# 数据结构和对象

#include "zmalloc.h"
#define s_malloc zmalloc
#define s_realloc zrealloc
#define s_free zfree

typedef char *sds;

/* Note: sdshdr5 is never used, we just access the flags byte directly.
 * However is here to document the layout of type 5 SDS strings. */
struct __attribute__ ((__packed__)) sdshdr5 {
    /* __attribute__ ((__packed__)) 取消字节对齐*/
    unsigned char flags; /* 3 lsb of type, and 5 msb of string length */
    char buf[];
};
struct __attribute__ ((__packed__)) sdshdr8 {
    uint8_t len; /* used */
    uint8_t alloc; /* excluding the header and null terminator */
    unsigned char flags; /* 3 lsb of type, 5 unused bits */
    char buf[];
};
struct __attribute__ ((__packed__)) sdshdr16 {
    uint16_t len; /* used */
    uint16_t alloc; /* excluding the header and null terminator */
    unsigned char flags; /* 3 lsb of type, 5 unused bits */
    char buf[];
};
struct __attribute__ ((__packed__)) sdshdr32 {
    uint32_t len; /* used */
    uint32_t alloc; /* excluding the header and null terminator */
    unsigned char flags; /* 3 lsb of type, 5 unused bits */
    char buf[];
};
struct __attribute__ ((__packed__)) sdshdr64 {
    uint64_t len; /* used */
    uint64_t alloc; /* excluding the header and null terminator */
    unsigned char flags; /* 3 lsb of type, 5 unused bits */
    char buf[];
};

// 根据字符串sds拿到sdshdr结构体的指针。
//    字符串sds减去相应结构体的大小得到结构体
#define SDS_HDR_VAR(T,s) struct sdshdr##T *sh = (void*)((s)-(sizeof(struct sdshdr##T)));
// 根据字符串sds拿到sdshdr结构体的地址
#define SDS_HDR(T,s) ((struct sdshdr##T *)((s)-(sizeof(struct sdshdr##T))))

static inline size_t sdslen(const sds s) {
    /*
     * inline关键字仅仅是建议编译器做内联展开处理，而不是强制。在gcc编译器中，如果编译优化设置为-O0，即使是inline函数也不会被内联展开，
     * 除非设置了强制内联（__attribute__((always_inline))）属性。
     * */
    unsigned char flags = s[-1];
    switch(flags&SDS_TYPE_MASK) {
        case SDS_TYPE_5:
            return SDS_TYPE_5_LEN(flags);
        case SDS_TYPE_8:
            return SDS_HDR(8,s)->len;
        case SDS_TYPE_16:
            return SDS_HDR(16,s)->len;
        case SDS_TYPE_32:
            return SDS_HDR(32,s)->len;
        case SDS_TYPE_64:
            return SDS_HDR(64,s)->len;
    }
    return 0;
}

sds sdsnew(const char *init) {
    size_t initlen = (init == NULL) ? 0 : strlen(init);
    return sdsnewlen(init, initlen);
}

sds sdsnewlen(const void *init, size_t initlen) {
    void *sh;
    sds s;
    char type = sdsReqType(initlen); /* 根据字符串的长度选择合适的sdshdr类型 */
    /* Empty strings are usually created in order to append. Use type 8
     * since type 5 is not good at this. */
    if (type == SDS_TYPE_5 && initlen == 0) type = SDS_TYPE_8;
    int hdrlen = sdsHdrSize(type);
    unsigned char *fp;

    sh = s_malloc(hdrlen+initlen+1);  /* sds结构长度+起始字符串长度+末尾空字符（1）*/
    if (init==SDS_NOINIT)
        init = NULL;
    else if (!init)
        memset(sh, 0, hdrlen+initlen+1);
    if (sh == NULL) return NULL;
    s = (char*)sh+hdrlen; /* 跳到结构体的最后，拿到sds的指针 */
    fp = ((unsigned char*)s)-1; /* 回过头来拿到结构体中flags成员的指针 */
    switch(type) { /* 初始化结构体成员 */
        case SDS_TYPE_5: {
            *fp = type | (initlen << SDS_TYPE_BITS);
            break;
        }
        case SDS_TYPE_8: {
            SDS_HDR_VAR(8,s);
            sh->len = initlen;
            sh->alloc = initlen;
            *fp = type;
            break;
        }
        case SDS_TYPE_16: {
            SDS_HDR_VAR(16,s);
            sh->len = initlen;
            sh->alloc = initlen;
            *fp = type;
            break;
        }
        case SDS_TYPE_32: {
            SDS_HDR_VAR(32,s);
            sh->len = initlen;
            sh->alloc = initlen;
            *fp = type;
            break;
        }
        case SDS_TYPE_64: {
            SDS_HDR_VAR(64,s);
            sh->len = initlen;
            sh->alloc = initlen;
            *fp = type;
            break;
        }
    }
    if (initlen && init)
        memcpy(s, init, initlen); /* 把字符串保存到sds中 */
    s[initlen] = '\0';  /* 加上\0作为字符串结束符 */
    return s;
}

sds sdscat(sds s, const char *t) {
    return sdscatlen(s, t, strlen(t));
}

sds sdscatlen(sds s, const void *t, size_t len) {
    // 获取当前SDS的长度，sdshdr->len
    size_t curlen = sdslen(s);

