String源码阅读（二）

本篇主要介绍String的部分方法。如没有阅读过一部分，请先阅读第一部分。

//返回value数组的长度，通俗易懂。
public int length() {
        return value.length;
    }

//判断value数组的长度
public boolean isEmpty() {
        return value.length == 0;
    }

 public char charAt(int index) {
        if ((index < 0) || (index >= value.length)) {
            throw new StringIndexOutOfBoundsException(index);
        }
        return value[index];
    }
//调用本地方法将实例成员value中的值复制到从dst数组中（从dstBegin开始复制）
void getChars(char dst[], int dstBegin) {
        System.arraycopy(value, 0, dst, dstBegin, value.length);
    }

//同理，重载方法
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);
    }

//使用StringCoding的encode方法解码，并指明编码方式，返回对应的编码
public byte[] getBytes(String charsetName)
            throws UnsupportedEncodingException {
        if (charsetName == null) throw new NullPointerException();
        return StringCoding.encode(charsetName, value, 0, value.length);
    }

//同理，不过指定的是字符集对象
public byte[] getBytes(Charset charset) {
        if (charset == null) throw new NullPointerException();
        return StringCoding.encode(charset, value, 0, value.length);
    }

//使用默认编码方式解码，ISO编码方式
public byte[] getBytes() {
        return StringCoding.encode(value, 0, value.length);
    }

 

 

equals方法首先会判断两个String是否为同一个对象，如果不是则判断参数中的another是否是String的实例，如果是则比较数组长度，如果长度相等，则比较数组值。

 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;
    }

 

无线程安全限制的内容比较，此方法是私有的并且参数为abstractStringBuilder。

 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;
    }

 

首先判断是否是AbstractStringBuilder的实例，如果是，判断是StringBuffer还是StringBuilder。如果是StringBuffer，则用

synchronized保证线程安全并调用无线程安全限制的内容比较方法。如果是StringBuilder，由于StringBuilder线程安全，则直接调用无线程安全限制的内容比较方法。如果是一个String实例，则调用eaquals方法。如果是一个字符序列实例，则比较长度与内容。

  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;
    }

 

equalsIgnoreCase方法，首先判断是否为同一个字符串，如果是返回true，如果不是，判断another是否为空&&长度是否相等，再通过

regionMatches方法判断。regionMatches方法后面会讲到。

  public boolean equalsIgnoreCase(String anotherString) {
        return (this == anotherString) ? true
                //此处的&&用的很巧妙
                : (anotherString != null)
                && (anotherString.value.length == value.length)
                && regionMatches(true, 0, anotherString, 0, value.length);
    }

 

 

由于实现了compareAble接口，所以要实现compareTo方法。比较方法为使用第一个不一样的字符进行比较，如果字符一样，则使用长度进行比较。

 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;
    }

 

 忽略大小写的比较，使用Comparator接口实现，为防止Georgin奇奇怪怪的大小写，所以转化为小写比对后，再转化成大写比较，再返回差值。

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

 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; }
    }

 

 

从other的ooffest开始，从this的toffset开始，比较长度为len的子串是否相等（不忽略大小写）。 

 

 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;
    }

 

 

//多了一个参数ignoreCase，为true时表示忽略大小写。 最下面，大小写都判断一次，为防止Georgin奇奇怪怪的大小写字符。

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;
    }

 

 

 

//判断this从toffest开始，是否与preffix相等。

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;
    }

 

 

 

//是否以suffix结尾。从value.length - suffix.value.length开始，判断字符串是否相同。

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

 

hash码计算方式为：

s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]

因为31是一个奇质数，所以31*i=32*i-i=(i<<5)-i，这种位移与减法结合的计算相比一般的运算快很多。

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;
    }

 

 

从formIndex开始查找代码点ch对应字符的位置。其中

if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {

判断ch是否在BMPCODE中，也就是是否小于两个字节（java中的char为两个字节），小于两个字节的话可以直接强转为char类型。如果不在BMPCODE中，则调用indexOfSupplementary方法。

 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);
        }
    }

 

 

highSurrogate和lowSurrogate分别为高代理以及低代理。java中的字符为16位的，采用utf-16，共有65536个，但是现在字符早已经超过65536个，于是Unicode规定在65536中拿出2048个规定为Surrogates，让它们两个一组来表示大于65536的字符。

 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;
    }

 

其余的相似重载indexof方法都是对此方法进行的封装，外部不能直接调用此方法。

在source数组中查找是否有target子数组，sourceOffest与sourceCount表示有效值，target同理。formIndex为source数组的查找开始位置，开始位置是相对sourceOffest而言的，比如source长度为5，sourceOffest为1，formIndex为1，那么数组有效位从下标为1开始，formIndex实际上的值在数组下标为2的位置。算法很简单，记录taregt的第一位，找到source与target第一位相等的字符，此字符的下一位与target的下一位比对。如果相等则继续向下比对，直到到达target的相对结束位置，并返回相对sourceOffest的结果位置。如果不相等则i++。返回值也是相对sourceOffest而言的。

 

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;
    }

 

与indexOf思路相同。

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;
        }
    }

 

subString直接返回一个新的String对象。

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);
    }

 

拼接字符串，本质上是合并数组。

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);
    }

 

 

替换字符，如果oldChar==newChar则返回当前对象。对方法做了优化，如果当前对象中没有oldChar的字符，则不建立buf数组。

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;
    }

 

contains直接调用indexOf方法。

public boolean contains(CharSequence s) {
        return indexOf(s.toString()) > -1;
    }