redis源码解析（二）动态字符串sds基本功能函数

1. 简介

  本文继上文基础上，分析动态字符串的功能函数，位于sds.c。由于函数较多，本篇介绍实现动态变化的基本增删新建释放函数。

2. 源码分析

  sdsHdrSize()函数用于返回sdshdr的大小，主要使用sizeof()函数实现。

/*返回sdshdr大小，主要使用sizeof()函数*/
static inline int sdsHdrSize(char type) {
    switch(type&SDS_TYPE_MASK) {
        case SDS_TYPE_5:
            return sizeof(struct sdshdr5);
        case SDS_TYPE_8:
            return sizeof(struct sdshdr8);
        case SDS_TYPE_16:
            return sizeof(struct sdshdr16);
        case SDS_TYPE_32:
            return sizeof(struct sdshdr32);
        case SDS_TYPE_64:
            return sizeof(struct sdshdr64);
    }
    return 0;
}

  sdsReqType()根据size返回sdsHdr类型

/*根据size返回sds的类型*/
static inline char sdsReqType(size_t string_size) {
    if (string_size < 1<<5)
        return SDS_TYPE_5;
    if (string_size < 1<<8)
        return SDS_TYPE_8;
    if (string_size < 1<<16)
        return SDS_TYPE_16;
#if (LONG_MAX == LLONG_MAX)
    if (string_size < 1ll<<32)
        return SDS_TYPE_32;
#endif
    return SDS_TYPE_64;
}

  sdsnewlen()函数创建新的sds动态数组

/* 初始化函数
 * Create a new sds string with the content specified by the 'init' pointer
 * and 'initlen'.
 * If NULL is used for 'init' the string is initialized with zero bytes.
 *
 * The string is always null-termined (all the sds strings are, always) so
 * even if you create an sds string with:
 *
 * mystring = sdsnewlen("abc",3);
 *
 * You can print the string with printf() as there is an implicit \0 at the
 * end of the string. However the string is binary safe and can contain
 * \0 characters in the middle, as the length is stored in the sds header. */
sds sdsnewlen(const void *init, size_t initlen) {
    void *sh;
    sds s;
	/*根据initlen返回type*/
    char type = sdsReqType(initlen);
    /* 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;
	/*hdrlen赋值为sds的size*/
    int hdrlen = sdsHdrSize(type);
    unsigned char *fp; /* flags pointer. */

	/*分配空间*/
    sh = s_malloc(hdrlen+initlen+1);
    if (!init)
        memset(sh, 0, hdrlen+initlen+1);

	/*错误返回*/
    if (sh == NULL) return NULL;
	/*s指向数据，fp为首指针前一位，指向flag，存储type*/
    s = (char*)sh+hdrlen;
    fp = ((unsigned char*)s)-1;
    switch(type) {
        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);
    s[initlen] = '\0';
    return s;
}

  sdsempty()函数利用sdsnewlen创建空sds动态数组

/* 创建空sds
 * Create an empty (zero length) sds string. Even in this case the string
 * always has an implicit null term. */
sds sdsempty(void) {
    return sdsnewlen("",0);
}

  sdsnew()利用sdsnewlen()创建sds动态数组

/* 创建新sds
 * Create a new sds string starting from a null terminated C string. 
 */
sds sdsnew(const char *init) {
    size_t initlen = (init == NULL) ? 0 : strlen(init);
    return sdsnewlen(init, initlen);
}

  sdsdup()函数使用sdsnewlen()复制已有的sds

/* 复制sds
 * Duplicate an sds string. 
 */
sds sdsdup(const sds s) {
    return sdsnewlen(s, sdslen(s));
}

  sdsfree()函数释放sds的空间

/* 释放sds
 * Free an sds string. No operation is performed if 's' is NULL. 
 */
void sdsfree(sds s) {
    if (s == NULL) return;
    s_free((char*)s-sdsHdrSize(s[-1]));
}

  sdsupdatelen()函数更新sdsHdr的长度

/* 当sds数据变化后，调用该函数更新sds长度
 * Set the sds string length to the length as obtained with strlen(), so
 * considering as content only up to the first null term character.
 *
 * This function is useful when the sds string is hacked manually in some
 * way, like in the following example:
 *
 * s = sdsnew("foobar");
 * s[2] = '\0';
 * sdsupdatelen(s);
 * printf("%d\n", sdslen(s));
 *
 * The output will be "2", but if we comment out the call to sdsupdatelen()
 * the output will be "6" as the string was modified but the logical length
 * remains 6 bytes. */
void sdsupdatelen(sds s) {
    size_t reallen = strlen(s);
    sdssetlen(s, reallen);
}

  sdsclear()函数将sds长度和内容置零

/* 清空sds
 * Modify an sds string in-place to make it empty (zero length).
 * However all the existing buffer is not discarded but set as free space
 * so that next append operations will not require allocations up to the
 * number of bytes previously available. */
void sdsclear(sds s) {
    sdssetlen(s, 0);
    s[0] = '\0';
}