    s = sdsMakeRoomFor(s,len);
    if (s == NULL) return NULL;
    // 将目标字符串的内容复制到原SDS后面
    memcpy(s+curlen, t, len);
    // 重新设置sds的长度，即更新sdshdr->len
    sdssetlen(s, curlen+len);
    // sds后面加上'\0'
    s[curlen+len] = '\0';
    return s;
}

sds sdsMakeRoomFor(sds s, size_t addlen) {
    void *sh, *newsh;
    // 计算SDS剩余缓存大小： sdshdr->alloc - sdshdr->len
    size_t avail = sdsavail(s);
    size_t len, newlen;
    char type, oldtype = s[-1] & SDS_TYPE_MASK;
    int hdrlen;

    /* 剩余空间足够addlen长度字符的加入，立即返回 */
    if (avail >= addlen) return s;

    // 当前SDS使用了的长度 sdshdr->len
    len = sdslen(s);
    // 获取SDS的sdshdr结构体的指针
    sh = (char*)s-sdsHdrSize(oldtype);
    newlen = (len+addlen);
    // SDS_MAX_PREALLOC： 字符串最大的预分配长度是1M
    if (newlen < SDS_MAX_PREALLOC)
        newlen *= 2;
    else
        newlen += SDS_MAX_PREALLOC;

    // 根据新的sds字符串的长度重新计算sdshdr的类型
    type = sdsReqType(newlen);

    /* Don't use type 5: the user is appending to the string and type 5 is
     * not able to remember empty space, so sdsMakeRoomFor() must be called
     * at every appending operation. */
    if (type == SDS_TYPE_5) type = SDS_TYPE_8;

    // sdshdr结构体的长度
    hdrlen = sdsHdrSize(type);
    // sdshdr类型没有变，对sdshdr realloc扩容即可
    if (oldtype==type) {
        newsh = s_realloc(sh, hdrlen+newlen+1);
        if (newsh == NULL) return NULL;
        s = (char*)newsh+hdrlen;
    } else {
        /* Since the header size changes, need to move the string forward,
         * and can't use realloc */
        // sdshdr的类型和大小都变了需要创建一个新的sdshdr
        newsh = s_malloc(hdrlen+newlen+1);
        if (newsh == NULL) return NULL;
        // 将s复制到新的sdshdr后面的sds中
        memcpy((char*)newsh+hdrlen, s, len+1);
        // 回收旧的sdshdr
        s_free(sh);
        // 新的sds指针
        s = (char*)newsh+hdrlen;
        // 设置sdshdr的类别
        s[-1] = type;
        // 设置新的sdshdr的长度成员, sdshdr->len
        sdssetlen(s, len);
    }
    sdssetalloc(s, newlen);
    return s;
}

typedef struct listNode {
    struct listNode *prev;
    struct listNode *next;
    void *value;
} listNode;

typedef struct listIter {
    listNode *next;
    int direction;
} listIter;

/* 使用list持有链表 */
typedef struct list {
    // 表头节点
    listNode *head;
    // 表尾节点
    listNode *tail;
    // 链表所包含的节点数量
    unsigned long len;
    // 节点值复制函数
    void *(*dup)(void *ptr);
    // 节点值释放函数
    void (*free)(void *ptr);
    // 节点值对比函数
    int (*match)(void *ptr, void *key);
} list;

typedef struct dict {           /* 字典的结构 */
    dictType *type;             /* 类型特定函数 */
    void *privdata;             /* 私有数据 */
    dictht ht[2];               /* 二元哈希表 */
    long rehashidx;             /* rehash索引进度，值为-1时表示没有在进行rehash */
    unsigned long iterators;    /* 当前运行的迭代器个数 */
} dict;

#define dictIsRehashing(d) ((d)->rehashidx != -1)

typedef struct dictht {         /* 哈希表的结构 */
    dictEntry **table;          /* 哈希表键值对指针数组 */
    unsigned long size;         /* 哈希表的大小 */
    unsigned long sizemask;     /* 哈希表大小掩码，用于计算索引值，总是等于size-1*/
    unsigned long used;         /* 该哈希表已有的节点（键值对）数目 */
} dictht;

h = dictHashKey(d, de->key) & d->ht[1].sizemask;

typedef struct dictEntry {          /* 保存hash表中的键值对 */
    void *key;                      /* 键 */
    union {                         /* 值 */
        void *val;
        uint64_t u64;
        int64_t s64;
        double d;
    } v;
    struct dictEntry *next;         /* 指向哈希表中哈希值相同的下一个节点，用于解决键冲突问题 */
} dictEntry;

uint64_t dictGenHashFunction(const void *key, int len);
uint64_t dictGenCaseHashFunction(const unsigned char *buf, int len);

/* Expand the hash table if needed */
static int _dictExpandIfNeeded(dict *d)
{
    /* 正在hash中，返回 0 */
    if (dictIsRehashing(d)) return DICT_OK;

    /* 如果哈希表是空的，将其扩充到起始大小 */
    if (d->ht[0].size == 0) return dictExpand(d, DICT_HT_INITIAL_SIZE);

