerCharArray.length;
                if (mapLen > srcCount) {
                    char[] result2 = new char[result.length + mapLen - srcCount];
                    System.arraycopy(result, 0, result2, 0, i + resultOffset);
                    result = result2;
                }
                for (int x = 0; x < mapLen; ++x) {
                    result[i + resultOffset + x] = lowerCharArray[x];
                }
                resultOffset += (mapLen - srcCount);
            } else {
                result[i + resultOffset] = (char)lowerChar;
            }
        }
        return new String(result, 0, len + resultOffset);
    }


    public String toLowerCase() {
        return toLowerCase(Locale.getDefault());
    }


    public String toUpperCase(Locale locale) {
        if (locale == null) {
            throw new NullPointerException();
        }

        int firstLower;
        final int len = value.length;

        /* Now check if there are any characters that need to be changed. */
        scan: {
            for (firstLower = 0 ; firstLower < len; ) {
                int c = (int)value[firstLower];
                int srcCount;
                if ((c >= Character.MIN_HIGH_SURROGATE)
                        && (c <= Character.MAX_HIGH_SURROGATE)) {
                    c = codePointAt(firstLower);
                    srcCount = Character.charCount(c);
                } else {
                    srcCount = 1;
                }
                int upperCaseChar = Character.toUpperCaseEx(c);
                if ((upperCaseChar == Character.ERROR)
                        || (c != upperCaseChar)) {
                    break scan;
                }
                firstLower += srcCount;
            }
            return this;
        }

        /* 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);
    }


    public String toUpperCase() {
        return toUpperCase(Locale.getDefault());
    }


    public String trim() {
        int len = value.length;
        int st = 0;
        char[] val = value;    /* avoid getfield opcode */

        while ((st < len) && (val[st] <= ' ')) {
            st++;
        }
        while ((st < len) && (val[len - 1] <= ' ')) {
            len--;
        }
        return ((st > 0) || (len < value.length)) ? substring(st, len) : this;
    }

    /**
     * This object (which is already a string!) is itself returned.
     *
     * @return  the string itself.
     */
    public String toString() {
        return this;
    }


    /**
     * 说明:将此字符串转换为新的字符数组。
     * @return
     */
    public char[] toCharArray() {
        // Cannot use Arrays.copyOf because of class initialization order issues
        char result[] = new char[value.length];
        System.arraycopy(value, 0, result, 0, value.length);
        return result;
    }


    public static String format(String format, Object... args) {
        return new Formatter().format(format, args).toString();
    }


    public static String format(Locale l, String format, Object... args) {
        return new Formatter(l).format(format, args).toString();
    }


    public static String valueOf(Object obj) {
        return (obj == null) ? "null" : obj.toString();
    }


    public static String valueOf(char data[]) {
        return new String(data);
    }


    public static String valueOf(char data[], int offset, int count) {
        return new String(data, offset, count);
    }

    public static String copyValueOf(char data[], int offset, int count) {
        return new String(data, offset, count);
    }


    public static String copyValueOf(char data[]) {
        return new String(data);
    }


    public static String valueOf(boolean b) {
        return b ? "true" : "false";
    }


    public static String valueOf(char c) {
        char data[] = {c};
        return new String(data, true);
    }


    public static String valueOf(int i) {
        return Integer.toString(i);
    }


    public static String valueOf(long l) {
        return Long.toString(l);
    }


    public static String valueOf(float f) {
        return Float.toString(f);
    }


    public static String valueOf(double d) {
        return Double.toString(d);
    }


    /**
     * 说明:
     *  jdk1.6中字符串常量池存放在永久代中:
     * 当使用intern()方法时,查询字符串常量池是否存在当前字符串,
     * 若不存在则将当前字符串复制到字符串常量池中,并返回字符串常量池中的引用。
     *
     *   jdk1.7中字符串常量池存放在堆中:
     * 当使用intern()方法时,先查询字符串常量池是否存在当前字符串,
     * 若字符串常量池中不存在则再从堆中查询,然后存储并返回相关引用;
     * 若都不存在则将当前字符串复制到字符串常量池中,并返回字符串常量池中的引用。
     * @return
     */
    public native String intern();
}

 

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值