前言
DualPivotQuicksort 源码分析
一、经典快排
传统的快速排序是取一个轴，将数组划分成两部分，将小于该轴的放在左边，大于的放在右边，之后递归两边的数组。
二、双轴快排的优点？
双轴故名思意，用两个轴将原来的两个分区变为三个，相比之前的快排能多确定一个区间，并且引入多个轴，减小了最坏情况的概率（最大或最小）。
三、开始之前
在读懂源码之前先好好理解下面这个图（copy自jdk1.8源码之中的，下面也有）/*
* Partitioning:
*
* left part center part right part
* +--------------------------------------------------------------+
* | < pivot1 | pivot1 <= && <= pivot2 | ? | > pivot2 |
* +--------------------------------------------------------------+
* ^ ^ ^
* | | |
* less k great
*
* Invariants:
*
* all in (left, less) < pivot1
* pivot1 <= all in [less, k) <= pivot2
* all in (great, right) > pivot2
*
* Pointer k is the first index of ?-part.
*/
四、参数
/**
* Prevents instantiation.
*/
private DualPivotQuicksort() {}
/*
* Tuning parameters.
*/
/**
* 归并排序的最大有序分组.
*/
private static final int MAX_RUN_COUNT = 67;
/**
* 相同元素多就用快排取代归并.
*/
private static final int MAX_RUN_LENGTH = 33;
/**
* 如果需要排序的Array长度小于该常量，则使用快速排序
*/
private static final int QUICKSORT_THRESHOLD = 286;
/**
* 如果需要排序的Array长度小于该值，优先使用插入排序
*/
private static final int INSERTION_SORT_THRESHOLD = 47;
/**
* If the length of a byte array to be sorted is greater than this
* constant, counting sort is used in preference to insertion sort.
*/
private static final int COUNTING_SORT_THRESHOLD_FOR_BYTE = 29;
/**
* If the length of a short or char array to be sorted is greater
* than this constant, counting sort is used in preference to Quicksort.
*/
private static final int COUNTING_SORT_THRESHOLD_FOR_SHORT_OR_CHAR = 3200;
五、归并排序
JDK代码如下：
/**
* Sorts the specified range of the array using the given
* workspace array slice if possible for merging
*
* @param a the array to be sorted
* @param left the index of the first element, inclusive, to be sorted
* @param right the index of the last element, inclusive, to be sorted
* @param work a workspace array (slice)
* @param workBase origin of usable space in work array
* @param workLen usable size of work array
*/
static void sort(int[] a, int left, int right,
int[] work, int workBase, int workLen) {
// 长度小于286的优先使用快速排序
if (right - left < QUICKSORT_THRESHOLD) {
sort(a, left, right, true);
return;
}
/*
* Index run[i] is the start of i-th run
* (ascending or descending sequence).
