sds.h
/**
* redis 动态字符串
*/
#ifndef __SDS_H
#define __SDS_H
#define SDS_MAX_PREALLOC (1024*1024)
extern const char *SDS_NOINIT;
#include <sys/types.h>
#include <stdarg.h>
#include <stdint.h>
/**
* sds 类型是 char * 的别名
*/
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. */
// 根据存储的内容选择不同数据结构,以节省内存
// 这里的 '__attribute__ ((__packed__))' 要求编译器取消内存对齐优化,按照实际的占用字节数进行对齐
// string_size < 32
struct __attribute__ ((__packed__)) sdshdr5 {
/**
* 前 5 位保存字符串长度,后 3 位保存类型值
*/
unsigned char flags; /* 3 lsb of type, and 5 msb of string length */
//实际保存字符串数据的地方以及末尾的一个 \0
char buf[];
};
// 32 <= string_size < 256
struct __attribute__ ((__packed__)) sdshdr8 {
/* 记录当前 buf 的长度(不包含 '\0') */
uint8_t len; /* used */
/* 记录当前 buf 总共分配的内存大小(不包含 '\0') */
uint8_t alloc; /* excluding the header and null terminator */
/* 记录当前 buf 的属性,用来标识到底是 sdshdr8 还是 sdshdr16 等 */
unsigned char flags;
// 实际保存字符串数据的地方以及末尾的一个 \0
char buf[];
};
// 256 <= string_size < 65536(64K)
struct __attribute__ ((__packed__)) sdshdr16 {
// 记录当前 buf 的长度(不包含 '\0')
uint16_t len; /* used */
// 记录当前 buf 总共分配的内存大小(不包含 '\0'
uint16_t alloc; /* excluding the header and null terminator */
//记录当前 buf 的属性,用来标识到底是 sdshdr8 还是 sdshdr16 等
unsigned char flags; /* 3 lsb of type, 5 unused bits */
// 实际保存字符串数据的地方以及末尾的一个 \0
char buf[];
};
// 65536(64K) <= string_size < 4GB
struct __attribute__ ((__packed__)) sdshdr32 {
//记录当前 buf 的长度(不包含 '\0')
uint32_t len; /* used */
//记录当前 buf 总共分配的内存大小(不包含 '\0')
uint32_t alloc; /* excluding the header and null terminator */
//记录当前 buf 的属性等
unsigned char flags; /* 3 lsb of type, 5 unused bits */
// 实际保存字符串数据的地方以及末尾的一个 \0
char buf[];
};
// 4G <= string_size
struct __attribute__ ((__packed__)) sdshdr64 {
//记录当前 buf 的长度(不包含 '\0')
uint64_t len; /* used */
//记录当前 buf 总共分配的内存大小(不包含 '\0')
uint64_t alloc; /* excluding the header and null terminator */
//记录当前 buf 的属性等
unsigned char flags; /* 3 lsb of type, 5 unused bits */
// 实际保存字符串数据的地方以及末尾的一个 \0
char buf[];
};
// flags 值的定义
#define SDS_TYPE_5 0
#define SDS_TYPE_8 1
#define SDS_TYPE_16 2
#define SDS_TYPE_32 3
#define SDS_TYPE_64 4
// 掩码,flags & SDS_TYPE_MASK 即可获得具体的 flags 值
#define SDS_TYPE_MASK 7
#define SDS_TYPE_BITS 3
// 这里的 s 是一个 sds
// 可以通过 sds 的头指针进行寻址,拿到整个 struct 的指针
// buf[-1]的值是flags的值 存的值再内存中是连续的 (len alloc flags buf)
#define SDS_HDR_VAR(T,s) struct sdshdr##T *sh = (void*)((s)-(sizeof(struct sdshdr##T)));
#define SDS_HDR(T,s) ((struct sdshdr##T *)((s)-(sizeof(struct sdshdr##T))))
#define SDS_TYPE_5_LEN(f) ((f)>>SDS_TYPE_BITS)
//判断字符串长度 inline内联
static inline size_t sdslen(const sds s) {
// 通过 buf 的 -1 下标获取 flags 的值
unsigned char flags = s[-1];
//SDS_TYPE_MASK = 7 flags&SDS_TYPE_MASK运算获取flags具体的值
switch(flags&SDS_TYPE_MASK) {
case SDS_TYPE_5:
//flags的值 flags >> 3
return SDS_TYPE_5_LEN(flags);
case SDS_TYPE_8:
//SDS_HDR(8,s) == ((struct sdshdr8 *)((s)-(sizeof(struct sdshdrT8)))->len sdshdr8的len方法
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可用内存大小
static inline size_t sdsavail(const sds s) {
//s[-1]的值是flags的值, 要求编译器取消内存对齐优化,按照实际的占用字节数进行对齐,buf的前面是flags
unsigned char flags = s[-1];
//flags&SDS_TYPE_MASK运算获取flags具体的值
switch(flags&SDS_TYPE_MASK) {
case SDS_TYPE_5: {
return 0;
}
//sh->alloc - sh->len; 分配内存大小减去字符串长度
case SDS_TYPE_8: {
SDS_HDR_VAR(8,s);
return sh->alloc - sh->len;
}
case SDS_TYPE_16: {
SDS_HDR_VAR(16,s);
return sh->alloc - sh->len;
}
case SDS_TYPE_32: {
SDS_HDR_VAR(32,s);
return sh->alloc - sh->len;
}
case SDS_TYPE_64: {
SDS_HDR_VAR(64,s);
return sh->alloc - sh->len;
}
}
return 0;
}
//给sds设置新的长度
static inline void sdssetlen(sds s, size_t newlen) {
//获取flags的值
unsigned char flags = s[-1];
switch(flags&SDS_TYPE_MASK) {
case SDS_TYPE_5:
{
unsigned char *fp = ((unsigned char*)s)-1;
/**
* 位或| 二进制中只要有一个为1 就位1 10010 | 01100 = 11110
* 左移 << newlen << 3 = newlen * 2^3 = newlen * 8
*/
//0 | newlen * 8 = newlen * 8
*fp = SDS_TYPE_5 | (newlen << SDS_TYPE_BITS);
}
break;
case SDS_TYPE_8:
SDS_HDR(8,s)->len = newlen;
break;
case SDS_TYPE_16:
SDS_HDR(16,s)->len = newlen;
break;
case SDS_TYPE_32:
SDS_HDR(32,s)->len = newlen;
break;
case SDS_TYPE_64:
SDS_HDR(64,s)->len = newlen;
break;
}
}
/**
* 增加sds字符串长度
* @param s 字符串
* @param inc 新的长度
*/
static inline void sdsinclen(sds s, size_t inc) {
unsigned char flags = s[-1];
switch(flags&SDS_TYPE_MASK) {
case SDS_TYPE_5:
{
unsigned char *fp = ((unsigned char*)s)-1;
unsigned char newlen = SDS_TYPE_5_LEN(flags)+inc;
*fp = SDS_TYPE_5 | (newlen << SDS_TYPE_BITS);
}
break;
case SDS_TYPE_8:
SDS_HDR(8,s)->len += inc;
break;
case SDS_TYPE_16:
SDS_HDR(16,s)->len += inc;
break;
case SDS_TYPE_32:
SDS_HDR(32,s)->len += inc;
break;
case SDS_TYPE_64:
SDS_HDR(64,s)->len += inc;
break;
}
}
/**
* sds 分配的大小 = sds可用大小 + sds长度
* @param s 字符串
* @return
*/
/* sdsalloc() = sdsavail() + sdslen() */
static inline size_t sdsalloc(const sds s) {
unsigned char flags = s[-1];
switch(flags&SDS_TYPE_MASK) {
case SDS_TYPE_5:
//flags >> 3 = flags / 8
return SDS_TYPE_5_LEN(flags);
case SDS_TYPE_8:
return SDS_HDR(8,s)->alloc;
case SDS_TYPE_16:
return SDS_HDR(16,s)->alloc;
case SDS_TYPE_32:
return SDS_HDR(32,s)->alloc;
case SDS_TYPE_64:
return SDS_HDR(64,s)->alloc;