    /* If we reached the 1:1 ratio, and we are allowed to resize the hash
     * table (global setting) or we should avoid it but the ratio between
     * elements/buckets is over the "safe" threshold, we resize doubling
     * the number of buckets.
     *
     * 如果比例达到了1:1，并且我们允许调整哈希表的大小或者 键值对的数目/哈希表的大小 超过了
     * 安全阈值，我们将哈希表的大小调整到键值对数目的两倍
     * */
    if (d->ht[0].used >= d->ht[0].size &&
        (dict_can_resize ||
         d->ht[0].used/d->ht[0].size > dict_force_resize_ratio))
    {
        return dictExpand(d, d->ht[0].used*2);
    }
    return DICT_OK;
}

/* Expand or create the hash table
 * 对已有hash表扩容或者创建一个新的hash表ht[1] */
int dictExpand(dict *d, unsigned long size)
{
    /* the size is invalid if it is smaller than the number of
     * elements already inside the hash table 
     * 如果正在reharsh，或者size小于元素（键值对）的个数，那么是无效的
     */
    if (dictIsRehashing(d) || d->ht[0].used > size)
        return DICT_ERR; /* 返回的是1 */

    dictht n; /* the new hash table */
    unsigned long realsize = _dictNextPower(size);

    /* Rehashing to the same table size is not useful. */
    if (realsize == d->ht[0].size) return DICT_ERR;

    /* Allocate the new hash table and initialize all pointers to NULL */
    n.size = realsize;
    n.sizemask = realsize-1;
    n.table = zcalloc(realsize*sizeof(dictEntry*));
    n.used = 0;

    /* Is this the first initialization? If so it's not really a rehashing
     * we just set the first hash table so that it can accept keys. */
    if (d->ht[0].table == NULL) {
        d->ht[0] = n;
        return DICT_OK;
    }

    /* Prepare a second hash table for incremental rehashing */
    d->ht[1] = n;
    d->rehashidx = 0;
    return DICT_OK;
}

/* Rehash for an amount of time between ms milliseconds and ms+1 milliseconds */
int dictRehashMilliseconds(dict *d, int ms) {
    long long start = timeInMilliseconds();
    int rehashes = 0;

    while(dictRehash(d,100)) {
        rehashes += 100;
        if (timeInMilliseconds()-start > ms) break;
    }
    return rehashes;
}

/* This function performs just a step of rehashing, and only if there are
 * no safe iterators bound to our hash table. When we have iterators in the
 * middle of a rehashing we can't mess with the two hash tables otherwise
 * some element can be missed or duplicated.
 *
 * This function is called by common lookup or update operations in the
 * dictionary so that the hash table automatically migrates from H1 to H2
 * while it is actively used. */
static void _dictRehashStep(dict *d) {
    if (d->iterators == 0) dictRehash(d,1);
}

/* Performs N steps of incremental rehashing. Returns 1 if there are still
 * keys to move from the old to the new hash table, otherwise 0 is returned.
 *
 * Note that a rehashing step consists in moving a bucket (that may have more
 * than one key as we use chaining) from the old to the new hash table, however
 * since part of the hash table may be composed of empty spaces, it is not
 * guaranteed that this function will rehash even a single bucket, since it
 * will visit at max N*10 empty buckets in total, otherwise the amount of
 * work it does would be unbound and the function may block for a long time.
 * */
int dictRehash(dict *d, int n) {
    /* 哈希表中会存在大量的空的 buckets，设置最大的数目。否则不可预期结束时间 */
    int empty_visits = n*10; /* Max number of empty buckets to visit. */
    if (!dictIsRehashing(d)) return 0;

    while(n-- && d->ht[0].used != 0) {
        dictEntry *de, *nextde;

        /* Note that rehashidx can't overflow as we are sure there are more
         * elements because ht[0].used != 0 */
        assert(d->ht[0].size > (unsigned long)d->rehashidx);
        while(d->ht[0].table[d->rehashidx] == NULL) { /* 跳过空buckets：如果该table数组该索引是空值，rehashidx加1 */
            d->rehashidx++;
            if (--empty_visits == 0) return 1;
        }
        
        de = d->ht[0].table[d->rehashidx];
        /* Move all the keys in this bucket from the old to the new hash HT */
        while(de) {
            uint64_t h;

            nextde = de->next; /* 之前在同一hash index下的其他键值对重新计算index */
            /* Get the index in the new hash table */
            h = dictHashKey(d, de->key) & d->ht[1].sizemask;
            de->next = d->ht[1].table[h];
            d->ht[1].table[h] = de;
            d->ht[0].used--;
            d->ht[1].used++;
            de = nextde;
        }
        d->ht[0].table[d->rehashidx] = NULL; /* ht[1]的table中该位置清空值 */
        d->rehashidx++;
    }

    /* Check if we already rehashed the whole table...
     * 判断是否整个表以前rehash完成，完成后rehashidx设为-1，原始的ht[0]被ht[1]替代，重新初始化ht[1] */
    if (d->ht[0].used == 0) {
        zfree(d->ht[0].table);
        d->ht[0] = d->ht[1];
        _dictReset(&d->ht[1]);
        d->rehashidx = -1;
        return 0;
    }

