String源码分析

直接进入正题，看源码：

String类里面用来存储value的是一个final数组，不允许修改

 /** The value is used for character storage. */
    private final char value[];

字符串长度

就是返回value数组的长度

 /**
     * Returns the length of this string.
     * The length is equal to the number of <a href="Character.html#unicode">Unicode
     * code units</a> in the string.
     *
     * @return  the length of the sequence of characters represented by this
     *          object.
     */
     
    public int length() {
        return value.length;
    }

返回字符串中某一个位置的字符

 public char charAt(int index) {
 //1.首先判断是否越界
        if ((index < 0) || (index >= value.length)) {
            throw new StringIndexOutOfBoundsException(index);
        }
        //2.返回指定位置的值
        return value[index];
    }

字符串比较

• equals(Object anObject)

public boolean equals(Object anObject) {
//1.首先判断引用是否相同
        if (this == anObject) {
            return true;
        }
        //2.是否String实例（instanceof判断实例是否相同）
        if (anObject instanceof String) {
        //3.为什么要实例一个新的String？
            String anotherString = (String)anObject;
            int n = value.length;
            //4.长度是否相同
            if (n == anotherString.value.length) {
                char v1[] = value;
                char v2[] = anotherString.value;
                int i = 0;
                //5.逐个字符进行比较
                while (n-- != 0) {
                    if (v1[i] != v2[i])
                        return false;
                    i++;
                }
                return true;
            }
        }
        return false;
    }

• equalsIgnoreCase(String anotherString)

与equals方法相似，但忽略大小写

public static int toUpperCase(int codePoint) {
    return CharacterData.of(codePoint).toUpperCase(codePoint);
}

//1.ignoreCase参数？
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;
}

• compareTo(String anotherString)

当前对象比参数大则返回正整数，反之返回负整数，相等返回0

 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;
        //1.逐个比较
        while (k < lim) {
            char c1 = v1[k];
            char c2 = v2[k];
            if (c1 != c2) {
                return c1 - c2;
            }
            k++;
        }
        //2.当前对象较长则返回的是正整数，反之则是负整数
        return len1 - len2;
    }

• compareToIgnoreCase(String str)

和compareTo方法类似，忽略了字符的大小写

public int compareToIgnoreCase(String str) {
    return CASE_INSENSITIVE_ORDER.compare(this, str);
}

//1.暂时不懂为什么要用一个内部类
public static final Comparator<String> CASE_INSENSITIVE_ORDER
                                         = new CaseInsensitiveComparator();
    private static class CaseInsensitiveComparator
            implements Comparator<String>, java.io.Serializable {
        // use serialVersionUID from JDK 1.2.2 for interoperability
        private static final long serialVersionUID = 8575799808933029326L;

        public int compare(String s1, String s2) {
            int n1 = s1.length();
            int n2 = s2.length();
            int min = Math.min(n1, n2);
            for (int i = 0; i < min; i++) {
                char c1 = s1.charAt(i);
                char c2 = s2.charAt(i);
                if (c1 != c2) {
                    c1 = Character.toUpperCase(c1);
                    c2 = Character.toUpperCase(c2);
                    if (c1 != c2) {
                        c1 = Character.toLowerCase(c1);
                        c2 = Character.toLowerCase(c2);
                        if (c1 != c2) {
                            // No overflow because of numeric promotion
                            return c1 - c2;
                        }
                    }
                }
            }
            return n1 - n2;
        }

        /** Replaces the de-serialized object. */
        private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
    }
    

字符串拼接

构建一个新的数组，将原字符串放在前面，再将需要连接的字符串放在后面

    public String concat(String str) {
        int otherLen = str.length();
        //1.如果要连接的字符串长度为0则...
        if (otherLen == 0) {
            return this;
        }
        int len = value.length;
        //2.构建一个数组，长度为len+otherLen，数组前面的值为value
        char buf[] = Arrays.copyOf(value, len + otherLen);
        //3.将str拼接到buf数组后面
        str.getChars(buf, len);
        return new String(buf, true);
    }
    
    void getChars(char dst[], int dstBegin) {
        System.arraycopy(value, 0, dst, dstBegin, value.length);
    }
    