}
return 0;
}
/**
* 设置字符串可用内存为新分配的内存
* @param s 字符串
* @param newlen 新的长度
*/
static inline void sdssetalloc(sds s, size_t newlen) {
unsigned char flags = s[-1];
//选择那种字符串类型
switch(flags&SDS_TYPE_MASK) {
case SDS_TYPE_5:
/* Nothing to do, this type has no total allocation info. */
break;
case SDS_TYPE_8:
//设置字符串buf内存 sds->alloc = newlen
SDS_HDR(8,s)->alloc = newlen;
break;
case SDS_TYPE_16:
SDS_HDR(16,s)->alloc = newlen;
break;
case SDS_TYPE_32:
SDS_HDR(32,s)->alloc = newlen;
break;
case SDS_TYPE_64:
SDS_HDR(64,s)->alloc = newlen;
break;
}
}
//创建一个initlen长度的sds字符串,如果创建不成功会返回异常
sds sdsnewlen(const void *init, size_t initlen);
//尝试创建initlen长度的sds字符串,创建不成功返回NULL
sds sdstrynewlen(const void *init, size_t initlen);
//给字符串init创建一个sdh
sds sdsnew(const char *init);
//创建一个空字符串
sds sdsempty(void);
//复制字符串
sds sdsdup(const sds s);
//释放字符串
void sdsfree(sds s);
//扩展sds字符串长度
sds sdsgrowzero(sds s, size_t len);
//sds连接固定长度len的char字符串
sds sdscatlen(sds s, const void *t, size_t len);
//sds连接char字符串,模仿strcat
sds sdscat(sds s, const char *t);
//sds连接sds字符串,模仿strcat
sds sdscatsds(sds s, const sds t);
//sds拷贝固定长度len的char字符串
sds sdscpylen(sds s, const char *t, size_t len);
//sds拷贝char字符串
sds sdscpy(sds s, const char *t);
//sds连接格式化字符串,采用C实现格式功能
sds sdscatvprintf(sds s, const char *fmt, va_list ap);
#ifdef __GNUC__
sds sdscatprintf(sds s, const char *fmt, ...)
__attribute__((format(printf, 2, 3)));
#else
sds sdscatprintf(sds s, const char *fmt, ...);
#endif
//sds连接格式化字符串,自定义格式化功能
sds sdscatfmt(sds s, char const *fmt, ...);
// 前后去掉字符 cset
sds sdstrim(sds s, const char *cset);
void sdssubstr(sds s, size_t start, size_t len);
//截断字符串
void sdsrange(sds s, ssize_t start, ssize_t end);
//更新字符串长度
void sdsupdatelen(sds s);
//清空sds字符串
void sdsclear(sds s);
//比较两个sds字符串
int sdscmp(const sds s1, const sds s2);
//sds分割函数 对于strsplit
sds *sdssplitlen(const char *s, ssize_t len, const char *sep, int seplen, int *count);
//释放分割出来的sds
void sdsfreesplitres(sds *tokens, int count);
//sds转小写
void sdstolower(sds s);
//sds转大写
void sdstoupper(sds s);
//longlong类型转化为sds字符串
sds sdsfromlonglong(long long value);
//sds添加转义字符字符串
sds sdscatrepr(sds s, const char *p, size_t len);
//sds根据转义字符分割,必须用sdsfreesplitres().
sds *sdssplitargs(const char *line, int *argc);
sds sdsmapchars(sds s, const char *from, const char *to, size_t setlen);
//字符串连接后,转化为sds
sds sdsjoin(char **argv, int argc, char *sep);
//sds 连接sds
sds sdsjoinsds(sds *argv, int argc, const char *sep, size_t seplen);
/* Callback for sdstemplate. The function gets called by sdstemplate
* every time a variable needs to be expanded. The variable name is
* provided as variable, and the callback is expected to return a
* substitution value. Returning a NULL indicates an error.
*/
typedef sds (*sdstemplate_callback_t)(const sds variable, void *arg);
//sds回调模板函数
sds sdstemplate(const char *template, sdstemplate_callback_t cb_func, void *cb_arg);
// sds扩展函数 sds的扩容
/* Low level functions exposed to the user API */
sds sdsMakeRoomFor(sds s, size_t addlen);
//配合sdsMakeRoomFor使用,重置sds长度
void sdsIncrLen(sds s, ssize_t incr);
//sds释放空闲空间
sds sdsRemoveFreeSpace(sds s);
//计算sds开辟空间的大小
size_t sdsAllocSize(sds s);
//返回buf缓冲指针
void *sdsAllocPtr(sds s);
/* Export the allocator used by SDS to the program using SDS.
* Sometimes the program SDS is linked to, may use a different set of
* allocators, but may want to allocate or free things that SDS will
* respectively free or allocate. */
//开辟size大小的空间
void *sds_malloc(size_t size);
//如果size> ptr.length 重新开辟size大小的空间
void *sds_realloc(void *ptr, size_t size);
//释放指针空间
void sds_free(void *ptr);
#ifdef REDIS_TEST
int sdsTest(int argc, char *argv[], int accurate);
#endif
#endif
sds.c
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <assert.h>
#include <limits.h>
#include "sds.h"
#include "sdsalloc.h"
/**
* 常量
*/
const char *SDS_NOINIT = "SDS_NOINIT";
/**
* 获取sds类型结构占用的内存大小
* @param type sds的类型
* @return 内存大小
*/
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;
}
/**
* 通过sds字符串长度获取所需要的sds类型
* @param string_size 字符串长度
* @return 字符串类型
*/
static inline char sdsReqType(size_t string_size) {
//string_size < 2^5 = string_size < 32
if (string_size < 1<<5)
return SDS_TYPE_5;
// 32 <= string_size < 256
if (string_size < 1<<8)
return SDS_TYPE_8;
// 256 <= string_size < 65536(64K)
if (string_size < 1<<16)
return SDS_TYPE_16;
// LONG_MAX == LLONG_MAX = 8 代表64位系统
#if (LONG_MAX == LLONG_MAX)
// 65536(64K) <= string_size < 4GB
if (string_size < 1ll<<32)
return SDS_TYPE_32;
// 4G <= string_size
return SDS_TYPE_64;
#else
//32位系统
return SDS_TYPE_32;
#endif
}
/**
* 获取sds字符串在该类型中的允许的最大长度
* @param type 类型
* @return 长度
*/
static inline size_t sdsTypeMaxSize(char type) {
if (type == SDS_TYPE_5)
return (1<<5) - 1;
if (type == SDS_TYPE_8)
return (1<<8) - 1;
if (type == SDS_TYPE_16)
return (1<<16) - 1;
#if (LONG_MAX == LLONG_MAX)
//预编译命令 代表64位系统
if (type == SDS_TYPE_32)
return (1ll<<32) - 1;
#endif
//-1 相当于最大的 SDS_TYPE_64 或者 SDS_TYPE_32
return -1; /* this is equivalent to the max SDS_TYPE_64 or SDS_TYPE_32 */
}
/* 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.