    /* More to rehash... */
    return 1;
}

/* Reset a hash table already initialized with ht_init().
 * NOTE: This function should only be called by ht_destroy(). */
static void _dictReset(dictht *ht) /* 初始化dictht表结构 */
{
    ht->table = NULL;
    ht->size = 0;
    ht->sizemask = 0;
    ht->used = 0;
}

/* Create a new hash table */
dict *dictCreate(dictType *type, void *privDataPtr)
{
    dict *d = zmalloc(sizeof(*d));

    _dictInit(d,type,privDataPtr);
    return d;
}

/* 初始化字典结构体 */
int _dictInit(dict *d, dictType *type, void *privDataPtr)
{
    _dictReset(&d->ht[0]);
    _dictReset(&d->ht[1]);
    d->type = type;
    d->privdata = privDataPtr;
    d->rehashidx = -1;
    d->iterators = 0;
    return DICT_OK;
}

/* Add an element to the target hash table */
int dictAdd(dict *d, void *key, void *val)
{
    dictEntry *entry = dictAddRaw(d,key,NULL);

    if (!entry) return DICT_ERR;
    dictSetVal(d, entry, val);
    return DICT_OK;
}

/* Low level add or find:
 * This function adds the entry but instead of setting a value returns the
 * dictEntry structure to the user, that will make sure to fill the value
 * field as he wishes.
 *
 * This function is also directly exposed to the user API to be called
 * mainly in order to store non-pointers inside the hash value, example:
 *
 * entry = dictAddRaw(dict,mykey,NULL);
 * if (entry != NULL) dictSetSignedIntegerVal(entry,1000);
 *
 * Return values:
 *
 * If key already exists NULL is returned, and "*existing" is populated
 * with the existing entry if existing is not NULL.
 *
 * If key was added, the hash entry is returned to be manipulated by the caller.
 */
dictEntry *dictAddRaw(dict *d, void *key, dictEntry **existing)
{
    long index;
    dictEntry *entry;
    dictht *ht;

    if (dictIsRehashing(d)) _dictRehashStep(d);

    /* Get the index of the new element, or -1 if
     * the element already exists. */
    if ((index = _dictKeyIndex(d, key, dictHashKey(d,key), existing)) == -1)
        return NULL;

    /* Allocate the memory and store the new entry.
     * Insert the element in top, with the assumption that in a database
     * system it is more likely that recently added entries are accessed
     * more frequently. */
    ht = dictIsRehashing(d) ? &d->ht[1] : &d->ht[0];
    entry = zmalloc(sizeof(*entry));
    /* 新的键值对插入链表的头部 */
    entry->next = ht->table[index];
    ht->table[index] = entry;
    ht->used++;

    /* Set the hash entry fields. */
    dictSetKey(d, entry, key);
    return entry;
}

/* Returns the index of a free slot that can be populated with
 * a hash entry for the given 'key'.
 * If the key already exists, -1 is returned
 * and the optional output parameter may be filled.
 *
 * Note that if we are in the process of rehashing the hash table, the
 * index is always returned in the context of the second (new) hash table. */
static long _dictKeyIndex(dict *d, const void *key, uint64_t hash, dictEntry **existing)
{
    unsigned long idx, table;
    dictEntry *he;
    if (existing) *existing = NULL; /* 判断existing是否为空指针，如果是则将其指向的值设为NULL */

    /* Expand the hash table if needed */
    if (_dictExpandIfNeeded(d) == DICT_ERR)
        return -1;
    for (table = 0; table <= 1; table++) {
        idx = hash & d->ht[table].sizemask; /* 用hash值与掩码进行与操作得出索引值 */
        /* Search if this slot does not already contain the given key */
        he = d->ht[table].table[idx];   /* 当前索引下的dictEntry */
        while(he) { /* 遍历查找相同key的dictEntry */
            if (key==he->key || dictCompareKeys(d, key, he->key)) {
                if (existing) *existing = he; /* 如果existing不是空指针，将其指向找到的dictEntry */
                return -1;
            }
            he = he->next;
        }
        if (!dictIsRehashing(d)) break; /* 如果没有在rehashing，则遍历ht[1] */
    }
    return idx;
}

#define dictSetKey(d, entry, _key_) do { \
    if ((d)->type->keyDup) \
        (entry)->key = (d)->type->keyDup((d)->privdata, _key_); \
    else \
        (entry)->key = (_key_); \
} while(0)

#define dictSetVal(d, entry, _val_) do { \
    if ((d)->type->valDup) \
        (entry)->v.val = (d)->type->valDup((d)->privdata, _val_); \
    else \
        (entry)->v.val = (_val_); \
} while(0)

/* Search and remove an element. This is an helper function for
 * dictDelete() and dictUnlink(), please check the top comment
 * of those functions. */
static dictEntry *dictGenericDelete(dict *d, const void *key, int nofree) {
    uint64_t h, idx;
    dictEntry *he, *prevHe;
    int table;

    if (d->ht[0].used == 0 && d->ht[1].used == 0) return NULL;

    if (dictIsRehashing(d)) _dictRehashStep(d);
    h = dictHashKey(d, key);

    for (table = 0; table <= 1; table++) {
        idx = h & d->ht[table].sizemask;
        he = d->ht[table].table[idx];
        prevHe = NULL;
        while(he) {
            if (key==he->key || dictCompareKeys(d, key, he->key)) {
                /* Unlink the element from the list */
                if (prevHe)
                    prevHe->next = he->next;
                else
                    d->ht[table].table[idx] = he->next;
                if (!nofree) {
                    dictFreeKey(d, he);
                    dictFreeVal(d, he);
                    zfree(he);
                }
                d->ht[table].used--;
                return he;
            }
            prevHe = he;
            he = he->next;
        }
        if (!dictIsRehashing(d)) break;
    }
    return NULL; /* not found */
}

