学习JDK源码：String

Posted 2020-10-15 时光与我恰经过

　　用了好久的Java了，从来没有看过jdk的源码，趁着今天有点时间，拿出了jdk的源码看了下，今天先看了关于String的，毕竟开发中String类型使用最广泛。在我们下载安装jdk的时候，部分源码也已经同时存放在我们电脑里了，具体路径为jdk目录下的src.zip压缩包，解压即可。

java.lang.String

 1 public final class String 2 implements java.io.Serializable, Comparable<String>, CharSequence  

这是String类的声明，很明显它是由final类型声明的，所以它不能被继承，而它又实现了Serializable接口，代表它是可以被序列化的。

接着我们来看看类内部是怎么定义的

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

使用final类型的字符数组存储字符串内容，String初始化后就不能被改变。

有一种写法，String s = “abc”； s = “bcd”；当然这并不是改变了字符串s的值，只是将s指向了一个新的字符串，所以千万不要以为字符串是可以变的。

/** Cache the hash code for the string */
    private int hash; // Default to 0

指定缓存字符串的hash code的值，默认为0

/** use serialVersionUID from JDK 1.0.2 for interoperability */
    private static final long serialVersionUID = -6849794470754667710L;

相当于java类的身份证。主要用于版本控制。
serialVersionUID作用是序列化时保持版本的兼容性，即在版本升级时反序列化仍保持对象的唯一性。
有两种生成方式：
       一个是默认的1L，比如：private static final long serialVersionUID = 1L;
       一个是根据类名、接口名、成员方法及属性等来生成一个64位的哈希字段，比如：
       private static final long serialVersionUID = xxxxL;

/**
     * 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>
     */
    private static final ObjectStreamField[] serialPersistentFields =
        new ObjectStreamField[0];

serialPersistentFields 用于指定哪些字段需要被默认序列化，如：

private static final ObjectStreamField[] serialPersistentFields =    
{  
    new ObjectStreamField("name", String.class),   
    new ObjectStreamField("a", Integer.TYPE)   
}; 

看了String类的构造方法，惊叹不已，源码中有足足15种构造方法，其中最常用的不外乎以下几种

public String(byte bytes[]) {
        this(bytes, 0, bytes.length);
    }
public String(StringBuffer buffer) {
        synchronized(buffer) {
            this.value = Arrays.copyOf(buffer.getValue(), buffer.length());
        }
    }
public String(StringBuilder builder) {
        this.value = Arrays.copyOf(builder.getValue(), builder.length());
    }

再往后看就是String类自身提供的一系列方法了:

// 返回字符串的长度  
    public int length() {
        return value.length;
    }
    // 字符串是否为空
    public boolean isEmpty() {
        return value.length == 0;
    }
    // 字符串目标位置的字符
    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
    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
    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
    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);
    }
//返回从0处开始的第i个Code Point的位置
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);
    }
    //判断两个字符串是否相等
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;
    }
    //不区分大小写的情况下比较两个字符串是否相等
public boolean equalsIgnoreCase(String anotherString) {
        return (this == anotherString) ? true
                : (anotherString != null)
                && (anotherString.value.length == value.length)
                && regionMatches(true, 0, anotherString, 0, value.length);
    }
//计算当前字符串比目标字符串长度大多少
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;
    }

//获取哈希值
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;
    }
//返回某个指定的字符串值在字符串中首次出现的位置
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);
        }
    }
//返回某个指定的字符串值在字符串中最后一次出现的位置
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);
        }
    }
//从指定位置截取字符串直至最后一位
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);
    }
//截取字符串从beginIndex至beginIndex
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);
    }

//字符串拼接
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);
 }
//字符串替换
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;
    }
//判断字符串是否包含在另一个字符串中
public boolean contains(CharSequence s) {
        return indexOf(s.toString()) > -1;
    }
//将目标字符串中匹配的字符全部替换成另一字符串
public String replaceAll(String regex, String replacement) {
        return Pattern.compile(regex).matcher(this).replaceAll(replacement);
    }
//按约定分隔符将目标字符串分割成多个字符串并返回字符串数组
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);
    }