/*----------------------------------------
随机生成文本程序
2011.3.15 by LiWang112358
----------------------------------------*/
#include <iostream>
#include <time.h>
using namespace std;
int k = 2;//二元模型;当前单词的产生依赖于前一个单词
char inputchars[5000000];
char * word[1000000];
int nword = 0;
int cmp(char * p,char * q)
{
int n = k;
for (; *p == *q; p ++ ,q ++)
if ( 0 == *p && -- n == 0)//只有当后缀数组的前两个单词相同时,默认是相同的
return 0;
return *p - *q;
}
int sortcmp(const void * p,const void * q)
{
return cmp((char *)p,(char *)q) <= 0;
}
void myQsort(char * a[],int l,int r)
{
int i,j;
char * s = a[l];
i=l;
j=r;
while (i<=j)
{
while (cmp(a[i],s) < 0 && i<=j) i++;
while (cmp(a[j],s) > 0 && i<=j) j--;
if (i<=j)
{
swap(a[i],a[j]);
i++;
j--;
}
}
if (i<r) myQsort(a,i,r);
if (l<j) myQsort(a,l,j);
}
int find(int begin,int end,char * x,char * a[]) // 二分查找
{
int l = begin,r = end,mid = (l + r) >> 1;
while (l <= r)
{
if (strcmp(a[mid],x) < 0) l = mid + 1;
else if (strcmp(a[mid],x) > 0) r = mid - 1;
else if (strcmp(a[mid],x) == 0)
{
while (mid > 0 && strcmp(a[mid],a[mid - 1]) == 0) --mid;
return mid;
}
mid = (l + r) >> 1;
}
return -1;
}
char * skip(char * p,int num)
{
for (int i = 0; i < num ; ++ i)
{
for (; (*p) > 0; ++ p);
p++;
}
return p;
}
int main()
{
freopen("in.txt","r",stdin);
memset(inputchars,0,sizeof(inputchars));
word[0] = inputchars;
while (scanf("%s",word[nword]) != EOF)
{
word[nword + 1] = word[nword] + strlen(word[nword]) + 1;
nword ++;
}
for (int i = 0; i < k; ++ i)
word[nword][i] = 0;
myQsort(word,0,nword - 1);
srand(int(time(0)));
char * p = inputchars;
for (int i = 0; i < 10000; ++ i)
{
printf("%s ",p);
if ( i > 0 && i % 20 == 0) printf("/n");
int pos = find(0,nword - 1,p,word);
int j = 0;
for (j = 0; strcmp(p,word[pos + j]) == 0 && pos + j < nword; ++ j);
int rd = abs(rand()) % j;
p = word[pos + rd];
p = skip(p,1);
if (strlen(skip(p,k - 1)) == 0) break;
}
return 0;
}
转自:http://blog.csdn.net/liwang112358/article/details/6253758