/* Remove an element, returning DICT_OK on success or DICT_ERR if the
 * element was not found. */
int dictDelete(dict *ht, const void *key) {
    return dictGenericDelete(ht,key,0) ? DICT_OK : DICT_ERR;
}

/* Add or Overwrite:
 * Add an element, discarding the old value if the key already exists.
 * Return 1 if the key was added from scratch, 0 if there was already an
 * element with such key and dictReplace() just performed a value update
 * operation. */
int dictReplace(dict *d, void *key, void *val)
{
    dictEntry *entry, *existing, auxentry;

    /* Try to add the element. If the key
     * does not exists dictAdd will succeed. */
    entry = dictAddRaw(d,key,&existing);
    if (entry) {
        dictSetVal(d, entry, val);
        return 1;
    }

    /* Set the new value and free the old one. Note that it is important
     * to do that in this order, as the value may just be exactly the same
     * as the previous one. In this context, think to reference counting,
     * you want to increment (set), and then decrement (free), and not the
     * reverse. */
    auxentry = *existing;
    dictSetVal(d, existing, val);
    dictFreeVal(d, &auxentry);
    return 0;
}

dictEntry *dictFind(dict *d, const void *key)
{
    dictEntry *he;
    uint64_t h, idx, table;

    if (d->ht[0].used + d->ht[1].used == 0) return NULL; /* dict is empty */
    if (dictIsRehashing(d)) _dictRehashStep(d);
    h = dictHashKey(d, key);
    for (table = 0; table <= 1; table++) {
        idx = h & d->ht[table].sizemask;
        he = d->ht[table].table[idx];
        while(he) {
            if (key==he->key || dictCompareKeys(d, key, he->key))
                return he;
            he = he->next;
        }
        if (!dictIsRehashing(d)) return NULL;
    }
    return NULL;
}

static void _dictRehashStep(dict *d) {
    if (d->iterators == 0) dictRehash(d,1);
}

/* A fingerprint is a 64 bit number that represents the state of the dictionary
 * at a given time, it's just a few dict properties xored together.
 * When an unsafe iterator is initialized, we get the dict fingerprint, and check
 * the fingerprint again when the iterator is released.
 * If the two fingerprints are different it means that the user of the iterator
 * performed forbidden operations against the dictionary while iterating. */
long long dictFingerprint(dict *d) {
    long long integers[6], hash = 0;
    int j;

    integers[0] = (long) d->ht[0].table;
    integers[1] = d->ht[0].size;
    integers[2] = d->ht[0].used;
    integers[3] = (long) d->ht[1].table;
    integers[4] = d->ht[1].size;
    integers[5] = d->ht[1].used;

    /* We hash N integers by summing every successive integer with the integer
     * hashing of the previous sum. Basically:
     *
     * Result = hash(hash(hash(int1)+int2)+int3) ...
     *
     * This way the same set of integers in a different order will (likely) hash
     * to a different number. */
    for (j = 0; j < 6; j++) {
        hash += integers[j];
        /* For the hashing step we use Tomas Wang's 64 bit integer hash. */
        hash = (~hash) + (hash << 21); // hash = (hash << 21) - hash - 1;
        hash = hash ^ (hash >> 24);
        hash = (hash + (hash << 3)) + (hash << 8); // hash * 265
        hash = hash ^ (hash >> 14);
        hash = (hash + (hash << 2)) + (hash << 4); // hash * 21
        hash = hash ^ (hash >> 28);
        hash = hash + (hash << 31);
    }
    return hash;
}