* If SDS_NOINIT is used, the buffer is left uninitialized;
*
* 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. */
/**
* 用于创建sds字符串
* const void *init 代表任何类型的值
* @param init init指针 init 代表任何类型的值,值为常量,无法修改其值,但是可以其使指针指向其他对象
* @param initlen 字符串长度
* @param trymalloc 分配的buf大小
* @return sds字符串
*/
sds _sdsnewlen(const void *init, size_t initlen, int trymalloc) {
void *sh;
sds s;
//通过sds字符串长度获取sds类型
char type = sdsReqType(initlen);
/* Empty strings are usually created in order to append. Use type 8
* since type 5 is not good at this. */
// 如果类型SDS_TYPE_5 并且长度位0 则类型设置为 SDS_TYPE_8 ,空的字符串通常使用类型SDS_TYPE_8,以便于追加字符,
if (type == SDS_TYPE_5 && initlen == 0) type = SDS_TYPE_8;
//sds 的类型占用的内存的大小
int hdrlen = sdsHdrSize(type);
//定义flags标识 标识sds的buf属性
unsigned char *fp; /* flags pointer. */
size_t usable;
//断言 字符串长度 + 类型占用的长度 + 1 > 字符串长度
assert(initlen + hdrlen + 1 > initlen); /* Catch size_t overflow */
// 分配内存的大小 sh如果为NULL则分配失败 否则usable为分配的可用内存大小
sh = trymalloc?
s_trymalloc_usable(hdrlen+initlen+1, &usable) :
s_malloc_usable(hdrlen+initlen+1, &usable);
//如果分配内存失败则返回 NULL
if (sh == NULL) return NULL;
// 如果init==SDS_NOINIT(这里判断地址是否相同),设置init为NULL
if (init==SDS_NOINIT)
init = NULL;
else if (!init)
// 清空内存内容
memset(sh, 0, hdrlen+initlen+1);
// c字符串
s = (char*)sh+hdrlen;
// 标志位(sdshdr_xx中flags)
fp = ((unsigned char*)s)-1;
//字符串可用内存大小 = 分配的内存大小-sds结构大小-1
usable = usable-hdrlen-1;
//判断可用内存大小 是否大于该类型最大可用大小
if (usable > sdsTypeMaxSize(type))
//是的话分配该类型最大可用内存大小
usable = sdsTypeMaxSize(type);
// 根据得到的sds类型设置头部信息
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 = usable;
*fp = type;
break;
}
case SDS_TYPE_16: {
SDS_HDR_VAR(16,s);
sh->len = initlen;
sh->alloc = usable;
*fp = type;
break;
}
case SDS_TYPE_32: {
SDS_HDR_VAR(32,s);
sh->len = initlen;
sh->alloc = usable;
*fp = type;
break;
}
case SDS_TYPE_64: {
SDS_HDR_VAR(64,s);
sh->len = initlen;
sh->alloc = usable;
*fp = type;
break;
}
}
// 拷贝字符串到sds字符串中
if (initlen && init)
memcpy(s, init, initlen);
// 设置标准结束符
s[initlen] = '\0';
return s;
}
/**
* 创建sds字符串 使用s_malloc_usable创建内存空间
* @param init 任意类型的值 常量 值不可更改 但指针可以更改指向的对象
* @param initlen
* @return 字符串
*/
sds sdsnewlen(const void *init, size_t initlen) {
return _sdsnewlen(init, initlen, 0);
}
/**
* 尝试创建sds,使用s_trymalloc_usable创建内存空间
* @param init 任意类型的值
* @param initlen
* @return
*/
sds sdstrynewlen(const void *init, size_t initlen) {
return _sdsnewlen(init, initlen, 1);
}
/**
* 创建0长度的字符串
* @return sds字符串
*/
/* 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);
}
/**
* 从一个以null结尾的 C字符串 创建一个新的sds字符串
* @param init
* @return
*/
/* Create a new sds string starting from a null terminated C string. */
sds sdsnew(const char *init) {
// 判断传入的字符串是否为NULL 如果为NULL为创建一个空的sds字符串,否则创建strlen(init)长度的sds字符串
size_t initlen = (init == NULL) ? 0 : strlen(init);
return sdsnewlen(init, initlen);
}
/**
* 复制一个sds
* @param s
* @return
*/
/* Duplicate an sds string. */
sds sdsdup(const sds s) {
return sdsnewlen(s, sdslen(s));
}
/**
* 释放sds字符串
* @param s sds字符串
*/
/* Free an sds string. No operation is performed if 's' is NULL. */
void sdsfree(sds s) {
//如果sds字符串为NULL为不作操作
if (s == NULL) return;
//释放内存空间
s_free((char*)s-sdsHdrSize(s[-1]));
}
/* 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. */
/**
* 将sds的已经使用的长度修改成第一个'\0'结尾的字符串的长度,相当于从第一个\0截断
*
* 当修改给sds字符串中某一个字符为'\0' ,
* 此时需要执行该方法去更新sds字符串长度,因为sds长度记录在sds头len中,如果不去更新,则sds长度不变,
* 例子:
* s = sdsnew("foobar");
* s[2] = '\0';
* dsupdatelen(s);
* rintf("%d\n", sdslen(s));
* 此时输出长度为2
* 如果没有dsupdatelen(s); 则sds长度还是原来的6
* @param s
*/
void sdsupdatelen(sds s) {
//获取sds长度即 到第一个'\0'的长度
size_t reallen = strlen(s);
// 给sds设置新的长度
sdssetlen(s, reallen);
}
/* 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. */
/**
* 将sds的内存清零但不释放
* 设置sds长度为0,并将第一个字符位置设置为结束符 '\0'
* @param s
*/
void sdsclear(sds s) {
sdssetlen(s, 0);
s[0] = '\0';
}
/* 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. */
/**
* 给一个sds扩充空间以供以后使用
* 该方法用于添加sds字符串sds的alloc的小 即可用空间大小,不会改变字符串长度
* @param s sds字符串
* @param addlen 需要新增的大小
* @return sds字符串
*/
sds sdsMakeRoomFor(sds s, size_t addlen) {
void *sh, *newsh;
//获取sds当前可用空间
size_t avail = sdsavail(s);
size_t len, newlen, reqlen;
//获取sds的类型 s[-1]= flags oldtype = flags & SDS_TYPE_MASK;
char type, oldtype = s[-1] & SDS_TYPE_MASK;
int hdrlen;
size_t usable;
//如果可用空间大于扩容大小 则无须扩容直接返回
/* Return ASAP if there is enough space left. */
if (avail >= addlen) return s;
//判断字符串长度
len = sdslen(s);
//获取sds类型结构占用的内存大小
sh = (char*)s-sdsHdrSize(oldtype);
//新的内存大小等于 sds字符串长度+新增长度
reqlen = newlen = (len+addlen);
//断言 新增后的长度要大于 sds字符串长度
assert(newlen > len); /* Catch size_t overflow */
//如果新的长度小于 1M,则扩容为其2倍
if (newlen < SDS_MAX_PREALLOC)
newlen *= 2;
//否则+1M
else
newlen += SDS_MAX_PREALLOC;
//修改要扩容sds字符串的类型
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. */
//如果类型是SDS_TYPE_5 的话将类型设置为 SDS_TYPE_8
if (type == SDS_TYPE_5) type = SDS_TYPE_8;
//获取新的类型的结构占用的空间大小
hdrlen = sdsHdrSize(type);
//断言 新的类型结构占用的空间 + 扩容后的长度+1 要大于 扩容前sds字符串长度+addlen新增长度
assert(hdrlen + newlen + 1 > reqlen); /* Catch size_t overflow */
if (oldtype==type) {
//如果旧的类型和新的类型一致,则重新分配内存
newsh = s_realloc_usable(sh, hdrlen+newlen+1, &usable);
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 */
//如果新类型和旧内存不一致则重新创建一个新的内存空间
//分配内存 如果为NULL则内存分配失败 否则usable为可用内存大小
newsh = s_malloc_usable(hdrlen+newlen+1, &usable);
if (newsh == NULL) return NULL;
//复制字符串
memcpy((char*)newsh+hdrlen, s, len+1);
//释放之前的sds字符串
s_free(sh);
s = (char*)newsh+hdrlen;
//设置新标识
s[-1] = type;
//给sds设置新的长度
sdssetlen(s, len);
}
//可用内存 = 分配的可用内存-sds类型结构内存-1
usable = usable-hdrlen-1;
//如果可用内存 > 类型最大的内存则重新设置sds类型
if (usable > sdsTypeMaxSize(type))
usable = sdsTypeMaxSize(type);