  动态字符串之扩容：sdsMakeRoomFor()函数。根据增加的addlen来调整sdsHdr的类型。

/* sds扩容
 * Enlarge the free space at the end of the sds string so that the caller
 * is sure that after calling this function can overwrite up to addlen
 * bytes after the end of the string, plus one more byte for nul term.
 *
 * Note: this does not change the *length* of the sds string as returned
 * by sdslen(), but only the free buffer space we have. 
 */
sds sdsMakeRoomFor(sds s, size_t addlen) {
    void *sh, *newsh;
    size_t avail = sdsavail(s);
    size_t len, newlen;
    char type, oldtype = s[-1] & SDS_TYPE_MASK;
    int hdrlen;

    /* 可用空间够大，则不扩容了
     * Return ASAP if there is enough space left. 
     */
    if (avail >= addlen) return s;

    len = sdslen(s);
    sh = (char*)s-sdsHdrSize(oldtype);
    newlen = (len+addlen);
    /*这里的翻倍规则和动态数组vector是一样的：便于下次扩容*/
    if (newlen < SDS_MAX_PREALLOC)
        newlen *= 2;
    else
        newlen += SDS_MAX_PREALLOC;

    type = sdsReqType(newlen);

    /* 不适用type 5
     * 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;

    hdrlen = sdsHdrSize(type);
    if (oldtype==type) {
        newsh = s_realloc(sh, hdrlen+newlen+1);
        if (newsh == NULL) return NULL;
        s = (char*)newsh+hdrlen;
    } else {
        /* 头部size变化了
         * Since the header size changes, need to move the string forward,
         * and can't use realloc */
        newsh = s_malloc(hdrlen+newlen+1);
        if (newsh == NULL) return NULL;
        memcpy((char*)newsh+hdrlen, s, len+1);
        s_free(sh);
        s = (char*)newsh+hdrlen;
        s[-1] = type;
        sdssetlen(s, len);
    }
    sdssetalloc(s, newlen);
    return s;
}

  压缩空间的函数sdsRemoveFreeSpace()，功能和扩展空间相反。

/* 用于节省空间，和扩容相反
 * Reallocate the sds string so that it has no free space at the end. The
 * contained string remains not altered, but next concatenation operations
 * will require a reallocation.
 *
 * After the call, the passed sds string is no longer valid and all the
 * references must be substituted with the new pointer returned by the call. */
sds sdsRemoveFreeSpace(sds s) {
    void *sh, *newsh;
    char type, oldtype = s[-1] & SDS_TYPE_MASK;
    int hdrlen, oldhdrlen = sdsHdrSize(oldtype);
    size_t len = sdslen(s);
    sh = (char*)s-oldhdrlen;

    /* Check what would be the minimum SDS header that is just good enough to
     * fit this string. */
    type = sdsReqType(len);
    hdrlen = sdsHdrSize(type);

    /* If the type is the same, or at least a large enough type is still
     * required, we just realloc(), letting the allocator to do the copy
     * only if really needed. Otherwise if the change is huge, we manually
     * reallocate the string to use the different header type. */
    if (oldtype==type || type > SDS_TYPE_8) {
        newsh = s_realloc(sh, oldhdrlen+len+1);
        if (newsh == NULL) return NULL;
        s = (char*)newsh+oldhdrlen;
    } else {
        newsh = s_malloc(hdrlen+len+1);
        if (newsh == NULL) return NULL;
        memcpy((char*)newsh+hdrlen, s, len+1);
        s_free(sh);
        s = (char*)newsh+hdrlen;
        s[-1] = type;
        sdssetlen(s, len);
    }
    sdssetalloc(s, len);
    return s;
}