/* dictScan() is used to iterate over the elements of a dictionary.
 *
 * Iterating works the following way:
 *
 * 1) Initially you call the function using a cursor (v) value of 0.
 * 2) The function performs one step of the iteration, and returns the
 *    new cursor value you must use in the next call.
 * 3) When the returned cursor is 0, the iteration is complete.
 *
 * The function guarantees all elements present in the
 * dictionary get returned between the start and end of the iteration.
 * However it is possible some elements get returned multiple times.
 *
 * For every element returned, the callback argument 'fn' is
 * called with 'privdata' as first argument and the dictionary entry
 * 'de' as second argument.
 *
 * HOW IT WORKS.
 *
 * The iteration algorithm was designed by Pieter Noordhuis.
 * The main idea is to increment a cursor starting from the higher order
 * bits. That is, instead of incrementing the cursor normally, the bits
 * of the cursor are reversed, then the cursor is incremented, and finally
 * the bits are reversed again.
 *
 * This strategy is needed because the hash table may be resized between
 * iteration calls.
 *
 * dict.c hash tables are always power of two in size, and they
 * use chaining, so the position of an element in a given table is given
 * by computing the bitwise AND between Hash(key) and SIZE-1
 * (where SIZE-1 is always the mask that is equivalent to taking the rest
 *  of the division between the Hash of the key and SIZE).
 *
 * For example if the current hash table size is 16, the mask is
 * (in binary) 1111. The position of a key in the hash table will always be
 * the last four bits of the hash output, and so forth.
 *
 * WHAT HAPPENS IF THE TABLE CHANGES IN SIZE?
 *
 * If the hash table grows, elements can go anywhere in one multiple of
 * the old bucket: for example let's say we already iterated with
 * a 4 bit cursor 1100 (the mask is 1111 because hash table size = 16).
 *
 * If the hash table will be resized to 64 elements, then the new mask will
 * be 111111. The new buckets you obtain by substituting in ??1100
 * with either 0 or 1 can be targeted only by keys we already visited
 * when scanning the bucket 1100 in the smaller hash table.
 *
 * By iterating the higher bits first, because of the inverted counter, the
 * cursor does not need to restart if the table size gets bigger. It will
 * continue iterating using cursors without '1100' at the end, and also
 * without any other combination of the final 4 bits already explored.
 *
 * Similarly when the table size shrinks over time, for example going from
 * 16 to 8, if a combination of the lower three bits (the mask for size 8
 * is 111) were already completely explored, it would not be visited again
 * because we are sure we tried, for example, both 0111 and 1111 (all the
 * variations of the higher bit) so we don't need to test it again.
 *
 * WAIT... YOU HAVE *TWO* TABLES DURING REHASHING!
 *
 * Yes, this is true, but we always iterate the smaller table first, then
 * we test all the expansions of the current cursor into the larger
 * table. For example if the current cursor is 101 and we also have a
 * larger table of size 16, we also test (0)101 and (1)101 inside the larger
 * table. This reduces the problem back to having only one table, where
 * the larger one, if it exists, is just an expansion of the smaller one.
 *
 * LIMITATIONS
 *
 * This iterator is completely stateless, and this is a huge advantage,
 * including no additional memory used.
 *
 * The disadvantages resulting from this design are:
 *
 * 1) It is possible we return elements more than once. However this is usually
 *    easy to deal with in the application level.
 * 2) The iterator must return multiple elements per call, as it needs to always
 *    return all the keys chained in a given bucket, and all the expansions, so
 *    we are sure we don't miss keys moving during rehashing.
 * 3) The reverse cursor is somewhat hard to understand at first, but this
 *    comment is supposed to help.
 */
unsigned long dictScan(dict *d,
                       unsigned long v,
                       dictScanFunction *fn,
                       dictScanBucketFunction* bucketfn,
                       void *privdata)
{
    dictht *t0, *t1;
    const dictEntry *de, *next;
    unsigned long m0, m1;

    if (dictSize(d) == 0) return 0;

    if (!dictIsRehashing(d)) {
        t0 = &(d->ht[0]);
        m0 = t0->sizemask;

        /* Emit entries at cursor */
        if (bucketfn) bucketfn(privdata, &t0->table[v & m0]);
        de = t0->table[v & m0];
        while (de) {
            next = de->next;
            fn(privdata, de);
            de = next;
        }

        /* Set unmasked bits so incrementing the reversed cursor
         * operates on the masked bits */
        v |= ~m0;

        /* Increment the reverse cursor */
        v = rev(v);
        v++;
        v = rev(v);

    } else {
        t0 = &d->ht[0];
        t1 = &d->ht[1];

        /* Make sure t0 is the smaller and t1 is the bigger table */
        if (t0->size > t1->size) {
            t0 = &d->ht[1];
            t1 = &d->ht[0];
        }

        m0 = t0->sizemask;
        m1 = t1->sizemask;

        /* Emit entries at cursor */
        if (bucketfn) bucketfn(privdata, &t0->table[v & m0]);
        de = t0->table[v & m0];
        while (de) {
            next = de->next;
            fn(privdata, de);
            de = next;
        }

        /* Iterate over indices in larger table that are the expansion
         * of the index pointed to by the cursor in the smaller table */
        do {
            /* Emit entries at cursor */
            if (bucketfn) bucketfn(privdata, &t1->table[v & m1]);
            de = t1->table[v & m1];
            while (de) {
                next = de->next;
                fn(privdata, de);
                de = next;
            }

            /* Increment the reverse cursor not covered by the smaller mask.*/
            v |= ~m1;
            v = rev(v);
            v++;
            v = rev(v);

            /* Continue while bits covered by mask difference is non-zero */
        } while (v & (m0 ^ m1));
    }

    return v;
}

/* ZSETs use a specialized version of Skiplists */
typedef struct zskiplistNode {
    sds ele;
    double score;                           /* 分值，跳跃表中的节点按各自的分值从小到大排列 */
    struct zskiplistNode *backward;         /* 后退指针 */
    struct zskiplistLevel {
        struct zskiplistNode *forward;      /* 前进指针 */
        unsigned int span;                  /* 跨度，前进指针所指向节点和当前节点的距离 */
    } level[];                              /* 层 */
} zskiplistNode;

typedef struct zskiplist {
    struct zskiplistNode *header, *tail; /* 跳跃表的头尾指针 */
    unsigned long length;                /* 跳跃表的长度 */
    int level;                           /* 目前跳跃表内，层数最大的那个节点的层数（表头节点不计算在内）*/
} zskiplist;

typedef struct zset {
    dict *dict;
    zskiplist *zsl;
} zset;

typedef struct intset {
    uint32_t encoding;  /* 编码方式 */
    uint32_t length;    /* 集合包含的元素数目 */
    int8_t contents[];  /* 保存元素的数组。虽然声明为int8_t类型的数组，但实际上并不保存该类型的值，数组类型取决于encoding属性的值 */
} intset;