//设置字符串可用内存为新分配的内存
sdssetalloc(s, usable);
return s;
}
/* 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. */
/**
* 根据实际使用长度减少sds的分配内存 设置sds可用空间为0
* 重新分配sds字符串内存空间,传入的s字符串将不可以,指针将指向新创建的sds字符串
* @param s sds字符串
* @return
*/
sds sdsRemoveFreeSpace(sds s) {
void *sh, *newsh;
//s[-1] = flags sds类型
char type, oldtype = s[-1] & SDS_TYPE_MASK;
int hdrlen, oldhdrlen = sdsHdrSize(oldtype);
//获取sds字符串长度
size_t len = sdslen(s);
//获取s的可用内存
size_t avail = sdsavail(s);
//sda的buf长度 = sds长度 - sds类型结构占用的内存空间大小
sh = (char*)s-oldhdrlen;
//如果可用空间已经为0,那么无须调整
/* Return ASAP if there is no space left. */
if (avail == 0) return s;
/* Check what would be the minimum SDS header that is just good enough to
* fit this string. */
//获取该长度所需要的的sds类型
type = sdsReqType(len);
//获取sds类型结构占用的内存大小
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) {
//如果旧sds类型和 sds字符串最少需要的sds类型一致,重新分配内存并将之前sds内存释放
newsh = s_realloc(sh, oldhdrlen+len+1);
//如果分配失败则返回NULL
if (newsh == NULL) return NULL;
//c 字符串
s = (char*)newsh+oldhdrlen;
} else {
//sds字符串最少需要空间的sds类型 和 原sds类型不一致 分配内存
newsh = s_malloc(hdrlen+len+1);
//如果为NULL则分配失败
if (newsh == NULL) return NULL;
//复制
memcpy((char*)newsh+hdrlen, s, len+1);
//释放原sds串内存
s_free(sh);
// c串
s = (char*)newsh+hdrlen;
//设置新的类型
s[-1] = type;
//设置新的sds长度
sdssetlen(s, len);
}
//设置sds可用内存为0的内存
sdssetalloc(s, len);
return s;
}
/* Return the total size of the allocation of the specified 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.
*/
// 返回一个sds的总长度,包括头,二进制字符串分配的内存长度和'\0'
size_t sdsAllocSize(sds s) {
//sds分配的内存大小
size_t alloc = sdsalloc(s);
// sds类型结构占用的内存大小 + 可用内存空间 + 1
return sdsHdrSize(s[-1])+alloc+1;
}
/* Return the pointer of the actual SDS allocation (normally SDS strings
* are referenced by the start of the string buffer). */
/**
* 返回一个sds的控制结构的起始地址
* @param s sds字符串
* @return 返回buf缓冲指针
*/
void *sdsAllocPtr(sds s) {
return (void*) (s-sdsHdrSize(s[-1]));
}
/* 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);
*/
/**
* 增加一个sds的已经使用的长度,要求加完之后不能超过分配的内存长度
* @param s
* @param incr
*/
void sdsIncrLen(sds s, ssize_t incr) {
unsigned char flags = s[-1];
size_t len;
//判断类型
switch(flags&SDS_TYPE_MASK) {
case SDS_TYPE_5: {
//标志位flags
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';
}
/* 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. */
/**
* 给一个sds的已经使用长度增加到指定长度,并将增加部分内存清零
* @param s
* @param len
* @return
*/
sds sdsgrowzero(sds s, size_t len) {
//获取sds字符串长度
size_t curlen = sdslen(s);
//指定的长度如果下雨当前sds字符串长度 则不做处理
if (len <= curlen) return s;
//sds扩容
s = sdsMakeRoomFor(s,len-curlen);
//如果为NULL 则内存分配失败
if (s == NULL) return NULL;
// s+curlen ~ len-curlen+1 区间为0
/* Make sure added region doesn't contain garbage */
memset(s+curlen,0,(len-curlen+1)); /* also set trailing \0 byte */
//设置sds长度
sdssetlen(s, len);
return s;
}
/* 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. */
/**
* 在一个sds后面连接给定长度的二进制字符串
* @param s sds字符串
* @param t 任意类型的值
* @param len 长度
* @return sds字符串
*/
sds sdscatlen(sds s, const void *t, size_t len) {
//获取sds字符串长度
size_t curlen = sdslen(s);
//sds扩容
s = sdsMakeRoomFor(s,len);
if (s == NULL) return NULL;
//复制字符串
memcpy(s+curlen, t, len);
//重新设置字符串
sdssetlen(s, curlen+len);
//sds末尾置'\0'
s[curlen+len] = '\0';
return s;
}
/* Append the specified null terminated 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. */
/**
* 在一个sds后面连接一个C字符串
* @param s
* @param t
* @return
*/
sds sdscat(sds s, const char *t) {
return sdscatlen(s, t, strlen(t));
}
/* 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. */
/**
* 将一个sds的已经使用的内存连接到另一个sds中
* @param s
* @param t
* @return
*/
sds sdscatsds(sds s, const sds t) {
return sdscatlen(s, t, sdslen(t));
}
/* Destructively modify the sds string 's' to hold the specified binary
* safe string pointed by 't' of length 'len' bytes. */
/**
* 将一个给定长度的二进制字符串复制到sds,并更新已经使用的长度
* @param s
* @param t
* @param len
* @return
*/
sds sdscpylen(sds s, const char *t, size_t len) {
//如果长度len大于sds分配的内存大小
if (sdsalloc(s) < len) {
//sds扩容
s = sdsMakeRoomFor(s,len-sdslen(s));
if (s == NULL) return NULL;
}
//复制字符串
memcpy(s, t, len);
s[len] = '\0';
//设置长度
sdssetlen(s, len);
return s;
}
/* Like sdscpylen() but 't' must be a null-termined string so that the length
* of the string is obtained with strlen(). */
/**
* 将一个C字符串复制到sds
* @param s
* @param t
* @return
*/
sds sdscpy(sds s, const char *t) {
return sdscpylen(s, t, strlen(t));
}
/* 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
/**
* 将一个long long转换成C字符串格式
* @param s
* @param value
* @return
*/
int sdsll2str(char *s, long long value) {
char *p, aux;
unsigned long long v;
size_t l;
/* Generate the string representation, this method produces
* a 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;
}
/**
* 将一个unsigned long long 转换成C字符串格式
* @param s
* @param v
* @return
*/
/* 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
* a 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;
}
/* Create an sds string from a long long value. It is much faster than:
*
* sdscatprintf(sdsempty(),"%lld\n", value);
*/
/**
* 使用long long制造一个sds
* @param value
* @return
*/
sds sdsfromlonglong(long long value) {
char buf[SDS_LLSTR_SIZE];
//转换成C串
int len = sdsll2str(buf,value);
//创建sds字符串 使用s_malloc_usable创建内存空
return sdsnewlen(buf,len);
}
/**
* 将可变长格式化字符串连接到sds后面
* @param s
* @param fmt
* @param ap
* @return
*/
/* Like sdscatprintf() but gets va_list instead of being variadic. */
sds sdscatvprintf(sds s, const char *fmt, va_list ap) {
va_list cpy;
char staticbuf[1024], *buf = staticbuf, *t;
//获取fmt字符串长度 * 2
size_t buflen = strlen(fmt)*2;
int bufstrlen;
/* We try to start using a static buffer for speed.
