我想写一个函数,它以一个字母数组作为参数,并从中选择一些字母。

假设您提供了一个包含8个字母的数组,并希望从中选择3个字母。那么你应该得到:

8! / ((8 - 3)! * 3!) = 56

数组(或单词),每个数组由3个字母组成。


当前回答

下面是一个简单易懂的递归c++解决方案:

#include<vector>
using namespace std;

template<typename T>
void ksubsets(const vector<T>& arr, unsigned left, unsigned idx,
    vector<T>& lst, vector<vector<T>>& res)
{
    if (left < 1) {
        res.push_back(lst);
        return;
    }
    for (unsigned i = idx; i < arr.size(); i++) {
        lst.push_back(arr[i]);
        ksubsets(arr, left - 1, i + 1, lst, res);
        lst.pop_back();
    }
}

int main()
{
    vector<int> arr = { 1, 2, 3, 4, 5 };
    unsigned left = 3;
    vector<int> lst;
    vector<vector<int>> res;
    ksubsets<int>(arr, left, 0, lst, res);
    // now res has all the combinations
}

其他回答

下面是一个方法,它从一个随机长度的字符串中给出指定大小的所有组合。类似于昆玛斯的解,但适用于不同的输入和k。

代码可以更改为换行,即'dab'从输入'abcd' w k=3。

public void run(String data, int howMany){
    choose(data, howMany, new StringBuffer(), 0);
}


//n choose k
private void choose(String data, int k, StringBuffer result, int startIndex){
    if (result.length()==k){
        System.out.println(result.toString());
        return;
    }

    for (int i=startIndex; i<data.length(); i++){
        result.append(data.charAt(i));
        choose(data,k,result, i+1);
        result.setLength(result.length()-1);
    }
}

"abcde"的输出:

ABC abd ace ade BCD bce bde cde

在Python中,利用递归的优势和所有事情都是通过引用完成的事实。对于非常大的集合,这将占用大量内存,但其优点是初始集合可以是一个复杂的对象。它只会找到唯一的组合。

import copy

def find_combinations( length, set, combinations = None, candidate = None ):
    # recursive function to calculate all unique combinations of unique values
    # from [set], given combinations of [length].  The result is populated
    # into the 'combinations' list.
    #
    if combinations == None:
        combinations = []
    if candidate == None:
        candidate = []

    for item in set:
        if item in candidate:
            # this item already appears in the current combination somewhere.
            # skip it
            continue

        attempt = copy.deepcopy(candidate)
        attempt.append(item)
        # sorting the subset is what gives us completely unique combinations,
        # so that [1, 2, 3] and [1, 3, 2] will be treated as equals
        attempt.sort()

        if len(attempt) < length:
            # the current attempt at finding a new combination is still too
            # short, so add another item to the end of the set
            # yay recursion!
            find_combinations( length, set, combinations, attempt )
        else:
            # the current combination attempt is the right length.  If it
            # already appears in the list of found combinations then we'll
            # skip it.
            if attempt in combinations:
                continue
            else:
                # otherwise, we append it to the list of found combinations
                # and move on.
                combinations.append(attempt)
                continue
    return len(combinations)

你可以这样使用它。传递'result'是可选的,所以你可以用它来获取可能组合的数量…尽管这样做效率很低(最好通过计算来完成)。

size = 3
set = [1, 2, 3, 4, 5]
result = []

num = find_combinations( size, set, result ) 
print "size %d results in %d sets" % (size, num)
print "result: %s" % (result,)

您应该从测试数据中得到以下输出:

size 3 results in 10 sets
result: [[1, 2, 3], [1, 2, 4], [1, 2, 5], [1, 3, 4], [1, 3, 5], [1, 4, 5], [2, 3, 4], [2, 3, 5], [2, 4, 5], [3, 4, 5]]

如果你的集合是这样的,它也会工作得很好:

set = [
    [ 'vanilla', 'cupcake' ],
    [ 'chocolate', 'pudding' ],
    [ 'vanilla', 'pudding' ],
    [ 'chocolate', 'cookie' ],
    [ 'mint', 'cookie' ]
]

现在又出现了祖辈COBOL,一种饱受诟病的语言。

让我们假设一个包含34个元素的数组,每个元素8个字节(完全是任意选择)。其思想是枚举所有可能的4元素组合,并将它们加载到一个数组中。

我们使用4个指标,每个指标代表4个组中的每个位置

数组是这样处理的:

    idx1 = 1
    idx2 = 2
    idx3 = 3
    idx4 = 4

我们把idx4从4变到最后。对于每个idx4,我们得到一个唯一的组合 四人一组。当idx4到达数组的末尾时,我们将idx3增加1,并将idx4设置为idx3+1。然后再次运行idx4到最后。我们以这种方式继续,分别增加idx3、idx2和idx1,直到idx1的位置距离数组末端小于4。算法就完成了。

1          --- pos.1
2          --- pos 2
3          --- pos 3
4          --- pos 4
5
6
7
etc.

第一次迭代:

1234
1235
1236
1237
1245
1246
1247
1256
1257
1267
etc.