    String(char[] value, boolean share) {
        // assert share : "unshared not supported";
        this.value = value;
    }

截取字符串中的一段

• substring(int beginIndex)
  返回一个新的字符串，从beginIndex处开始截取到末尾

public String substring(int beginIndex) {
     //1.入参越界判断
    if (beginIndex < 0) {
        throw new StringIndexOutOfBoundsException(beginIndex);
    }
    int subLen = value.length - beginIndex;
    if (subLen < 0) {
        throw new StringIndexOutOfBoundsException(subLen);
    }
    //2.new一个新的字符串
    return (beginIndex == 0) ? this : new String(value, beginIndex, subLen);
}

• substring(int beginIndex, int endIndex)
  和上一个方法类似，具体看源码

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);
    }

清除字符串两边的空格

注意下列代码中/* avoid getfield opcode */那句代码，注释的意思是避免getfield操作

查阅后得知，getfield操作的含义是“获取指定类的实例域，并将其值压入栈顶”
具体可以看该篇博客
https://blog.csdn.net/gaopu12345/article/details/52084218

    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;
    }

替换

替换字符串中某个字符，返回新的字符串

   public String replace(char oldChar, char newChar) {
        //1.判断新旧字符
        if (oldChar != newChar) {
            int len = value.length;
            int i = -1;
            char[] val = value; /* avoid getfield opcode */

            while (++i < len) {
                if (val[i] == oldChar) {
                    break;
                }
            }
            //2.在字符串中找到要替换的字符后才会继续
            if (i < len) {
            //3.构建一个新的字符串
                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;
    }

查找

• indexOf(int ch)
  返回从头开始该字符第一次出现的位置，实际上调用的是indexOf(int ch, int fromIndex)方法，源码如下

    public int indexOf(int ch) {
        return indexOf(ch, 0);
    }

• indexOf(int ch, int fromIndex)

    public int indexOf(int ch, int fromIndex) {
        final int max = value.length;
        //1.入参越界判断
        if (fromIndex < 0) {
            fromIndex = 0;
        } else if (fromIndex >= max) {
            // Note: fromIndex might be near -1>>>1.
            return -1;
        }
        
        //2.处理常用字符
        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 {
        //3.处理不常用字符
            return indexOfSupplementary(ch, fromIndex);
        }
    }
    
        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;
    }

• lastIndexOf(int ch)和lastIndexOf(int ch, int fromIndex)
  和上面的两个方法类似，不过返回的是最后一次出现该字符的位置

    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);
        }
    }
    
    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;
    }

查找字符串

• indexOf(String str)
  返回从头开始第一次出现该字符串的第一个字符的位置

    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,
            char[] target, int targetOffset, int targetCount,
            int fromIndex) {
        //1.入参检查
        if (fromIndex >= sourceCount) {
            return (targetCount == 0 ? sourceCount : -1);
        }
        if (fromIndex < 0) {
            fromIndex = 0;
        }
        if (targetCount == 0) {
            return fromIndex;
        }
        //2.记下第一个字符
        char first = target[targetOffset];
        //3.所需遍历的最长单位 例如："beautiful"-"ti"则8-1=7
        int max = sourceOffset + (sourceCount - targetCount);

        for (int i = sourceOffset + fromIndex; i <= max; i++) {
            /* Look for first character. */
            //4.首先找到与以第一个字符匹配的位置
            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;
    }

• lastIndexOf(String str)

    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,
            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;
        }
    }

判断字符串是否以某个字符串开头

    public boolean startsWith(String prefix) {
        return startsWith(prefix, 0);
    }

    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;
    }

判断字符串是否以某个字符串结尾

对上一段代码的重用

    public boolean endsWith(String suffix) {
        return startsWith(suffix, value.length - suffix.value.length);
    }

其他类型转换成字符串类型

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

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

总结

• 从源码中可以看出，当对String类型的字符串进行修改的时候，都是构建一个新的字符串，这样会造成很多垃圾，所以当需要对字符串频繁的修改时，尽量不去使用String，而是使用StringBuffer或StringBuilder

• 源码中的/* avoid getfield opcode */这种思想值得我学习一下