/* Resize the intset */
static intset *intsetResize(intset *is, uint32_t len) {
    uint32_t size = len*intrev32ifbe(is->encoding);
    is = zrealloc(is,sizeof(intset)+size); /*  realloc函数用于修改一个原先已经分配的内存块的大小，可以使一块内存的扩大或缩小。 */
    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--) /* 从后往前写，这样就不会覆盖数据 */
        _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;
}

/* 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;
}

/* 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. */
        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;
        }
    }

    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;
    }
}

typedef struct redisObject {
    unsigned type:4;        /* 对象的类型 */
    unsigned encoding:4;    /* 对象的编码，ptr指向对象的底层实现结构，结构由这个属性决定。
                            * 通过encoding属性来设定对象所使用的编码，而不是特定类型的对象关联一种固定的编码，
                            * 可以极大的提升redis的灵活性和效率。
                            * */
    unsigned lru:LRU_BITS; /* LRU time (relative to global lru_clock) or
                            * LFU data (least significant 8 bits frequency
                            * and most significant 16 bits access time). */
    int refcount;          /* 引用计数 */
    void *ptr;
} robj;

/* The actual Redis Object */
#define OBJ_STRING 0    /* String object. */
#define OBJ_LIST 1      /* List object. */
#define OBJ_SET 2       /* Set object. */
#define OBJ_ZSET 3      /* Sorted set object. */
#define OBJ_HASH 4      /* Hash object. */

/* The "module" object type is a special one that signals that the object
 * is one directly managed by a Redis module. In this case the value points
 * to a moduleValue struct, which contains the object value (which is only
 * handled by the module itself) and the RedisModuleType struct which lists
 * function pointers in order to serialize, deserialize, AOF-rewrite and
 * free the object.
 *
 * Inside the RDB file, module types are encoded as OBJ_MODULE followed
 * by a 64 bit module type ID, which has a 54 bits module-specific signature
 * in order to dispatch the loading to the right module, plus a 10 bits
 * encoding version. */
#define OBJ_MODULE 5    /* Module object. */
#define OBJ_STREAM 6    /* Stream object. */

/* Objects encoding. Some kind of objects like Strings and Hashes can be
 * internally represented in multiple ways. The 'encoding' field of the object
 * is set to one of this fields for this object. */
#define OBJ_ENCODING_RAW 0     /* Raw representation */
#define OBJ_ENCODING_INT 1     /* Encoded as integer */
#define OBJ_ENCODING_HT 2      /* Encoded as hash table */
#define OBJ_ENCODING_ZIPMAP 3  /* Encoded as zipmap */
#define OBJ_ENCODING_LINKEDLIST 4 /* No longer used: old list encoding. */
#define OBJ_ENCODING_ZIPLIST 5 /* Encoded as ziplist */
#define OBJ_ENCODING_INTSET 6  /* Encoded as intset */
#define OBJ_ENCODING_SKIPLIST 7  /* Encoded as skiplist */
#define OBJ_ENCODING_EMBSTR 8  /* Embedded sds string encoding */
#define OBJ_ENCODING_QUICKLIST 9 /* Encoded as linked list of ziplists */
#define OBJ_ENCODING_STREAM 10 /* Encoded as a radix tree of listpacks */

robj *createObject(int type, void *ptr) {
    robj *o = zmalloc(sizeof(*o));
    o->type = type;
    o->encoding = OBJ_ENCODING_RAW;
    o->ptr = ptr;
    o->refcount = 1;

    /* Set the LRU to the current lruclock (minutes resolution), or
     * alternatively the LFU counter. */
    if (server.maxmemory_policy & MAXMEMORY_FLAG_LFU) {
        o->lru = (LFUGetTimeInMinutes()<<8) | LFU_INIT_VAL;
    } else {
        o->lru = LRU_CLOCK();
    }
    return o;
}

robj *createObject(int type, void *ptr);
robj *createStringObject(const char *ptr, size_t len);
robj *createRawStringObject(const char *ptr, size_t len);
robj *createEmbeddedStringObject(const char *ptr, size_t len);
robj *createStringObjectFromLongLong(long long value);
robj *createStringObjectFromLongLongForValue(long long value);
robj *createStringObjectFromLongDouble(long double value, int humanfriendly);
robj *createQuicklistObject(void);
robj *createZiplistObject(void);
robj *createSetObject(void);
robj *createIntsetObject(void);
robj *createHashObject(void);
robj *createZsetObject(void);
robj *createZsetZiplistObject(void);
robj *createStreamObject(void);
robj *createModuleObject(moduleType *mt, void *value);