一个COBOL的例子:

01  DATA_ARAY.
    05  FILLER     PIC X(8)    VALUE  "VALUE_01".
    05  FILLER     PIC X(8)    VALUE  "VALUE_02".
  etc.
01  ARAY_DATA    OCCURS 34.
    05  ARAY_ITEM       PIC X(8).

01  OUTPUT_ARAY   OCCURS  50000   PIC X(32).

01   MAX_NUM   PIC 99 COMP VALUE 34.

01  INDEXXES  COMP.
    05  IDX1            PIC 99.
    05  IDX2            PIC 99.
    05  IDX3            PIC 99.
    05  IDX4            PIC 99.
    05  OUT_IDX   PIC 9(9).

01  WHERE_TO_STOP_SEARCH          PIC 99  COMP.

* Stop the search when IDX1 is on the third last array element:

COMPUTE WHERE_TO_STOP_SEARCH = MAX_VALUE - 3     

MOVE 1 TO IDX1

PERFORM UNTIL IDX1 > WHERE_TO_STOP_SEARCH
   COMPUTE IDX2 = IDX1 + 1
   PERFORM UNTIL IDX2 > MAX_NUM
      COMPUTE IDX3 = IDX2 + 1
      PERFORM UNTIL IDX3 > MAX_NUM
         COMPUTE IDX4 = IDX3 + 1
         PERFORM UNTIL IDX4 > MAX_NUM
            ADD 1 TO OUT_IDX
            STRING  ARAY_ITEM(IDX1)
                    ARAY_ITEM(IDX2)
                    ARAY_ITEM(IDX3)
                    ARAY_ITEM(IDX4)
                    INTO OUTPUT_ARAY(OUT_IDX)
            ADD 1 TO IDX4
         END-PERFORM
         ADD 1 TO IDX3
      END-PERFORM
      ADD 1 TO IDX2
   END_PERFORM
   ADD 1 TO IDX1
END-PERFORM.

下面是我的Scala解决方案:

def combinations[A](s: List[A], k: Int): List[List[A]] = 
  if (k > s.length) Nil
  else if (k == 1) s.map(List(_))
  else combinations(s.tail, k - 1).map(s.head :: _) ::: combinations(s.tail, k)

我的实现在c/c++

#include <unistd.h>
#include <stdio.h>
#include <iconv.h>
#include <string.h>
#include <errno.h>
#include <stdlib.h>

int main(int argc, char **argv)
{
    int opt = -1, min_len = 0, max_len = 0;
    char ofile[256], fchar[2], tchar[2];
    ofile[0] = 0;
    fchar[0] = 0;
    tchar[0] = 0;
    while((opt = getopt(argc, argv, "o:f:t:l:L:")) != -1)
    {
            switch(opt)
            {
                    case 'o':
                    strncpy(ofile, optarg, 255);
                    break;
                    case 'f':
                    strncpy(fchar, optarg, 1);
                    break;
                    case 't':
                    strncpy(tchar, optarg, 1);
                    break;
                    case 'l':
                    min_len = atoi(optarg);
                    break;
                    case 'L':
                    max_len = atoi(optarg);
                    break;
                    default:
                    printf("usage: %s -oftlL\n\t-o output file\n\t-f from char\n\t-t to char\n\t-l min seq len\n\t-L max seq len", argv[0]);
            }
    }
if(max_len < 1)
{
    printf("error, length must be more than 0\n");
    return 1;
}
if(min_len > max_len)
{
    printf("error, max length must be greater or equal min_length\n");
    return 1;
}
if((int)fchar[0] > (int)tchar[0])
{
    printf("error, invalid range specified\n");
    return 1;
}
FILE *out = fopen(ofile, "w");
if(!out)
{
    printf("failed to open input file with error: %s\n", strerror(errno));
    return 1;
}
int cur_len = min_len;
while(cur_len <= max_len)
{
    char buf[cur_len];
    for(int i = 0; i < cur_len; i++)
        buf[i] = fchar[0];
    fwrite(buf, cur_len, 1, out);
    fwrite("\n", 1, 1, out);
    while(buf[0] != (tchar[0]+1))
    {
        while(buf[cur_len-1] < tchar[0])
        {
            (int)buf[cur_len-1]++;
            fwrite(buf, cur_len, 1, out);
            fwrite("\n", 1, 1, out);
        }
        if(cur_len < 2)
            break;
        if(buf[0] == tchar[0])
        {
            bool stop = true;
            for(int i = 1; i < cur_len; i++)
            {
                if(buf[i] != tchar[0])
                {
                    stop = false;
                    break;
                }
            }
            if(stop)
                break;
        }
        int u = cur_len-2;
        for(; u>=0 && buf[u] >= tchar[0]; u--)
            ;
        (int)buf[u]++;
        for(int i = u+1; i < cur_len; i++)
            buf[i] = fchar[0];
        fwrite(buf, cur_len, 1, out);
        fwrite("\n", 1, 1, out);
    }
    cur_len++;
}
fclose(out);
return 0;
}

这里我的实现在c++,它写所有的组合到指定的文件,但行为可以改变,我在生成各种字典,它接受最小和最大长度和字符范围,目前只有ANSI支持,它足以满足我的需求