redis 源码 -- intset

typedef struct intset {
    uint32_t encoding;
    uint32_t length;
    int8_t contents[];
} intset;

/* Note that these encodings are ordered, so:
 * INTSET_ENC_INT16 < INTSET_ENC_INT32 < INTSET_ENC_INT64. */
#define INTSET_ENC_INT16 (sizeof(int16_t))
#define INTSET_ENC_INT32 (sizeof(int32_t))
#define INTSET_ENC_INT64 (sizeof(int64_t))

2 方法

/* 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;
    }
}

/* Set the value at pos, using the configured encoding. */
static void _intsetSet(intset *is, int pos, int64_t value) {
    uint32_t encoding = intrev32ifbe(is->encoding);

    if (encoding == INTSET_ENC_INT64) {
        ((int64_t*)is->contents)[pos] = value;
        memrev64ifbe(((int64_t*)is->contents)+pos);
    } else if (encoding == INTSET_ENC_INT32) {
        ((int32_t*)is->contents)[pos] = value;
        memrev32ifbe(((int32_t*)is->contents)+pos);
    } else {
        ((int16_t*)is->contents)[pos] = value;
        memrev16ifbe(((int16_t*)is->contents)+pos);
    }
}

/* Create an empty intset. */
intset *intsetNew(void) {
    intset *is = zmalloc(sizeof(intset));          // zmalloc 前面是长度PREFIX_SIZE , 后面是PADDING， 凑够sizeof(long) 内存对齐
    is->encoding = intrev32ifbe(INTSET_ENC_INT16); // 初始为16为整形
    is->length = 0;
    return is;
}

/* Resize the intset */
static intset *intsetResize(intset *is, uint32_t len) {
    uint32_t size = len*intrev32ifbe(is->encoding);	// encoding 就是一个元素的长度，参数len是数量，（预留一些空间，比inset结构原有元素要多一点）
    is = zrealloc(is,sizeof(intset)+size);		// 
    return is;
}

/* 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. */
/**
  检索value的位置，采用二分查找算法。
  返回值1表示value被查找到，设置pos 等于值所在的位置；
  返回值0表示没有找到value，pos是可以插入的位置。
*/
static uint8_t intsetSearch(intset *is, int64_t value, uint32_t *pos) {
	// 数组长度使用4字节整型
    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 */
	// 长度为0，直接返回
    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. */
		//  大于最大的整型
        if (value > _intsetGet(is,intrev32ifbe(is->length)-1)) {
            if (pos) *pos = intrev32ifbe(is->length);
            return 0;
		//  小于最小的
        } 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;
        }
    }

	// 查到了，设置value的位置
    if (value == cur) {
        if (pos) *pos = mid;
        return 1;
    } else {
	// 没查到
        if (pos) *pos = min;
        return 0;
    }
}

/* Upgrades the intset to a larger encoding and inserts the given integer. */
/**
 提升编码并且添加一个值。16-->32-->64位编码
 
*/
static intset *intsetUpgradeAndAdd(intset *is, int64_t value) {
    uint8_t curenc = intrev32ifbe(is->encoding);
    uint8_t newenc = _intsetValueEncoding(value);
    int length = intrev32ifbe(is->length);
	// prepend做什么用的？
    int prepend = value < 0 ? 1 : 0;

    /* First set new encoding and resize */
	// 设置新的encoding
    is->encoding = intrev32ifbe(newenc);
	// resize通过realloc方法重新分配内存，数据内容会拷贝到新内存
	// 为什么多了一个单位？
    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. */
	/**
	 从后向前reset，不会覆盖掉数据，（因为新申请了一份内存空间，原来的低encoding的数都在最前面）
	*/
    while(length--)
		// 按照旧的encoding从intset（is）里面获取数值；is里面的encoding已经在resize前设置成新的
		// 如果新增数据 <0,最前面会空一格位置 prepend, 为什么？
        _intsetSet(is,length+prepend,_intsetGetEncoded(is,length,curenc));

    /* Set the value at the beginning or the end. */
	/** 源码证明，这个value只是个占位符，不是实际要插入的数据；必须必最大的大，或者比最小的小；
	    如果比最小的小，则放在最前面；否则放在最后面
	*/
    if (prepend)
        _intsetSet(is,0,value);
    else
        _intsetSet(is,intrev32ifbe(is->length),value);
    is->length = intrev32ifbe(intrev32ifbe(is->length)+1);
    return is;
}

/**
  向后搬一段，这一段有多长；从from开始到数组结束；is->length - from
*/
static void intsetMoveTail(intset *is, uint32_t from, uint32_t to) {
    void *src, *dst;
    uint32_t bytes = intrev32ifbe(is->length)-from;
    uint32_t encoding = intrev32ifbe(is->encoding);

    if (encoding == INTSET_ENC_INT64) {
        src = (int64_t*)is->contents+from;
        dst = (int64_t*)is->contents+to;
        bytes *= sizeof(int64_t);
    } else if (encoding == INTSET_ENC_INT32) {
        src = (int32_t*)is->contents+from;
        dst = (int32_t*)is->contents+to;
        bytes *= sizeof(int32_t);
    } else {
        src = (int16_t*)is->contents+from;
        dst = (int16_t*)is->contents+to;
        bytes *= sizeof(int16_t);
    }
	// 有别于memcpy函数，如果目标和源有重叠；不会丢数据
    memmove(dst,src,bytes);
}

memcpy和memmove（）都是C语言中的库函数，在头文件string.h中，作用是拷贝一定长度的内存的内容，原型分别如下：
void *memcpy(void *dst, const void *src, size_t count);

void *memmove(void *dst, const void *src, size_t count); 

他们的作用是一样的，唯一的区别是，当内存发生局部重叠的时候，memmove保证拷贝的结果是正确的，memcpy不保证拷贝的结果的正确。


第一种情况下，拷贝重叠的区域不会出现问题，内容均可以正确的被拷贝。
第二种情况下，问题出现在

/* Insert an integer in the intset */
intset *intsetAdd(intset *is, int64_t value, uint8_t *success) {
	// 获取值的encoding
    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. */
	// 如果添加值的encoding大于inset中原来的encoding则扩容
	// 为什么大于0就append，小于0就prepend呢？？？
    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. */
		// 如果添加的值已经存在，直接返回
        if (intsetSearch(is,value,&pos)) {
            if (success) *success = 0;
            return is;
        }

		// 如果添加值不存在，先扩容 + 1；然后pos后面的数组往后平移一个单位
        is = intsetResize(is,intrev32ifbe(is->length)+1);
        if (pos < intrev32ifbe(is->length)) intsetMoveTail(is,pos,pos+1);
    }

	// 设置新增的值
    _intsetSet(is,pos,value);
	// 更新length
    is->length = intrev32ifbe(intrev32ifbe(is->length)+1);
    return is;
}

/* 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 */
		// 如果不是最后一个，pos后面的统统往前挪一个位置
        if (pos < (len-1)) intsetMoveTail(is,pos+1,pos);
        is = intsetResize(is,len-1);
		// realloc方法，如果空间够，继续使用原来的内存；返回新的指针指向老内存，不需要free原来的指针
        is->length = intrev32ifbe(len-1);
    }
    return is;
}