  sdsAllocSize()函数返回sds的总大小

/* 返回sds对应的总大小
 * Return the total size of the allocation of the specifed sds string,
 * including:
 * 1) The sds header before the pointer.
 * 2) The string.
 * 3) The free buffer at the end if any.
 * 4) The implicit null term.
 */
size_t sdsAllocSize(sds s) {
    size_t alloc = sdsalloc(s);
    return sdsHdrSize(s[-1])+alloc+1;
}

  sdsAllocPtr()函数返回sds位置的指针

/* Return the pointer of the actual SDS allocation (normally SDS strings
 * are referenced by the start of the string buffer). */
void *sdsAllocPtr(sds s) {
    return (void*) (s-sdsHdrSize(s[-1]));
}

  sdsIncrLen()函数：增加sds的长度，减少剩余空间的大小

/* 增加sds长度，并减少剩余空间大小
 * Increment the sds length and decrements the left free space at the
 * end of the string according to 'incr'. Also set the null term
 * in the new end of the string.
 *
 * This function is used in order to fix the string length after the
 * user calls sdsMakeRoomFor(), writes something after the end of
 * the current string, and finally needs to set the new length.
 *
 * Note: it is possible to use a negative increment in order to
 * right-trim the string.
 *
 * Usage example:
 *
 * Using sdsIncrLen() and sdsMakeRoomFor() it is possible to mount the
 * following schema, to cat bytes coming from the kernel to the end of an
 * sds string without copying into an intermediate buffer:
 *
 * oldlen = sdslen(s);
 * s = sdsMakeRoomFor(s, BUFFER_SIZE);
 * nread = read(fd, s+oldlen, BUFFER_SIZE);
 * ... check for nread <= 0 and handle it ...
 * sdsIncrLen(s, nread);
 */
void sdsIncrLen(sds s, ssize_t incr) {
    unsigned char flags = s[-1];
    size_t len;
    switch(flags&SDS_TYPE_MASK) {
        case SDS_TYPE_5: {
            unsigned char *fp = ((unsigned char*)s)-1;
            unsigned char oldlen = SDS_TYPE_5_LEN(flags);
            assert((incr > 0 && oldlen+incr < 32) || (incr < 0 && oldlen >= (unsigned int)(-incr)));
            *fp = SDS_TYPE_5 | ((oldlen+incr) << SDS_TYPE_BITS);
            len = oldlen+incr;
            break;
        }
        case SDS_TYPE_8: {
            SDS_HDR_VAR(8,s);
            assert((incr >= 0 && sh->alloc-sh->len >= incr) || (incr < 0 && sh->len >= (unsigned int)(-incr)));
            len = (sh->len += incr);
            break;
        }
        case SDS_TYPE_16: {
            SDS_HDR_VAR(16,s);
            assert((incr >= 0 && sh->alloc-sh->len >= incr) || (incr < 0 && sh->len >= (unsigned int)(-incr)));
            len = (sh->len += incr);
            break;
        }
        case SDS_TYPE_32: {
            SDS_HDR_VAR(32,s);
            assert((incr >= 0 && sh->alloc-sh->len >= (unsigned int)incr) || (incr < 0 && sh->len >= (unsigned int)(-incr)));
            len = (sh->len += incr);
            break;
        }
        case SDS_TYPE_64: {
            SDS_HDR_VAR(64,s);
            assert((incr >= 0 && sh->alloc-sh->len >= (uint64_t)incr) || (incr < 0 && sh->len >= (uint64_t)(-incr)));
            len = (sh->len += incr);
            break;
        }
        default: len = 0; /* Just to avoid compilation warnings. */
    }
    s[len] = '\0';
}

  sdsgrowzero()函数将sds增长len，正常的部分填充0.

/* 将sds增长至某值，增长部分填充0
 * Grow the sds to have the specified length. Bytes that were not part of
 * the original length of the sds will be set to zero.
 *
 * if the specified length is smaller than the current length, no operation
 * is performed. */
sds sdsgrowzero(sds s, size_t len) {
    size_t curlen = sdslen(s);

    if (len <= curlen) return s;
    s = sdsMakeRoomFor(s,len-curlen);
    if (s == NULL) return NULL;