*/
int[] run = new int[MAX_RUN_COUNT + 1];
int count = 0; run[0] = left;
// 检查数组附近都是近似有序的，决定到底使用快排还是归并
for (int k = left; k < right; run[count] = k) {
if (a[k] < a[k + 1]) { // 升序
while (++k <= right && a[k - 1] <= a[k]);
} else if (a[k] > a[k + 1]) { // 降序
while (++k <= right && a[k - 1] >= a[k]);
//反转
for (int lo = run[count] - 1, hi = k; ++lo < --hi; ) {
int t = a[lo]; a[lo] = a[hi]; a[hi] = t;
}
} else { // equal
for (int m = MAX_RUN_LENGTH; ++k <= right && a[k - 1] == a[k]; ) {
if (--m == 0) {
sort(a, left, right, true);
return;
}
}
}
/*
* 数组不是高度有序的使用快速排序
*/
if (++count == MAX_RUN_COUNT) {
sort(a, left, right, true);
return;
}
}
// 检查特殊情况
// 实现说明：变量“right”增加1。
if (run[count] == right++) { // 包含一个对象
run[++count] = right;
} else if (count == 1) { // 已经是有序的
return;
}
//归并排序 没啥好说的了
// Determine alternation base for merge
byte odd = 0;
for (int n = 1; (n <<= 1) < count; odd ^= 1);
// Use or create temporary array b for merging
int[] b; // temp array; alternates with a
int ao, bo; // array offsets from 'left'
int blen = right - left; // space needed for b
if (work == null || workLen < blen || workBase + blen > work.length) {
work = new int[blen];
workBase = 0;
}
if (odd == 0) {
System.arraycopy(a, left, work, workBase, blen);
b = a;
bo = 0;
a = work;
ao = workBase - left;
} else {
b = work;
ao = 0;
bo = workBase - left;
}
// Merging
for (int last; count > 1; count = last) {
for (int k = (last = 0) + 2; k <= count; k += 2) {
int hi = run[k], mi = run[k - 1];
for (int i = run[k - 2], p = i, q = mi; i < hi; ++i) {
if (q >= hi || p < mi && a[p + ao] <= a[q + ao]) {
b[i + bo] = a[p++ + ao];
} else {
b[i + bo] = a[q++ + ao];
}
}
run[++last] = hi;
}
if ((count & 1) != 0) {
for (int i = right, lo = run[count - 1]; --i >= lo;
b[i + bo] = a[i + ao]
);
run[++last] = right;
}
int[] t = a; a = b; b = t;
int o = ao; ao = bo; bo = o;
}
}
六、双轴快排
JDK代码如下：
/**
* Sorts the specified range of the array by Dual-Pivot Quicksort.
*
* @param a the array to be sorted
* @param left the index of the first element, inclusive, to be sorted
* @param right the index of the last element, inclusive, to be sorted
* @param leftmost indicates if this part is the leftmost in the range 是否最左
*/
private static void sort(int[] a, int left, int right, boolean leftmost) {
int length = right - left + 1;
// 长度小于47的，使用插入排序
if (length < INSERTION_SORT_THRESHOLD) {
//是否最左，对于最左的理解：下面的快排最左边的值都小于别的分区
//这样做可以省去左侧边界检查if (j-- == left)，经过第一遍排序之后，左边一定小于右边。
if (leftmost) {
/*
* 传统插入排序
*/
for (int i = left, j = i; i < right; j = ++i) {
int ai = a[i + 1];
while (ai < a[j]) {
a[j + 1] = a[j];
if (j-- == left) {
break;
}
}
a[j + 1] = ai;
}
} else {
/*
* 跳过有序的
*/
do {
if (left >= right) {
return;
}
} while (a[++left] >= a[left - 1]);
/*
* 双插入排序，一次比较两个，省去了部分重复的比较
* 比较上面的传统插入省去了左侧检查（leftmost的区块边界值当哨兵）
*/
for (int k = left; ++left <= right; k = ++left) {
int a1 = a[k], a2 = a[left];
if (a1 < a2) {
a2 = a1; a1 = a[left];//比较两个数的大小
}
while (a1 < a[--k]) {
a[k + 2] = a[k];//先对大的数进行插入排序
}
a[++k + 1] = a1;
while (a2 < a[--k]) {
a[k + 1] = a[k];//a2省去了前面a1比较的
}
a[k + 1] = a2;
}
int last = a[right];
//处理多出来的，奇偶问题
while (last < a[--right]) {
a[right + 1] = a[right];
}
a[right + 1] = last;
}
return;
}
// 获取length的七分之一近似值
int seventh = (length >> 3) + (length >> 6) + 1;