* If not possible we revert to heap allocation. */
if (buflen > sizeof(staticbuf)) {
// 如果格式化字符串长度*2 大于 缓冲区长度,则分配内存
buf = s_malloc(buflen);
if (buf == NULL) return NULL;
} else {
//如果格式化字符串长度*2 小于等于缓冲区大小 则设置为缓冲区大小
buflen = sizeof(staticbuf);
}
/* Alloc enough space for buffer and \0 after failing to
* fit the string in the current buffer size. */
while(1) {
//将ap复制到cpy
va_copy(cpy,ap);
//将可变参数格式化输出到一个字符数组。
bufstrlen = vsnprintf(buf, buflen, fmt, cpy);
//将cpy置为NULL
va_end(cpy);
if (bufstrlen < 0) {
//如果bufstrlen小于0 且 buf 不等于 staticbuf释放buf 并返回NULL
if (buf != staticbuf) s_free(buf);
return NULL;
}
if (((size_t)bufstrlen) >= buflen) {
if (buf != staticbuf) s_free(buf);
buflen = ((size_t)bufstrlen) + 1;
buf = s_malloc(buflen);
if (buf == NULL) return NULL;
continue;
}
break;
}
/* Finally concat the obtained string to the SDS string and return it. */
//将字符串拼接到sds后面
t = sdscatlen(s, buf, bufstrlen);
if (buf != staticbuf) s_free(buf); //释放buf缓冲区内存
return t;
}
/* Append to the sds string 's' a string obtained using printf-alike format
* specifier.
*
* 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.
*
* Example:
*
* s = sdsnew("Sum is: ");
* s = sdscatprintf(s,"%d+%d = %d",a,b,a+b).
*
* Often you need to create a string from scratch with the printf-alike
* format. When this is the need, just use sdsempty() as the target string:
*
* s = sdscatprintf(sdsempty(), "... your format ...", args);
*/
/**
* 是sdscatvprintf的包装, 将可变长格式化字符串连接到sds后面
* @param s
* @param fmt
* @param ...
* @return
*/
sds sdscatprintf(sds s, const char *fmt, ...) {
va_list ap;
char *t;
va_start(ap, fmt);
t = sdscatvprintf(s,fmt,ap);
va_end(ap);
return t;
}
/* This function is similar to sdscatprintf, but much faster as it does
* not rely on sprintf() family functions implemented by the libc that
* are often very slow. Moreover directly handling the sds string as
* new data is concatenated provides a performance improvement.
*
* However this function only handles an incompatible subset of printf-alike
* format specifiers:
*
* %s - C String
* %S - SDS string
* %i - signed int
* %I - 64 bit signed integer (long long, int64_t)
* %u - unsigned int
* %U - 64 bit unsigned integer (unsigned long long, uint64_t)
* %% - Verbatim "%" character.
*/
/**
* 和sdscatvprintf功能一样,区别是不使用sprintf族函数,性能高
* @param s
* @param fmt
* @param ...
* @return
*/
sds sdscatfmt(sds s, char const *fmt, ...) {
//initlen= s长度
size_t initlen = sdslen(s);
const char *f = fmt;
long i;
va_list ap;
/* To avoid continuous reallocations, let's start with a buffer that
* can hold at least two times the format string itself. It's not the
* best heuristic but seems to work in practice. */
//sds扩容
s = sdsMakeRoomFor(s, strlen(fmt)*2);
//宏 ap储存fmt参数
va_start(ap,fmt);
f = fmt; /* Next format specifier byte to process. */
i = initlen; /* Position of the next byte to write to dest str. */
while(*f) {
char next, *str;
size_t l;
long long num;
unsigned long long unum;
/* Make sure there is always space for at least 1 char. */
if (sdsavail(s)==0) {
//如果可用空间为0,则扩容,内存大小+1
s = sdsMakeRoomFor(s,1);
}
switch(*f) {
case '%':
next = *(f+1);
f++;
switch(next) {
case 's':
case 'S':
str = va_arg(ap,char*);
//next如果是s则使用strlen获取长度,否则使用sds的sdslen根据sds的len值去获取长度
l = (next == 's') ? strlen(str) : sdslen(str);
if (sdsavail(s) < l) {
//如果可以长度小于l长度则扩容
s = sdsMakeRoomFor(s,l);
}
//复制
memcpy(s+i,str,l);
//增加sds字符串长度
sdsinclen(s,l);
i += l;
break;
case 'i':
case 'I':
if (next == 'i')
num = va_arg(ap,int);
else
num = va_arg(ap,long long);
{
//SDS_LLSTR_SIZE = 21 char buf[21]
char buf[SDS_LLSTR_SIZE];
//将long long转成C串
l = sdsll2str(buf,num);
if (sdsavail(s) < l) {
//可用空间小于l则扩容
s = sdsMakeRoomFor(s,l);
}
//复制
memcpy(s+i,buf,l);
//增加sds字符串长度
sdsinclen(s,l);
i += l;
}
break;
case 'u':
case 'U':
if (next == 'u')
unum = va_arg(ap,unsigned int);
else
unum = va_arg(ap,unsigned long long);
{
char buf[SDS_LLSTR_SIZE];
//将一个unsigned long long 转换成C字符串格式
l = sdsull2str(buf,unum);
if (sdsavail(s) < l) {
//扩容
s = sdsMakeRoomFor(s,l);
}
memcpy(s+i,buf,l);
sdsinclen(s,l);
i += l;
}
break;
default: /* Handle %% and generally %<unknown>. */
//处理%%的情况
s[i++] = next;
//增加sds字符串长
sdsinclen(s,1);
break;
}
break;
default:
s[i++] = *f;
sdsinclen(s,1);
break;
}
f++;
}
//设置ap 为NULL
va_end(ap);
//sds串末尾置为'\0'
/* Add null-term */
s[i] = '\0';
return s;
}
/* Remove the part of the string from left and from right composed just of
* contiguous characters found in 'cset', that is a null terminted C string.
*
* 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.
*
* Example:
*
* s = sdsnew("AA...AA.a.aa.aHelloWorld :::");
* s = sdstrim(s,"Aa. :");
* printf("%s\n", s);
*
* Output will be just "HelloWorld".
