匹配具有相同字母的单词

Question

我正在尝试匹配两个单词，然后将它们打印出来，例如 'act' 和 'cat' 中包含 'a、'c' 和 't' 以便它们匹配。这是我的代码：

#include <stdio.h>
#include <stdlib.h>

main()
{
  FILE        *fptr;
  char        words[100], input[100], store[1000][100] 
  char        ch
  int         i,j,k,z,b,*ptr;

  ptr = &b;

  fptr = fopen("d:\\words.txt","r");
  if (fptr == NULL)
  {
           printf("Could not open file");
           exit(1);
  }

  printf("Enter the scrambled word: ");
  fflush(stdin);
  fgets (input,sizeof(input),stdin);

  i = 0;
  while (fgets(words,sizeof(words),fptr) != NULL)
  {     
        if (strlen(input) == strlen(words))
        {
           strcpy(store[i],words);
           ++i;
        }
  }
  //this is where the problem is:
  /*am trying to match the letters in two words, if they don't match then store 1 in b,
  if b=0 then print out the word which matched with string 'input'*/
  for(z = 0; z < 1000; ++z)
  {
        b = 0;
        for(j = 0; j < strlen(input); ++j)
        {
              for(k = 0; k < strlen(store[z]); ++k)
              {
                    if(input[j] != store[z][k])
                        *ptr = 1;          
              }
        }
        if(*ptr == 0)
        {          
                   printf("Word #%2d is: %s\n", z, store[z]);   
        }
  }



  fflush(stdin);
  getchar();
}

我真的需要帮助。很抱歉，如果我没有把我的问题说清楚。

Answer 1

对两个字符串中的字母进行排序然后比较它们是一种更简单的方法来满足您的需求。 （假设你熟悉排序）

这可能不是最有效的，但我再说一遍，通常最好在你有一个可行的解决方案和性能指标之后再过分担心效率。

如果您想要一些更有效的方法来检测两个单词是否是字谜，请查看 Mats Petersson 提供的链接，Optimizing very often used anagram function

Answer 2

这样的东西也可以工作..（对不起，阅读代码很丑，正忙于其他事情）...

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <Windows.h>

#include <string>
#include <list>
#include <map>
#include <sstream>
#include <algorithm>

using namespace std;

map< string, list<string> > items;
int c = 0;

void readFile() {
        FILE * f = fopen( "c:\\t\\words.txt", "r" );
        fseek(f, 0L, SEEK_END);
        int size = ftell(f);
        fseek(f, 0L, SEEK_SET);
        char * data = (char*)malloc(size);
        fread(data, size, 1, f);

        string s = string(data);
        istringstream reader(s);
        while(reader) {
            string sub;
            reader >> sub;

            string original = sub;
            sort( sub.begin(), sub.end() );

            items[sub].push_back(original);        
            c++;
        }


        free(data);
        fclose(f);
}

bool     check( const string & v ) {
    string requestStr = v;
    sort( requestStr.begin(), requestStr.end() );
    printf("Requested: %s [%s]\n", v.c_str(), requestStr.c_str());

    if (items.find(requestStr) == items.end()) {
        printf("Not found\n");
        return false;
    }

    list<string>::iterator it = items[requestStr].begin();

    while (it != items[requestStr].end()) {
        printf("Found: %s\n", (*it).c_str());       
        it++;
    }
}

int main(int argc, char ** argv) {
    long t1 = GetTickCount();
    readFile();
    printf("Read wordlist (%i): %li ms\n", c, GetTickCount() - t1 );

    string str = "holiday";
     t1 = GetTickCount();
    check(str);
    printf("Time: %li ms\n",  GetTickCount() - t1 );


    str = "tac";
     t1 = GetTickCount();
    check(str);
    printf("Time: %li ms\n",  GetTickCount() - t1 );

    str = "dfgegs";
     t1 = GetTickCount();
    check(str);
    printf("Time: %li ms\n",  GetTickCount() - t1 );

}

109000字文件的结果

Read wordlist (109583): 5969 ms
Requested: holiday [adhiloy]
Found: holiday
Time: 0 ms
Requested: tac [act]
Found: act
Found: cat
Time: 0 ms
Requested: dfgegs [defggs]
Not found
Time: 0 ms

120000 次搜索需要 7188 毫秒，因此每次搜索大约需要 0.0599 毫秒...