/* A redis object, that is a type able to hold a string / list / set */

/* The actual Redis Object */
#define OBJ_STRING 0    /* String object. */
#define OBJ_LIST 1      /* List object. */
#define OBJ_SET 2       /* Set object. */
#define OBJ_ZSET 3      /* Sorted set object. */
#define OBJ_HASH 4      /* Hash object. */

/* The "module" object type is a special one that signals that the object
 * is one directly managed by a Redis module. In this case the value points
 * to a moduleValue struct, which contains the object value (which is only
 * handled by the module itself) and the RedisModuleType struct which lists
 * function pointers in order to serialize, deserialize, AOF-rewrite and
 * free the object.
 *
 * Inside the RDB file, module types are encoded as OBJ_MODULE followed
 * by a 64 bit module type ID, which has a 54 bits module-specific signature
 * in order to dispatch the loading to the right module, plus a 10 bits
 * encoding version. */
#define OBJ_MODULE 5    /* Module object. */
#define OBJ_STREAM 6    /* Stream object. */

void decrRefCount(robj *o) {
    if (o->refcount == 1) {
        switch(o->type) {
        case OBJ_STRING: freeStringObject(o); break;
        case OBJ_LIST: freeListObject(o); break;
        case OBJ_SET: freeSetObject(o); break;
        case OBJ_ZSET: freeZsetObject(o); break;
        case OBJ_HASH: freeHashObject(o); break;
        case OBJ_MODULE: freeModuleObject(o); break;
        case OBJ_STREAM: freeStreamObject(o); break;
        default: serverPanic("Unknown object type"); break;
        }
        zfree(o);
    } else {
        if (o->refcount <= 0) serverPanic("decrRefCount against refcount <= 0");
        if (o->refcount != OBJ_SHARED_REFCOUNT) o->refcount--;
    }
}

// 引用计数减 1
void incrRefCount(robj *o) {
    if (o->refcount != OBJ_SHARED_REFCOUNT) o->refcount++;
}

// 设置共享对象的引用计数
robj *makeObjectShared(robj *o) {
    serverAssert(o->refcount == 1);
    o->refcount = OBJ_SHARED_REFCOUNT;
    return o;
}

void freeStringObject(robj *o) {
    if (o->encoding == OBJ_ENCODING_RAW) {
        sdsfree(o->ptr);
    }
}

void freeListObject(robj *o) {
    if (o->encoding == OBJ_ENCODING_QUICKLIST) {
        quicklistRelease(o->ptr);
    } else {
        serverPanic("Unknown list encoding type");
    }
}

void freeSetObject(robj *o) {
    switch (o->encoding) {
    case OBJ_ENCODING_HT:
        dictRelease((dict*) o->ptr);
        break;
    case OBJ_ENCODING_INTSET:
        zfree(o->ptr);
        break;
    default:
        serverPanic("Unknown set encoding type");
    }
}

void freeZsetObject(robj *o) {
    zset *zs;
    switch (o->encoding) {
    case OBJ_ENCODING_SKIPLIST:
        zs = o->ptr;
        dictRelease(zs->dict);
        zslFree(zs->zsl);
        zfree(zs);
        break;
    case OBJ_ENCODING_ZIPLIST:
        zfree(o->ptr);
        break;
    default:
        serverPanic("Unknown sorted set encoding");
    }
}

void freeHashObject(robj *o) {
    switch (o->encoding) {
    case OBJ_ENCODING_HT:
        dictRelease((dict*) o->ptr);
        break;
    case OBJ_ENCODING_ZIPLIST:
        zfree(o->ptr);
        break;
    default:
        serverPanic("Unknown hash encoding type");
        break;
    }
}

typedef struct redisDb {
    dict *dict;                 /* 键空间 The keyspace for this DB */
    dict *expires;              /* Timeout of keys with a timeout set */
    dict *blocking_keys;        /* Keys with clients waiting for data (BLPOP)*/
    dict *ready_keys;           /* Blocked keys that received a PUSH */
    dict *watched_keys;         /* WATCHED keys for MULTI/EXEC CAS */
    int id;                     /* Database ID */
    long long avg_ttl;          /* Average TTL, just for stats */
    list *defrag_later;         /* List of key names to attempt to defrag one by one, gradually. */
} redisDb;

struct redisServer {
    /* General */
    pid_t pid;                  /* Main process pid. */
    char *configfile;           /* Absolute config file path, or NULL */
    char *executable;           /* Absolute executable file path. */
    char **exec_argv;           /* Executable argv vector (copy). */
    int dynamic_hz;             /* Change hz value depending on # of clients. */
    int config_hz;              /* Configured HZ value. May be different than
                                   the actual 'hz' field value if dynamic-hz
                                   is enabled. */
    int hz;                     /* serverCron() calls frequency in hertz */
    redisDb *db;                /* 数组，保存这服务器所有的数据库 */
    dict *commands;             /* Command table */
    dict *orig_commands;        /* Command table before command renaming. */
    aeEventLoop *el;
    // ...
};

/* With multiplexing we need to take per-client state.
 * Clients are taken in a linked list. */
typedef struct client {
    uint64_t id;            /* Client incremental unique ID. */
    int fd;                 /* Client socket. */
    redisDb *db;            /* Pointer to currently SELECTed DB. */
    robj *name;             /* As set by CLIENT SETNAME. */
    // ...
} client;