/*
* 获取5个轴，e1、e2、e3、e4、e5分别近似位于数组待排序部分的3/14, 5/14, 7/14, 9/14, 11/14，他们的选定是根据大量数据积累经验确定的
*/
int e3 = (left + right) >>> 1; // The midpoint
int e2 = e3 - seventh;
int e1 = e2 - seventh;
int e4 = e3 + seventh;
int e5 = e4 + seventh;
// 手动实现了插入排序，将这5个轴排序
if (a[e2] < a[e1]) { int t = a[e2]; a[e2] = a[e1]; a[e1] = t; }
if (a[e3] < a[e2]) { int t = a[e3]; a[e3] = a[e2]; a[e2] = t;
if (t < a[e1]) { a[e2] = a[e1]; a[e1] = t; }
}
if (a[e4] < a[e3]) { int t = a[e4]; a[e4] = a[e3]; a[e3] = t;
if (t < a[e2]) { a[e3] = a[e2]; a[e2] = t;
if (t < a[e1]) { a[e2] = a[e1]; a[e1] = t; }
}
}
if (a[e5] < a[e4]) { int t = a[e5]; a[e5] = a[e4]; a[e4] = t;
if (t < a[e3]) { a[e4] = a[e3]; a[e3] = t;
if (t < a[e2]) { a[e3] = a[e2]; a[e2] = t;
if (t < a[e1]) { a[e2] = a[e1]; a[e1] = t; }
}
}
}
// Pointers
int less = left; // 参考下图less的初始值
int great = right; // 参考下图great的初始值
//五个值都不相等时，才会用双轴快排，否则用单轴
if (a[e1] != a[e2] && a[e2] != a[e3] && a[e3] != a[e4] && a[e4] != a[e5]) {
/*
* e1-e5,取第二和第四个作为轴
* 是数组的三分位的近似值 pivot1 <= pivot2
*/
int pivot1 = a[e2];
int pivot2 = a[e4];
/*
*将第一个和最后一个需要排序的，挪动到轴所占据的位置（轴是基准，不需要排序）
*/
a[e2] = a[left];
a[e4] = a[right];
/*
* 跳过有序的，即 小于pivot1和大于pivot2的，这里做了++i而不是i++,把left和right空出来,给pivot1和pivot2腾位置。
*/
while (a[++less] < pivot1);
while (a[--great] > pivot2);
/*
* Partitioning:
*
* left part center part right part
* +--------------------------------------------------------------+
* | < pivot1 | pivot1 <= && <= pivot2 | ? | > pivot2 |
* +--------------------------------------------------------------+
* ^ ^ ^
* | | |
* less k great
*
* Invariants:
*
* all in (left, less) < pivot1
* pivot1 <= all in [less, k) <= pivot2
* all in (great, right) > pivot2
*
* Pointer k is the first index of ?-part.
*/
outer:
for (int k = less - 1; ++k <= great; ) {
int ak = a[k];
if (ak < pivot1) { // Move a[k] to left part
a[k] = a[less];
/*
*
* 这里用 "a[i] = b; i++;" 而不是
* "a[i++] = b;" 是性能问题，也就是这么写运行快一点.
*/
a[less] = ak;
++less;
} else if (ak > pivot2) { // Move a[k] to right part
while (a[great] > pivot2) {
if (great-- == k) {
break outer;
}
}
if (a[great] < pivot1) { // a[great] <= pivot2
a[k] = a[less];
a[less] = a[great];
++less;
} else { // pivot1 <= a[great] <= pivot2
a[k] = a[great];
}
/*
* "a[i] = b; i--;" 比 "a[i--] = b;" 性能好
*/
a[great] = ak;
--great;
}
}
// 将pivot1 pivot2归位（之前left和right空出来，这里就用到了）
a[left] = a[less - 1]; a[less - 1] = pivot1;
a[right] = a[great + 1]; a[great + 1] = pivot2;
// 实现递归，对左右部分排序，排除已知的轴心，这里就看出leftmost的作用了（不用做左边界检查）
sort(a, left, less - 2, leftmost);
sort(a, great + 2, right, false);
/*
* e1-e5是总长的4/7，如果中间部分长度大于这个值，就先进行处理，将等于轴心的值放到最左和最右（中间区域：pivot1 <= && <= pivot2）
*/
if (less < e1 && e5 < great) {
/*
* 跳过和轴相等的
*/
while (a[less] == pivot1) {
++less;
}
while (a[great] == pivot2) {
--great;
}
/*剩下的分区左边为等于轴1，右边等于轴2，还有要处理的大于轴1
*小于轴2的中间部分，下面把等于轴1和轴2的从中间分区找出来
* Partitioning:
*
* left part center part right part
* +----------------------------------------------------------+
* | == pivot1 | pivot1 < && < pivot2 | ? | == pivot2 |
* +----------------------------------------------------------+
* ^ ^ ^
* | | |
* less k great
*
* Invariants:
*
* all in (*, less) == pivot1
* pivot1 < all in [less, k) < pivot2
* all in (great, *) == pivot2
*
* Pointer k is the first index of ?-part.
