【发布时间】:2018-03-05 15:01:28
【问题描述】:
我目前正在使用 C 语言实现哈希表。我正在尝试实现动态调整大小,但遇到了问题。
如果调整散列表的大小意味着创建一个大小为两倍(或一半)的新表、重新散列并删除旧表,我该如何处理用户可能对旧表所做的旧引用?示例代码(我只是为了这个例子省略了错误检查):
int main(int argc, char *argv[])
{
ht = ht_create(5) /* make hashtable with size 5 */
ht_insert("john", "employee"); /* key-val pair "john -> employee" */
ht_insert("alice", "employee");
char *position = ht_get(ht, "alice"); /* get alice's position from hashtable ht */
ht_insert("bob", "boss"); /* this insert exceeds the load factor, resizes the hash table */
printf("%s", position); /* returns NULL because the previous hashtable that was resized was freed */
return 0;
}
在这种情况下,position 指向在哈希表中找到的alice 的值。当它被调整大小时,我们释放了哈希表并丢失了它。我该如何解决这个问题,这样用户就不必担心先前定义的指针被释放了?
编辑:我当前的哈希表实现
哈希.c
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "hash.h"
#define LOADFACTOR 0.75
typedef struct tableentry /* hashtab entry */
{
struct tableentry *next;
char *key;
void *val;
} tableentry_t;
typedef struct hashtable
{
datatype_t type;
size_t size;
size_t load; /* number of keys filled */
struct tableentry **tab;
} hashtable_t;
/* creates hashtable */
/* NOTE: dynamically allocated, remember to ht_free() */
hashtable_t *ht_create(size_t size, datatype_t type)
{
hashtable_t *ht = NULL;
if ((ht = malloc(sizeof(hashtable_t))) == NULL)
return NULL;
/* allocate ht's table */
if ((ht->tab = malloc(sizeof(tableentry_t) * size)) == NULL)
return NULL;
/* null-initialize table */
size_t i;
for (i = 0; i < size; i++)
ht->tab[i] = NULL;
ht->size = size;
ht->type = type;
return ht;
}
/* creates hash for a hashtab */
static unsigned hash(char *s)
{
unsigned hashval;
for (hashval = 0; *s != '\0'; s++)
hashval = *s + 31 * hashval;
return hashval;
}
static int *intdup(int *i)
{
int *new;
if ((new = malloc(sizeof(int))) == NULL)
return NULL;
*new = *i;
return new;
}
static void free_te(tableentry_t *te)
{
free(te->key);
free(te->val);
free(te);
}
/* loops through linked list freeing */
static void free_te_list(tableentry_t *te)
{
tableentry_t *next;
while (te != NULL)
{
next = te->next;
free_te(te);
te = next;
}
}
/* creates a key-val pair */
static tableentry_t *alloc_te(char *k, void *v, datatype_t type)
{
tableentry_t *te = NULL;
int status = 0;
/* alloc struct */
if ((te = calloc(1, sizeof(*te))) == NULL)
status = -1;
/* alloc key */
if ((te->key = strdup(k)) == NULL)
status = -1;
/* alloc value */
int *d;
char *s;
switch (type)
{
case STRING:
s = (char *) v;
if ((te->val = strdup(s)) == NULL)
status = -1;
break;
case INTEGER:
d = (int *) v;
if ((te->val = intdup(d)) == NULL)
status = -1;
break;
default:
status = -1;
}
if (status < 0)
{
free_te_list(te);
return NULL;
}
te->next = NULL;
return te;
}
static tableentry_t *lookup(hashtable_t *ht, char *k)
{
tableentry_t *te;
/* step through linked list */
for (te = ht->tab[hash(k) % ht->size]; te != NULL; te = te->next)
if (strcmp(te->key, k) == 0)
return te; /* found */
return NULL; /* not found */
}
/* inserts the key-val pair */
hashtable_t *ht_insert(hashtable_t *ht, char *k, void *v)
{
tableentry_t *te;
/* unique entry */
if ((te = lookup(ht, k)) == NULL)
{