    /* Make sure added region doesn't contain garbage */
    memset(s+curlen,0,(len-curlen+1)); /* also set trailing \0 byte */
    sdssetlen(s, len);
    return s;
}

  sdscatlen()函数将字符串t增加在sds之后。

/* Append the specified binary-safe string pointed by 't' of 'len' bytes to the
 * end of the specified sds string 's'.
 *
 * After the call, the passed sds string is no longer valid and all the
 * references must be substituted with the new pointer returned by the call. */
sds sdscatlen(sds s, const void *t, size_t len) {
    size_t curlen = sdslen(s);

    s = sdsMakeRoomFor(s,len);
    if (s == NULL) return NULL;
    memcpy(s+curlen, t, len);
    sdssetlen(s, curlen+len);
    s[curlen+len] = '\0';
    return s;
}

  sdscat()函数和上面函数的区别在于不输入长度len，而使用strlen获取长度

/* 在sds之后增加一个字符串t
 * Append the specified null termianted C string to the sds string 's'.
 *
 * After the call, the passed sds string is no longer valid and all the
 * references must be substituted with the new pointer returned by the call. */
sds sdscat(sds s, const char *t) {
    return sdscatlen(s, t, strlen(t));
}

  sdscatsds()函数在已有的sds之后加上另一个sds

/* 在已有的sds之后添加另一个sds
 * Append the specified sds 't' to the existing sds 's'.
 *
 * After the call, the modified sds string is no longer valid and all the
 * references must be substituted with the new pointer returned by the call. */
sds sdscatsds(sds s, const sds t) {
    return sdscatlen(s, t, sdslen(t));
}

  sdscpylen()使用t代替已有的s

/* 将已有的s内容用t代替
 * Destructively modify the sds string 's' to hold the specified binary
 * safe string pointed by 't' of length 'len' bytes. */
sds sdscpylen(sds s, const char *t, size_t len) {
    if (sdsalloc(s) < len) {
        s = sdsMakeRoomFor(s,len-sdslen(s));
        if (s == NULL) return NULL;
    }
    memcpy(s, t, len);
    s[len] = '\0';
    sdssetlen(s, len);
    return s;
}

  sdscpy()函数和上面函数的区别在于不需要输入len，使用strlen获取

/* 使用自动获取长度的方式，将s内容用以NULL结尾的字符串t代替
 * Like sdscpylen() but 't' must be a null-termined string so that the length
 * of the string is obtained with strlen(). */
sds sdscpy(sds s, const char *t) {
    return sdscpylen(s, t, strlen(t));
}

  sdsll2str()函数将一个long long整数转换为字符串s

/* 将一个long long整数转换为字符串s
 * Helper for sdscatlonglong() doing the actual number -> string
 * conversion. 's' must point to a string with room for at least
 * SDS_LLSTR_SIZE bytes.
 *
 * The function returns the length of the null-terminated string
 * representation stored at 's'. */
#define SDS_LLSTR_SIZE 21
int sdsll2str(char *s, long long value) {
    char *p, aux;
    unsigned long long v;
    size_t l;

    /* 每次获取最低位，因此存储的是逆序的
     * Generate the string representation, this method produces
     * an reversed string. 
     **/
    v = (value < 0) ? -value : value;
    p = s;
    do {
        *p++ = '0'+(v%10);
        v /= 10;
    } while(v);
    if (value < 0) *p++ = '-';

    /* Compute length and add null term. */
    l = p-s;
    *p = '\0';

    /* Reverse the string. */
    p--;
    while(s < p) {
        aux = *s;
        *s = *p;
        *p = aux;
        s++;
        p--;
    }
    return l;
}

  和上面类似，只是类型为unsigned

/* 和上面类似，只是类型为unsigned
 * Identical sdsll2str(), but for unsigned long long type. 
 */
int sdsull2str(char *s, unsigned long long v) {
    char *p, aux;
    size_t l;

    /* Generate the string representation, this method produces
     * an reversed string. */
    p = s;
    do {
        *p++ = '0'+(v%10);
        v /= 10;
    } while(v);

    /* Compute length and add null term. */
    l = p-s;
    *p = '\0';

    /* Reverse the string. */
    p--;
    while(s < p) {
        aux = *s;
        *s = *p;
        *p = aux;
        s++;
        p--;
    }
    return l;
}

  从long long类型创建一个sds

/* 从long long类型创建一个sds
 * Create an sds string from a long long value. It is much faster than:
 *
 * sdscatprintf(sdsempty(),"%lld\n", value);
 */
sds sdsfromlonglong(long long value) {
    char buf[SDS_LLSTR_SIZE];
    int len = sdsll2str(buf,value);

    return sdsnewlen(buf,len);
}