結合redis設計與實現的redis源碼學習-6-intset(整數集合)

整數集合是集合鍵的底層實現之一,當一個集合只包含整數值元素,並且這個結合的元素數量不多時,redis就會使用整數集合作爲集合建的底層實現。它可以保存類型爲int16_t,int32_t,int64_t的整數值,並且保證集合中不會出現重複元素。
整數集合具有以下特性:
1、整數集合的底層實現是數組,這個數組以有序,無重複的方式保存集合元素,在需要時,會根據新添加元素的類型來改變這個數組的類型;
2、升級操作爲整數集合帶來了操作上的靈活性,儘可能的節約了內存,但是不可降級;
上代碼:

#ifndef __INTSET_H
#define __INTSET_H
#include <stdint.h>

typedef struct intset{
//編碼方式
    uint32_t encoding;
    //整數集合包含的元素數量
    uint32_t length;
    //保存元素的數組,集合的每個元素都是contents的一個數組項,按值得大小從小到大有序排列且不重複
    int8_t contents[];
}intset;

intset *intsetNew(void);
intset *intsetAdd(intset *is, int64_t value, uint8_t *success);
intset *intsetRemove(intset *is, int64_t value, int *success);
uint8_t intsetFind(intset *is, int64_t value);
int64_t intsetRandom(intset *is);
uint8_t intsetGet(intset *is, uint32_t pos, int64_t *value);
uint32_t intsetLen(intset *is);
size_t intsetBlobLen(intset *is);

#ifdef REDIS_TEST
int intsetTest(int argc, char *argv[]); //測試函數,這裏我沒有貼上
#endif

#endif // __INTSET_H

.c文件

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "intset.h"
#include "zmalloc.h"
#include "endianconv.h"//大小端轉換的頭文件

/* Note that these encodings are ordered, so:宏定義計算各類型長度
 * 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))

/* 判斷存儲的數據大小Return the required encoding for the provided value. */
static uint8_t _intsetValueEncoding(int64_t v) {
    if (v < INT32_MIN || v > INT32_MAX)
        return INTSET_ENC_INT64;
    else if (v < INT16_MIN || v > INT16_MAX)
        return INTSET_ENC_INT32;
    else
        return INTSET_ENC_INT16;
}
/* Return the value at pos, given an encoding. 根據編碼和位置返回數值*/
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);//這些是轉換大小端的
        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;
    }
}
/* Return the value at pos, using the configured encoding. 返回排第幾的數*/
static int64_t _intsetGet(intset *is, int pos) {
    return _intsetGetEncoded(is,pos,intrev32ifbe(is->encoding));
}
/* Set the value at pos, using the configured encoding. 在某一位置設置值*/
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. 創建一個空整數集合*/
intset *intsetNew(void) {
    intset *is = zmalloc(sizeof(intset));
    is->encoding = intrev32ifbe(INTSET_ENC_INT16);
    is->length = 0;
    return is;
}

/* Resize the intset ,重置整數集合大小*/
static intset *intsetResize(intset *is, uint32_t len) {
    uint32_t size = len*intrev32ifbe(is->encoding);
    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.尋找插入點的位置 */
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;//空集合直接返回0位
        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,intrev32ifbe(is->length)-1)) {
            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;
    }
}
//升級整數集合的編碼大小
/* 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;
}
//移動整數集合的數值位置
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);
//根據編碼方式拷貝大小
    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);
    }
    memmove(dst,src,bytes);
}

/* Insert an integer in the intset 將給定元素插入到整數集合中*/
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. 升級整數集合*/
        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;//如果這個元素已經存在了,那麼直接返回現有集合
        }

        is = intsetResize(is,intrev32ifbe(is->length)+1);//增加一個元素位置
        if (pos < intrev32ifbe(is->length)) intsetMoveTail(is,pos,pos+1);//移動元素
    }

    _intsetSet(is,pos,value);//插入位置
    is->length = intrev32ifbe(intrev32ifbe(is->length)+1);
    return is;
}

/* Delete integer from intset 從整數集合中移除給定元素*/
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);//移動元素
        is = intsetResize(is,len-1);
        is->length = intrev32ifbe(len-1);
    }
    return is;
}
/* Determine whether a value belongs to this set 檢查給定值是否存在於集合中 */
uint8_t intsetFind(intset *is, int64_t value) {
    uint8_t valenc = _intsetValueEncoding(value);
    return valenc <= intrev32ifbe(is->encoding) && intsetSearch(is,value,NULL);
}

/* Return random member 隨機返回集合中的一個值*/
int64_t intsetRandom(intset *is) {
    return _intsetGet(is,rand()%intrev32ifbe(is->length));
}

/* Sets the value to the value at the given position. When this position is
 * out of range the function returns 0, when in range it returns 1. 
 * 取出底層數組在給定索引上的元素*/
uint8_t intsetGet(intset *is, uint32_t pos, int64_t *value) {
    if (pos < intrev32ifbe(is->length)) {
        *value = _intsetGet(is,pos);
        return 1;
    }
    return 0;
}

/* Return intset length 返回整數集合包含的元素個數 */
uint32_t intsetLen(intset *is) {
    return intrev32ifbe(is->length);
}

/* Return intset blob size in bytes. 返回整數集合所佔用的內存字節數 */
size_t intsetBlobLen(intset *is) {
    return sizeof(intset)+intrev32ifbe(is->length)*intrev32ifbe(is->encoding);
}
//還有一些測試函數,在此不表
發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章