te = alloc_te(k, v, ht->type);
unsigned hashval = hash(k) % ht->size;
/* insert at beginning of linked list */
te->next = ht->tab[hashval];
ht->tab[hashval] = te;
ht->load++;
}
/* replace val of previous entry */
else
{
free(te->val);
switch (ht->type)
{
case STRING:
if ((te->val = strdup(v)) == NULL)
return NULL;
break;
case INTEGER:
if ((te->val = intdup(v)) == NULL)
return NULL;
break;
default:
return NULL;
}
}
return ht;
}
static void delete_te(hashtable_t *ht, char *k)
{
tableentry_t *te, *prev;
unsigned hashval = hash(k) % ht->size;
te = ht->tab[hashval];
/* point head to next element if deleting head */
if (strcmp(te->key, k) == 0)
{
ht->tab[hashval] = te->next;
free_te(te);
ht->load--;
return;
}
/* otherwise look through, keeping track of prev to reassign its ->next */
for (; te != NULL; te = te->next)
{
if (strcmp(te->key, k) == 0)
{
prev->next = te->next;
free_te(te);
ht->load--;
return;
}
prev = te;
}
}
hashtable_t *ht_delete(hashtable_t *ht, char *k)
{
size_t i;
if (lookup(ht, k) == NULL)
return NULL;
else
delete_te(ht, k);
}
/* retrieve value from key */
void *ht_get(hashtable_t *ht, char *k)
{
tableentry_t *te;
if ((te = lookup(ht, k)) == NULL)
return NULL;
return te->val;
}
/* frees hashtable created from ht_create() */
void ht_free(hashtable_t *ht)
{
size_t i;
if (ht)
{
for (i = 0; i < ht->size; i++)
if (ht->tab[i] != NULL)
free_te_list(ht->tab[i]);
free(ht);
}
}
/* resizes hashtable, returns new hashtable and frees old */
static hashtable_t *resize(hashtable_t *oht, size_t size)
{
hashtable_t *nht; /* new hashtable */
nht = ht_create(size, oht->type);
/* rehash */
size_t i;
tableentry_t *te;
/* loop through hashtable */
for (i = 0; i < oht->size; i++)
/* loop through linked list */
for (te = oht->tab[i]; te != NULL; te = te->next)
/* insert & rehash old vals into new ht */
if (ht_insert(nht, te->key, te->val) == NULL)
return NULL;
ht_free(oht);
return nht;
}
哈希.h
/* a hash-table implementation in c */
/*
hashing algorithm: hashval = *s + 31 * hashval
resolves collisions using linked lists
*/
#ifndef HASH
#define HASH
typedef struct hashtable hashtable_t;
typedef enum datatype {STRING, INTEGER} datatype_t;
/* inserts the key-val pair */
hashtable_t *ht_insert(hashtable_t *ht, char *k, void *v);
/* creates hashtable */
/* NOTE: dynamically allocated, remember to ht_free() */
hashtable_t *ht_create(size_t size, datatype_t type);
/* frees hashtable created from ht_create() */
void ht_free(hashtable_t *ht);
/* retrive value from key */
void *ht_get(hashtable_t *ht, char *k);
hashtable_t *ht_delete(hashtable_t *ht, char *k);
#endif
【问题讨论】:
-
您可以在哈希表中添加一个条目,指明它使用的哈希算法。您可以使用低于 0x30000 的指针来指示它不是指向函数的指针,而是使用标准散列算法,并使用高于 0x30000 的指针作为指向函数的指针。这样,您需要做的就是将其重新散列为新的存储桶大小。您可以使用 0 作为“无效哈希函数”哈希函数的占位符。例如,0 可能表示“无效哈希函数”,1 可能表示标准哈希函数 #1,...,超过 0x30000 的指针可用于指示它是哈希函数指针。
-
哦,你的意思是,如果有人有一个指向哈希表的弱指针,但该表已调整大小?这不是问题,因为您永远不会破坏桌子;您只需停止世界(防止任何东西使用信号量/锁与哈希表交互)并重新散列所有内容。以后任何使用 table 的尝试都将在执行散列时使用新的存储桶大小。
-
所以你在调整大小后永远不会删除/释放旧的哈希表?这最终不会导致大量的内存空间浪费吗?
-
为什么会这样?哈希表是一种抽象数据结构,它与关联数组相同,只是它是桶表而不是关联表。您只需复制存储桶即可。哈希函数负责访问哪个存储桶,然后您像常规关联数组一样搜索它。
-
我在想,因为你会有一堆死的、空的、永远不会被使用的内存空间(来自旧的哈希表)。