*/
/**
* 从sds的头和尾去掉所有和给定字符一致的内容,保留剩下的部分
* @param s
* @param cset
* @return sds
*/
sds sdstrim(sds s, const char *cset) {
char *start, *end, *sp, *ep;
size_t len;
//sp 指向头 ep指向尾
sp = start = s;
ep = end = s+sdslen(s)-1;
// 用于去掉sp头部有参数cset的部分
while(sp <= end && strchr(cset, *sp)) sp++;
while(ep > sp && strchr(cset, *ep)) ep--;
//新的长度
len = (sp > ep) ? 0 : ((ep-sp)+1);
//sds拷贝 sp到s
if (s != sp) memmove(s, sp, len);
s[len] = '\0';
//设置sds
sdssetlen(s,len);
return s;
}
/* Changes the input string to be a subset of the original.
* It does not release the free space in the string, so a call to
* sdsRemoveFreeSpace may be wise after. */
/**
*
* @param s
* @param start
* @param len
*/
void sdssubstr(sds s, size_t start, size_t len) {
/* Clamp out of range input */
//获取sds长度
size_t oldlen = sdslen(s);
//如果起始点大于sds长度 则设置start = len = 0
if (start >= oldlen) start = len = 0;
//长度如果大于 sds长度-起始点 重新设置长度为 sds长度-起始点
if (len > oldlen-start) len = oldlen-start;
//将 s 的 N 个字节复制到 DEST,保证重叠字符串的正确行为。
/* Move the data */
if (len) memmove(s, s+start, len);
s[len] = 0;
//给sds设置新的长度
sdssetlen(s,len);
}
/* Turn the string into a smaller (or equal) string containing only the
* substring specified by the 'start' and 'end' indexes.
*
* start and end can be negative, where -1 means the last character of the
* string, -2 the penultimate character, and so forth.
*
* The interval is inclusive, so the start and end characters will be part
* of the resulting string.
*
* The string is modified in-place.
*
* NOTE: this function can be misleading and can have unexpected behaviour,
* specifically when you want the length of the new string to be 0.
* Having start==end will result in a string with one character.
* please consider using sdssubstr instead.
*
* Example:
*
* s = sdsnew("Hello World");
* sdsrange(s,1,-1); => "ello World"
*/
/**
* 将sds切片,提供起始和终止位置,可以是负数表示从结尾开始
* @param s sds字符串
* @param start 开始
* @param end 结束
*/
void sdsrange(sds s, ssize_t start, ssize_t end) {
size_t newlen, len = sdslen(s);
if (len == 0) return;
if (start < 0)
start = len + start;
if (end < 0)
end = len + end;
newlen = (start > end) ? 0 : (end-start)+1;
sdssubstr(s, start, newlen);
}
/**
* 将sds的所有字母变成小写,内部是tolower
* @param s sds
*/
/* Apply tolower() to every character of the sds string 's'. */
void sdstolower(sds s) {
size_t len = sdslen(s), j;
for (j = 0; j < len; j++) s[j] = tolower(s[j]);
}
/**
* 将sds的所有字母变成大写,内部是toupper
* @param s sds
*/
/* Apply toupper() to every character of the sds string 's'. */
void sdstoupper(sds s) {
size_t len = sdslen(s), j;
for (j = 0; j < len; j++) s[j] = toupper(s[j]);
}
/* Compare two sds strings s1 and s2 with memcmp().
*
* Return value:
*
* positive if s1 > s2.
* negative if s1 < s2.
* 0 if s1 and s2 are exactly the same binary string.
*
* If two strings share exactly the same prefix, but one of the two has
* additional characters, the longer string is considered to be greater than
* the smaller one. */
/**
* 比较两个sds,内部是memcmp
* @param s1 sds1
* @param s2 sds2
* @return
*/
int sdscmp(const sds s1, const sds s2) {
size_t l1, l2, minlen;
int cmp;
//获取sds字符串长度
l1 = sdslen(s1);
l2 = sdslen(s2);
minlen = (l1 < l2) ? l1 : l2;
/**
* memcmp
* s1 < s2 cmp <0
* s1==s2 cmp =0
* s1>s2 cmp > 0
*/
cmp = memcmp(s1,s2,minlen);
//如果cmp = 0的话 就比较长度
if (cmp == 0) return l1>l2? 1: (l1<l2? -1: 0);
return cmp;
}
/* Split 's' with separator in 'sep'. An array
* of sds strings is returned. *count will be set
* by reference to the number of tokens returned.
*
* On out of memory, zero length string, zero length
* separator, NULL is returned.
*
* Note that 'sep' is able to split a string using
* a multi-character separator. For example
* sdssplit("foo_-_bar","_-_"); will return two
* elements "foo" and "bar".
*
* This version of the function is binary-safe but
* requires length arguments. sdssplit() is just the
* same function but for zero-terminated strings.
*/
/**
*
* 将字符串用指定的分割器分割成若干部分,存入sds指针数组,并返回这个指针数组,是简单的字符串匹配,可以使用KMP优化
* 输入长度为@len的字符串@s,以及长度为@seplen的字符串@sep。使用@sep对@s进行切分。
* 切分好的字符串通过返回值@tokens传出,切分得到的个数通过参数@count传出。
*
* @param s s字符串
* @param len 长度
* @param sep 分隔字符串
* @param seplen 分隔字符串的长度
* @param count 分隔后的数组个数
* @return 返回@tokens
*/
sds *sdssplitlen(const char *s, ssize_t len, const char *sep, int seplen, int *count) {
int elements = 0, slots = 5;
long start = 0, j;
sds *tokens;
//如果分隔字符串长度小于0 或者要被分割的字符串长度小于0 那么直接返回NULL
if (seplen < 1 || len < 0) return NULL;
//分配内存空间
tokens = s_malloc(sizeof(sds)*slots);
//如果tokens为NULL 分配内存失败
if (tokens == NULL) return NULL;
if (len == 0) {
*count = 0;
return tokens;
}
for (j = 0; j < (len-(seplen-1)); j++) {
/* make sure there is room for the next element and the final one */
//确保预留空间
if (slots < elements+2) {
sds *newtokens;
slots *= 2;
//分配内存
newtokens = s_realloc(tokens,sizeof(sds)*slots);
if (newtokens == NULL) goto cleanup;
tokens = newtokens;
}
/* search the separator */
/*
* 两种情况:
* 1、sep只有一个字符,一个字符一个字符比较,如果相等则进行分割
* 2、sep是字符串有多个字符,直接用memcmp进行比较,等于0代表相等,每次比较的长度为seplen
*/
if ((seplen == 1 && *(s+j) == sep[0]) || (memcmp(s+j,sep,seplen) == 0)) {
//分割字符串
tokens[elements] = sdsnewlen(s+start,j-start);
//判断是否分配内存失败,如果失败则goto到cleanup去释放tokens空间
if (tokens[elements] == NULL) goto cleanup;
elements++;
start = j+seplen;
//跳过分割符
j = j+seplen-1; /* skip the separator */
}
}
/* Add the final element. We are sure there is room in the tokens array. */
//最后添加一个元素,确保tokens长度不为0
tokens[elements] = sdsnewlen(s+start,len-start);
//判断内存分配是否成功
if (tokens[elements] == NULL) goto cleanup;
elements++;
*count = elements;
return tokens;
cleanup:
{
//释放tokens数组中的元素
int i;
for (i = 0; i < elements; i++) sdsfree(tokens[i]);
s_free(tokens);
*count = 0;
return NULL;
}
}
/**
* 释放sdssplitlen产生的指针数组和其中的sds的内存
* @param tokens 分割后得到的数组
* @param count 数组中元素个数
*/
/* Free the result returned by sdssplitlen(), or do nothing if 'tokens' is NULL. */
void sdsfreesplitres(sds *tokens, int count) {
if (!tokens) return;
while(count--)
sdsfree(tokens[count]);
s_free(tokens);
}
/* Append to the sds string "s" an escaped string representation where
* all the non-printable characters (tested with isprint()) are turned into
* escapes in the form "\n\r\a...." or "\x<hex-number>".
