java中List的sort源码解读

最近看了一些排序相关的文章，因此比较好奇，Java中的排序是如何做的。本片文章介绍的是JDK1.8，List中的sort方法。

先来看看List中的sort是怎么写的：

    @SuppressWarnings({"unchecked", "rawtypes"})
    default void sort(Comparator<? super E> c) {
        Object[] a = this.toArray();
        Arrays.sort(a, (Comparator) c);
        ListIterator<E> i = this.listIterator();
        for (Object e : a) {
            i.next();
            i.set((E) e);
        }
    }

首先，你需要传入一个比较器作为参数，这个好理解，毕竟你肯定要定一个比较标准。然后就是将list转换成一个数组，再对这个数组进行排序，排序完之后，再利用iterator重新改变list。

接着，我们再来看看Arrays.sort：

    public static <T> void sort(T[] a, Comparator<? super T> c) {
        if (c == null) {
            sort(a);
        } else {
            if (LegacyMergeSort.userRequested)
                legacyMergeSort(a, c);
            else
                TimSort.sort(a, 0, a.length, c, null, 0, 0);
        }
    }

    public static void sort(Object[] a) {
        if (LegacyMergeSort.userRequested)
            legacyMergeSort(a);
        else
            ComparableTimSort.sort(a, 0, a.length, null, 0, 0);
    }

    static final class LegacyMergeSort {
        private static final boolean userRequested =
            java.security.AccessController.doPrivileged(
                new sun.security.action.GetBooleanAction(
                    "java.util.Arrays.useLegacyMergeSort")).booleanValue();
    }

这样可以看出，其实排序的核心就是TimSort，LegacyMergeSort大致意思是表明如果版本很旧的话，就用这个，新版本是不会采用这种排序方式的。

我们再来看看TimSort的实现：

    private static final int MIN_MERGE = 32;
    static <T> void sort(T[] a, int lo, int hi, Comparator<? super T> c,
                         T[] work, int workBase, int workLen) {
        assert c != null && a != null && lo >= 0 && lo <= hi && hi <= a.length;

        int nRemaining  = hi - lo;
        if (nRemaining < 2)
            return;  // Arrays of size 0 and 1 are always sorted

        // If array is small, do a "mini-TimSort" with no merges
        if (nRemaining < MIN_MERGE) {
            // 获得最长的递增序列
            int initRunLen = countRunAndMakeAscending(a, lo, hi, c);
            binarySort(a, lo, hi, lo + initRunLen, c);
            return;
        }

        /**
         * March over the array once, left to right, finding natural runs,
         * extending short natural runs to minRun elements, and merging runs
         * to maintain stack invariant.
         */
        TimSort<T> ts = new TimSort<>(a, c, work, workBase, workLen);
        int minRun = minRunLength(nRemaining);
        do {
            // Identify next run
            int runLen = countRunAndMakeAscending(a, lo, hi, c);

            // If run is short, extend to min(minRun, nRemaining)
            if (runLen < minRun) {
                int force = nRemaining <= minRun ? nRemaining : minRun;
                binarySort(a, lo, lo + force, lo + runLen, c);
                runLen = force;
            }

            // Push run onto pending-run stack, and maybe merge
            ts.pushRun(lo, runLen);
            ts.mergeCollapse();

            // Advance to find next run
            lo += runLen;
            nRemaining -= runLen;
        } while (nRemaining != 0);

        // Merge all remaining runs to complete sort
        assert lo == hi;
        ts.mergeForceCollapse();
        assert ts.stackSize == 1;
    }

如果小于2个，代表不再不需要排序；如果小于32个，则采用优化的二分排序。怎么优化的呢？首先获得最长的递增序列：

    private static <T> int countRunAndMakeAscending(T[] a, int lo, int hi,
                                                    Comparator<? super T> c) {
        assert lo < hi;
        int runHi = lo + 1;
        if (runHi == hi)
            return 1;

        // Find end of run, and reverse range if descending
        if (c.compare(a[runHi++], a[lo]) < 0) { // Descending
            // 一开始是递减序列，就找出最长递减序列的最后一个下标
            while (runHi < hi && c.compare(a[runHi], a[runHi - 1]) < 0)
                runHi++;
            // 逆转前面的递减序列
            reverseRange(a, lo, runHi);
        } else {                              // Ascending
            while (runHi < hi && c.compare(a[runHi], a[runHi - 1]) >= 0)
                runHi++;
        }

        return runHi - lo;
    }

接着进行二分排序：

    private static <T> void binarySort(T[] a, int lo, int hi, int start,
                                       Comparator<? super T> c) {
        assert lo <= start && start <= hi;
        if (start == lo)
            start++;
        for ( ; start < hi; start++) {
            T pivot = a[start];

            // Set left (and right) to the index where a[start] (pivot) belongs
            int left = lo;
            int right = start;
            assert left <= right;
            /*
             * Invariants:
             *   pivot >= all in [lo, left).
             *   pivot <  all in [right, start).
             */
            while (left < right) {
                int mid = (left + right) >>> 1;
                if (c.compare(pivot, a[mid]) < 0)
                    right = mid;
                else
                    left = mid + 1;
            }
            assert left == right;

            /*
             * The invariants still hold: pivot >= all in [lo, left) and
             * pivot < all in [left, start), so pivot belongs at left.  Note
             * that if there are elements equal to pivot, left points to the
             * first slot after them -- that's why this sort is stable.
             * Slide elements over to make room for pivot.
             */
            int n = start - left;  // The number of elements to move
            // Switch is just an optimization for arraycopy in default case
            switch (n) {
                case 2:  a[left + 2] = a[left + 1];
                case 1:  a[left + 1] = a[left];
                         break;
                default: System.arraycopy(a, left, a, left + 1, n);
            }
            a[left] = pivot;
        }
    }

有兴趣的话可以看看我的私人博客，也可以关注我的公众号，说不定会有意外的惊喜。