*/
outer:
for (int k = less - 1; ++k <= great; ) {
int ak = a[k];
//等于轴1的左移
if (ak == pivot1) { // Move a[k] to left part
a[k] = a[less];
a[less] = ak;
++less;
} else if (ak == pivot2) { // Move a[k] to right part
//跳过有序的
while (a[great] == pivot2) {
if (great-- == k) {
break outer;
}
}
//等于轴2的右移，这时判断great的值的大小
if (a[great] == pivot1) { // a[great] < pivot2
a[k] = a[less];
/*
* Even though a[great] equals to pivot1, the
* assignment a[less] = pivot1 may be incorrect,
* if a[great] and pivot1 are floating-point zeros
* of different signs. Therefore in float and
* double sorting methods we have to use more
* accurate assignment a[less] = a[great].
*/
//这里用pivot1赋值给a[less]不是很准确
a[less] = pivot1;
++less;
} else { // pivot1 < a[great] < pivot2
a[k] = a[great];
}
a[great] = ak;
--great;
}
}
}
// 递归排序剩余pivot1 < && < pivot2 的分区
sort(a, less, great, false);
} else { // 单轴分区
/*
* 使用之前的第三个轴
* 这个轴是中间值的近似值
*/
int pivot = a[e3];
/*
* 使用传统快排（单轴）
*
* left part center part right part
* +-------------------------------------------------+
* | < pivot | == pivot | ? | > pivot |
* +-------------------------------------------------+
* ^ ^ ^
* | | |
* less k great
*
* Invariants:
*
* all in (left, less) < pivot
* all in [less, k) == pivot
* all in (great, right) > pivot
*
* Pointer k is the first index of ?-part.
*/
//传统快排也没啥好说的了
for (int k = less; k <= great; ++k) {
if (a[k] == pivot) {
continue;
}
int ak = a[k];
if (ak < pivot) { // Move a[k] to left part
a[k] = a[less];
a[less] = ak;
++less;
} else { // a[k] > pivot - Move a[k] to right part
while (a[great] > pivot) {
--great;
}
if (a[great] < pivot) { // a[great] <= pivot
a[k] = a[less];
a[less] = a[great];
++less;
} else { // a[great] == pivot
/*
* Even though a[great] equals to pivot, the
* assignment a[k] = pivot may be incorrect,
* if a[great] and pivot are floating-point
* zeros of different signs. Therefore in float
* and double sorting methods we have to use
* more accurate assignment a[k] = a[great].
*/
a[k] = pivot;
}
a[great] = ak;
--great;
}
}
/*
* 递归排序左右两边，中间分区都等于轴不用再排序
*/
sort(a, left, less - 1, leftmost);
sort(a, great + 1, right, false);
}
}
。
总结
这是java JDK中Arrays.sort()排序用到的算法，一个工厂级的算法复杂度和需要考虑的维度，不是一个简单的冒泡或插入能比的，里面很多理念和边界值都是前人的经验所得，学到了学到了。
扫一扫
1267
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