*
* 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. */
/**
* 处理包含转义字符的二进制字符串
* @param s
* @param p
* @param len
* @return
*/
sds sdscatrepr(sds s, const char *p, size_t len) {
//给s字符串后拼接 "\""
s = sdscatlen(s,"\"",1);
while(len--) {
switch(*p) {
case '\\':
case '"':
//将可变长格式化字符串连接到sds后面
s = sdscatprintf(s,"\\%c",*p);
break;
case '\n': s = sdscatlen(s,"\\n",2); break;
case '\r': s = sdscatlen(s,"\\r",2); break;
case '\t': s = sdscatlen(s,"\\t",2); break;
case '\a': s = sdscatlen(s,"\\a",2); break;
case '\b': s = sdscatlen(s,"\\b",2); break;
default:
//检查所传的字符是否是可打印的 可打印为true 否则为false
if (isprint(*p))
//将可变长格式化字符串连接到sds后面
s = sdscatprintf(s,"%c",*p);
else
s = sdscatprintf(s,"\\x%02x",(unsigned char)*p);
break;
}
p++;
}
//给s字符串后拼接 "\""
return sdscatlen(s,"\"",1);
}
/**
* 判断char c是否是十六进制数,是根据ASCII码判断的
* @param c 字符
* @return
*/
/* Helper function for sdssplitargs() that returns non zero if 'c'
* is a valid hex digit. */
int is_hex_digit(char c) {
return (c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') ||
(c >= 'A' && c <= 'F');
}
/**
* 将一个十六进制字符转换成十进制
* @param c 字符
* @return
*/
/* Helper function for sdssplitargs() that converts a hex digit into an
* integer from 0 to 15 */
int hex_digit_to_int(char c) {
switch(c) {
case '0': return 0;
case '1': return 1;
case '2': return 2;
case '3': return 3;
case '4': return 4;
case '5': return 5;
case '6': return 6;
case '7': return 7;
case '8': return 8;
case '9': return 9;
case 'a': case 'A': return 10;
case 'b': case 'B': return 11;
case 'c': case 'C': return 12;
case 'd': case 'D': return 13;
case 'e': case 'E': return 14;
case 'f': case 'F': return 15;
default: return 0;
}
}
/* Split a line into arguments, where every argument can be in the
* following programming-language REPL-alike form:
*
* foo bar "newline are supported\n" and "\xff\x00otherstuff"
*
* The number of arguments is stored into *argc, and an array
* of sds is returned.
*
* The caller should free the resulting array of sds strings with
* sdsfreesplitres().
*
* Note that sdscatrepr() is able to convert back a string into
* a quoted string in the same format sdssplitargs() is able to parse.
*
* The function returns the allocated tokens on success, even when the
* input string is empty, or NULL if the input contains unbalanced
* quotes or closed quotes followed by non space characters
* as in: "foo"bar or "foo'
*/
/**
* 字符串分割函数
* 将一行内容读取到sds指针数组,解析配置文件时使用,每个配置项保存在一个sds中,此函数返回一个sds指针数组和其元素个数
* @param line
* @param argc
* @return
*/
sds *sdssplitargs(const char *line, int *argc) {
const char *p = line;
char *current = NULL;
char **vector = NULL;
*argc = 0;
while(1) {
/* skip blanks */
// isspace 判断字符是否为空白字符 不是空白字符 返回0 ,是空白字符 返回非0
while(*p && isspace(*p)) p++;
if (*p) {
/* get a token */
int inq=0; /* set to 1 if we are in "quotes" */
int insq=0; /* set to 1 if we are in 'single quotes' */
int done=0;
//如果curent为NULL则创建一个空的sds字符串
if (current == NULL) current = sdsempty();
while(!done) {
// *p = '"' inq = 1
//处理单引号
if (inq) {
//处理16进制数字转换
// 如果满足 *p == '\\' *(p+1) == 'x' 和 *(p+2)、*(p+3)都是十六进制
if (*p == '\\' && *(p+1) == 'x' &&
is_hex_digit(*(p+2)) &&
is_hex_digit(*(p+3)))
{
unsigned char byte;
// 16进制转10进制
byte = (hex_digit_to_int(*(p+2))*16)+
hex_digit_to_int(*(p+3));
current = sdscatlen(current,(char*)&byte,1);
p += 3;
} else if (*p == '\\' && *(p+1)) {
//处理特殊字符
char c;
p++;
switch(*p) {
case 'n': c = '\n'; break;
case 'r': c = '\r'; break;
case 't': c = '\t'; break;
case 'b': c = '\b'; break;
case 'a': c = '\a'; break;
default: c = *p; break;
}
current = sdscatlen(current,&c,1);
} else if (*p == '"') {
/* closing quote must be followed by a space or
* nothing at all. */
if (*(p+1) && !isspace(*(p+1))) goto err;
done=1;
} else if (!*p) {
/* unterminated quotes */
goto err;
} else {
current = sdscatlen(current,p,1);
}
} else if (insq) {
//处理单引号
if (*p == '\\' && *(p+1) == '\'') {
p++;
current = sdscatlen(current,"'",1);
} else if (*p == '\'') {
/* closing quote must be followed by a space or
* nothing at all. */
if (*(p+1) && !isspace(*(p+1))) goto err;
done=1;
} else if (!*p) {
/* unterminated quotes */
goto err;
} else {
current = sdscatlen(current,p,1);
}
} else {
switch(*p) {
case ' ':
case '\n':
case '\r':
case '\t':
case '\0':
done=1;
break;
case '"':
inq=1;
break;
case '\'':
insq=1;
break;
default:
//拼接到curent后面
current = sdscatlen(current,p,1);
break;
}
}
if (*p) p++;
}
//分配内存空间
/* add the token to the vector */
vector = s_realloc(vector,((*argc)+1)*sizeof(char*));
vector[*argc] = current;
(*argc)++;
current = NULL;
} else {
/* Even on empty input string return something not NULL. */
//即使输入为空也返回不为空的内容
if (vector == NULL) vector = s_malloc(sizeof(void*));
return vector;
}
}
err:
while((*argc)--)
sdsfree(vector[*argc]);
s_free(vector);
if (current) sdsfree(current);
*argc = 0;
return NULL;
}
/* Modify the string substituting all the occurrences of the set of
* characters specified in the 'from' string to the corresponding character
* in the 'to' array.
*
* For instance: sdsmapchars(mystring, "ho", "01", 2)
* will have the effect of turning the string "hello" into "0ell1".
*
* The function returns the sds string pointer, that is always the same
* as the input pointer since no resize is needed. */
/**
* 将sds中出现在指定字符集中的字符用另一个字符集中的字符代替,要求两个字符集长度相等
* @param s sds字符串
* @param from 指定的字符
* @param to 替换成的字符
* @param setlen 长度
* @return sds
*/
sds sdsmapchars(sds s, const char *from, const char *to, size_t setlen) {
size_t j, i, l = sdslen(s);
for (j = 0; j < l; j++) {
for (i = 0; i < setlen; i++) {
if (s[j] == from[i]) {
s[j] = to[i];
break;
}
}
}
return s;
}
/* Join an array of C strings using the specified separator (also a C string).
