intset
- 存储有序的整型集合
- 集合内唯一
说明
-
encoding 编码类型，决定每个元素占用几个字节。有三种类型
- INTSET_ENC_INT16 INT16_MIN ~ INT16_MAX 占2个字节
- INTSET_ENC_INT32 ,INT16_MAX~INT32_MAX 、 INT32_MIN ~ INT16_MIN 占4个字节
- INTSET_ENC_INT64 ,INT32_MAX~INT64_MAX 、 INT64_MIN ~ INT32_MIN 占8个字节
- 会根据待插入的值决定是否需要进行扩容操作。扩容会修改encoding,如果引起了扩容，柔性数组也要进行相应的扩展。只要待插入的值导致了扩容，则该待插入的值得不是最大值，就是最小值。
- length 元素个数。即一个intset中包括了多少个元素
- contents 存储具体元素。
操作
查询
- 如果编码方式大于当前intset的编码方式，直接返回0,否则调用调用intsetSearch函数进行查找
- intsetSearch 函数注释
- 如果找到返回1，并将pos的值指向找到元素的地址
- 如果找不到返回0，并将pos的会值指定value可以插入的位置
_intsetGet函数最终调用_intsetGetEncoded返回pos位置的值
#define intrev32ifbe(v) (v)
/* Determine whether a value belongs to this set */
uint8_t intsetFind(intset *is, int64_t value) {
uint8_t valenc = _intsetValueEncoding(value);
return valenc <= intrev32ifbe(is->encoding) && intsetSearch(is,value,NULL);
}
/* Search for the position of "value". Return 1 when the value was found and
* sets "pos" to the position of the value within the intset. Return 0 when
* the value is not present in the intset and sets "pos" to the position
* where "value" can be inserted. */
static uint8_t intsetSearch(intset *is, int64_t value, uint32_t *pos) {
int min = 0, max = intrev32ifbe(is->length)-1, mid = -1;
int64_t cur = -1;
/* The value can never be found when the set is empty */
if (intrev32ifbe(is->length) == 0) {
if (pos) *pos = 0;
return 0;
} else {
/* Check for the case where we know we cannot find the value,
* but do know the insert position. */
/** 如果 value 比集合中的最大值大 或者比集合中的最小值小，则肯定在集合中找不到元素 **/
if (value > _intsetGet(is,max)) {
if (pos) *pos = intrev32ifbe(is->length);
return 0;
} else if (value < _intsetGet(is,0)) {
if (pos) *pos = 0;
return 0;
}
}
/** 二分查找 **/
while(max >= min) {
mid = ((unsigned int)min + (unsigned int)max) >> 1;
cur = _intsetGet(is,mid);
if (value > cur) {
min = mid+1;
} else if (value < cur) {
max = mid-1;
} else {
break;
}
}
if (value == cur) {
if (pos) *pos = mid;
return 1;
} else {
if (pos) *pos = min;
return 0;
}
}
/* Return the value at pos, using the configured encoding. */
static int64_t _intsetGet(intset *is, int pos) {
return _intsetGetEncoded(is,pos,intrev32ifbe(is->encoding));
}
/* Return the value at pos, given an encoding. */
static int64_t _intsetGetEncoded(intset *is, int pos, uint8_t enc) {
int64_t v64;
int32_t v32;
int16_t v16;
if (enc == INTSET_ENC_INT64) {
memcpy(&v64,((int64_t*)is->contents)+pos,sizeof(v64));
memrev64ifbe(&v64);
return v64;
} else if (enc == INTSET_ENC_INT32) {
memcpy(&v32,((int32_t*)is->contents)+pos,sizeof(v32));
memrev32ifbe(&v32);
return v32;
} else {
memcpy(&v16,((int16_t*)is->contents)+pos,sizeof(v16));
memrev16ifbe(&v16);
return v16;
}
}
添加元素
- 获取要添加元素的编码值 valuec
- 如果valuec > 当前intset的编码,说明需要扩容(此时说明value肯定在集合中不存在，插入后value会在形成的新集合0或者lenght位置)，调用函数
intsetUpgradeAndAdd（先扩容，修改encoding,然后从由后到前执行复制） - 先进行查重，如果已存在，则无需再次插入；
- 如果存在，则插入，执行的是字节复制，并修改长度
/* Insert an integer in the intset */
intset *intsetAdd(intset *is, int64_t value, uint8_t *success) {
uint8_t valenc = _intsetValueEncoding(value);
uint32_t pos;
if (success) *success = 1;
/* Upgrade encoding if necessary. If we need to upgrade, we know that
* this value should be either appended (if > 0) or prepended (if < 0),
* because it lies outside the range of existing values. */
if (valenc > intrev32ifbe(is->encoding)) {
/* This always succeeds, so we don't need to curry *success. */
return intsetUpgradeAndAdd(is,value);
} else {
/* Abort if the value is already present in the set.
* This call will populate "pos" with the right position to insert
* the value when it cannot be found. */
if (intsetSearch(is,value,&pos)) {
if (success) *success = 0;
return is;
}
is = intsetResize(is,intrev32ifbe(is->length)+1);
if (pos < intrev32ifbe(is->length)) intsetMoveTail(is,pos,pos+1);
}
_intsetSet(is,pos,value);
is->length = intrev32ifbe(intrev32ifbe(is->length)+1);
return is;
}
/* Upgrades the intset to a larger encoding and inserts the given integer. */
static intset *intsetUpgradeAndAdd(intset *is, int64_t value) {
uint8_t curenc = intrev32ifbe(is->encoding);
uint8_t newenc = _intsetValueEncoding(value);
int length = intrev32ifbe(is->length);
int prepend = value < 0 ? 1 : 0;
/* First set new encoding and resize */
is->encoding = intrev32ifbe(newenc);
is = intsetResize(is,intrev32ifbe(is->length)+1);
/* Upgrade back-to-front so we don't overwrite values.
* Note that the "prepend" variable is used to make sure we have an empty
* space at either the beginning or the end of the intset. */
while(length--)
_intsetSet(is,length+prepend,_intsetGetEncoded(is,length,curenc));
/* Set the value at the beginning or the end. */
if (prepend)
_intsetSet(is,0,value);
else
_intsetSet(is,intrev32ifbe(is->length),value);
is->length = intrev32ifbe(intrev32ifbe(is->length)+1);
return is;
}
/* Resize the intset */
static intset *intsetResize(intset *is, uint32_t len) {
uint64_t size = (uint64_t)len*intrev32ifbe(is->encoding);
assert(size <= SIZE_MAX - sizeof(intset));
is = zrealloc(is,sizeof(intset)+size);
return is;
}
删除元素
- 不会导致数组的encoding变化
- 如果要删除元素的encoding 小于等于is的encoding才有元素要移除（小于的原因是可能is已经扩容过）
/* Delete integer from intset */
intset *intsetRemove(intset *is, int64_t value, int *success) {
uint8_t valenc = _intsetValueEncoding(value);
uint32_t pos;
if (success) *success = 0;
if (valenc <= intrev32ifbe(is->encoding) && intsetSearch(is,value,&pos)) {
uint32_t len = intrev32ifbe(is->length);
/* We know we can delete */
if (success) *success = 1;
/* Overwrite value with tail and update length */
if (pos < (len-1)) intsetMoveTail(is,pos+1,pos);
is = intsetResize(is,len-1);
is->length = intrev32ifbe(len-1);
}
return is;
}
