编程珠玑 15 章

/* str.c */
/* 编程珠玑 15 章 */

/* 统计文本中每个单词出现的频率 */

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

typedef struct node
{
	char *word;
	unsigned int count;
	struct node *next;
}node, *nodeptr;

#define NHASH 299
#define MULT	31

nodeptr bin[NHASH];

unsigned int hash(char *p)
{
	unsigned int h = 0;
	
	for (; *p; p++)
	{
		h = MULT * h + (*p);
	}
	
	return h % NHASH;
}

void incword(char *s)
{
	int h;
	nodeptr p;
	
	h = hash(s);
	for (p = bin[h]; p != NULL; p++)
	{
		if (0 == strcmp(p->word, s))
		{
			p->count++;
			return;
		}
	}
	
	p = (nodeptr)malloc(sizeof(node));
	if (NULL == p)
	{
		printf("malloc failed!\n");
		exit(0);
	}
	
	
	p->word = (char *)malloc(sizeof(s) + 1);
	if (NULL == p->word)
	{
		free(p);
		printf("malloc failed!\n");
		exit(0);
	}
	
	strcpy(p->word, s);
	p->count = 1;
	
	p->next = bin[h];
	bin[h] = p;
}

int main()
{
	int i;
	char buf[256], buf1[256];
	nodeptr p;
	FILE *input;
	int j;
	
	input = fopen("data.txt", "r");
	if (NULL == input)
	{
		printf("fopne failed\n");
		exit(0);
	}
	
	for (i = 0; i < NHASH; i++)
	{
		bin[i] = NULL;
	}
	
	printf("input string:\n");
	//while (gets(buf) && (strcmp(buf, "end") != 0))
	//while (scanf("%s", buf) && (strcmp(buf, "end") != 0))
	while (fgets(buf, 256, input) != NULL)
	{
		j = 0;
		for (i = 0; buf[i] != '\0'; i++)
		{
			if (buf[i] != ' ' && buf[i] != '\n')
			{
				j++;
				continue;
			}
			if (j != 0)
			{
				strncpy(buf1, buf+i-j, j);
				buf1[j] = '\0';
				incword(buf1);
				j = 0;
			}
		}
		if (j != 0)
		{
			strncpy(buf1, buf+i-j, j);
			buf1[j] = '\0';
			incword(buf1);
		}
		
	}
	printf("\n\nresult:\n");
	for (i = 0; i < NHASH; i++)
	{
		for (p = bin[i]; p != NULL; p = p->next)
		{
			printf("%s:%d\n",  p->word, p->count);
		}
	}
	
	printf("\n");
	fclose(input);
	
	return 0;
}


//求两个字符串相同部分长度
int comlen(char *p, char *q)
{
	int i = 0;
	
	while (*p && (*p++ == *q++))
	{
		i++;
	}
	
	return i;
}

int max_sub_str(char *s, char *sub)
{
	int i, j;
	int len;
	int maxi, maxj;
	int maxlen, thislen;
	
	maxi = 0;
	maxj = 0;
	maxlen = 0;
	thislen = 0;
	len = strlen(s);
	printf("%d\n", len);
	
	for (i = 0; i < len; i++)
	{
		for (j = i + 1; j < len; j++)
		{
				if ((thislen = comlen(s+i, s+j)) > maxlen)
				{
					maxlen = thislen;
					maxi = i;
					maxj = j;
				}
		}
	}
	sub = s + maxi;
	
	return maxlen;
}

int main()
{
	char str[] = "ni hao wo zai jsp ei wo zai zhe ni";
	char sub[256];
	int len;

	len = max_sub_str(str, sub);

	if (len != 0)
	{
		printf("len:%d\n", len);	
	}

	return 0;
}


/* 后缀数组 */
#define MAXN 5000

char c[MAXN], *a[MAXN];


int input_data()
{
	int n = 0;
	char ch;
	
	printf("input data:\n");
	while ((ch = getchar()) != '\n')
	{
		a[n] = &c[n];
		c[n++] = ch;
	}
	c[n] = '\0';

	return n - 1;
}

void qsort1(char *array[], int n)
{
	int i, j;
	char *tmp;
	
	for (i = 0; i < n - 1; i++)
	{
		tmp = array[i];
		for (j = i+1; j < n; j++)
		{
			if (strcmp(array[i], array[j]) > 0)
			{
				array[i] = array[j];
			}
		}
		array[j] = tmp;
	}
}

void max_sub_str(char *array[], int n)
{
	int i;
	int len = 0;
	int maxi = 0;
	int maxlen = 0;
	
	for (i = 0; i < n - 1; i++)
	{
		if ((len = comlen(array[i], array[i+1])) > maxlen)
		{
			maxlen = len;
			maxi = i;
		}
	}
	
	printf("\nmax sub str:%s\n", a[maxi]);
}

int main()
{
	int n;

	n = input_data();
	qsort1(a, n);
	max_sub_str(a, n);

	return 0;
}