* Returns the result as an sds string. */
/**
* 将若干C字符串用提供的分割器连接起来,产生一个sds
* @param argv C字符串
* @param argc 个数
* @param sep 分割符
* @return
*/
sds sdsjoin(char **argv, int argc, char *sep) {
sds join = sdsempty();
int j;
for (j = 0; j < argc; j++) {
//字符串拼接到join后面
join = sdscat(join, argv[j]);
if (j != argc-1) join = sdscat(join,sep);
}
return join;
}
/**
* 和sdsjoin类似,连接的是若干sds
* @param argv 若干个sds字符串
* @param argc 个数
* @param sep 分隔符
* @param seplen 长度
* @return
*/
/* Like sdsjoin, but joins an array of SDS strings. */
sds sdsjoinsds(sds *argv, int argc, const char *sep, size_t seplen) {
sds join = sdsempty();
int j;
for (j = 0; j < argc; j++) {
join = sdscatsds(join, argv[j]);
if (j != argc-1) join = sdscatlen(join,sep,seplen);
}
return join;
}
/* Wrappers to the allocators used by SDS. Note that SDS will actually
* just use the macros defined into sdsalloc.h in order to avoid to pay
* the overhead of function calls. Here we define these wrappers only for
* the programs SDS is linked to, if they want to touch the SDS internals
* even if they use a different allocator. */
/**
* 分配内存
* @param size
* @return
*/
void *sds_malloc(size_t size) { return s_malloc(size); }
/**
* 重新分配内存
* @param ptr
* @param size
* @return
*/
void *sds_realloc(void *ptr, size_t size) { return s_realloc(ptr,size); }
/**
* 释放内存
* @param ptr
*/
void sds_free(void *ptr) { s_free(ptr); }
/* Perform expansion of a template string and return the result as a newly
* allocated sds.
*
* Template variables are specified using curly brackets, e.g. {variable}.
* An opening bracket can be quoted by repeating it twice.
*/
/**
* sds回调模板函数
* @param template
* @param cb_func
* @param cb_arg
* @return
*/
sds sdstemplate(const char *template, sdstemplate_callback_t cb_func, void *cb_arg)
{
sds res = sdsempty();
const char *p = template;
while (*p) {
/* Find next variable, copy everything until there */
const char *sv = strchr(p, '{');
if (!sv) {
/* Not found: copy till rest of template and stop */
res = sdscat(res, p);
break;
} else if (sv > p) {
/* Found: copy anything up to the begining of the variable */
res = sdscatlen(res, p, sv - p);
}
/* Skip into variable name, handle premature end or quoting */
//跳过遍历名称
sv++;
if (!*sv) goto error; /* Premature end of template */
if (*sv == '{') {
/* Quoted '{' */
p = sv + 1;
res = sdscat(res, "{");
continue;
}
/* Find end of variable name, handle premature end of template */
const char *ev = strchr(sv, '}');
if (!ev) goto error;
/* Pass variable name to callback and obtain value. If callback failed,
* abort. */
// 通过变量名称去回调
sds varname = sdsnewlen(sv, ev - sv);
sds value = cb_func(varname, cb_arg);
//释放内存空间
sdsfree(varname);
if (!value) goto error;
//将值添加到结果
/* Append value to result and continue */
res = sdscat(res, value);
//释放值
sdsfree(value);
p = ev + 1;
}
return res;
error:
//释放res
sdsfree(res);
return NULL;
}
#ifdef REDIS_TEST
#include <stdio.h>
#include <limits.h>
#include "testhelp.h"
#define UNUSED(x) (void)(x)
static sds sdsTestTemplateCallback(sds varname, void *arg) {
UNUSED(arg);
static const char *_var1 = "variable1";
static const char *_var2 = "variable2";
if (!strcmp(varname, _var1)) return sdsnew("value1");
else if (!strcmp(varname, _var2)) return sdsnew("value2");
else return NULL;
}
int sdsTest(int argc, char **argv, int accurate) {
UNUSED(argc);
UNUSED(argv);
UNUSED(accurate);
{
sds x = sdsnew("foo"), y;
test_cond("Create a string and obtain the length",
sdslen(x) == 3 && memcmp(x,"foo\0",4) == 0);
sdsfree(x);
x = sdsnewlen("foo",2);
test_cond("Create a string with specified length",
sdslen(x) == 2 && memcmp(x,"fo\0",3) == 0);
x = sdscat(x,"bar");
test_cond("Strings concatenation",
sdslen(x) == 5 && memcmp(x,"fobar\0",6) == 0);
x = sdscpy(x,"a");
test_cond("sdscpy() against an originally longer string",
sdslen(x) == 1 && memcmp(x,"a\0",2) == 0);
x = sdscpy(x,"xyzxxxxxxxxxxyyyyyyyyyykkkkkkkkkk");
test_cond("sdscpy() against an originally shorter string",
sdslen(x) == 33 &&
memcmp(x,"xyzxxxxxxxxxxyyyyyyyyyykkkkkkkkkk\0",33) == 0);
sdsfree(x);
x = sdscatprintf(sdsempty(),"%d",123);
test_cond("sdscatprintf() seems working in the base case",
sdslen(x) == 3 && memcmp(x,"123\0",4) == 0);
sdsfree(x);
x = sdscatprintf(sdsempty(),"a%cb",0);
test_cond("sdscatprintf() seems working with \\0 inside of result",
sdslen(x) == 3 && memcmp(x,"a\0""b\0",4) == 0);
{
sdsfree(x);
char etalon[1024*1024];
for (size_t i = 0; i < sizeof(etalon); i++) {
etalon[i] = '0';
}
x = sdscatprintf(sdsempty(),"%0*d",(int)sizeof(etalon),0);
test_cond("sdscatprintf() can print 1MB",
sdslen(x) == sizeof(etalon) && memcmp(x,etalon,sizeof(etalon)) == 0);
}
sdsfree(x);
x = sdsnew("--");
x = sdscatfmt(x, "Hello %s World %I,%I--", "Hi!", LLONG_MIN,LLONG_MAX);
test_cond("sdscatfmt() seems working in the base case",
sdslen(x) == 60 &&
memcmp(x,"--Hello Hi! World -9223372036854775808,"
"9223372036854775807--",60) == 0);
printf("[%s]\n",x);
sdsfree(x);
x = sdsnew("--");
x = sdscatfmt(x, "%u,%U--", UINT_MAX, ULLONG_MAX);
test_cond("sdscatfmt() seems working with unsigned numbers",
sdslen(x) == 35 &&
memcmp(x,"--4294967295,18446744073709551615--",35) == 0);
sdsfree(x);
x = sdsnew(" x ");
sdstrim(x," x");
test_cond("sdstrim() works when all chars match",
sdslen(x) == 0);
sdsfree(x);
x = sdsnew(" x ");
sdstrim(x," ");
test_cond("sdstrim() works when a single char remains",
sdslen(x) == 1 && x[0] == 'x');
sdsfree(x);
x = sdsnew("xxciaoyyy");
sdstrim(x,"xy");
test_cond("sdstrim() correctly trims characters",
sdslen(x) == 4 && memcmp(x,"ciao\0",5) == 0);
y = sdsdup(x);
sdsrange(y,1,1);
test_cond("sdsrange(...,1,1)",
sdslen(y) == 1 && memcmp(y,"i\0",2) == 0);
sdsfree(y);
y = sdsdup(x);
sdsrange(y,1,-1);
test_cond("sdsrange(...,1,-1)",
sdslen(y) == 3 && memcmp(y,"iao\0",4) == 0);
sdsfree(y);
y = sdsdup(x);
sdsrange(y,-2,-1);
test_cond("sdsrange(...,-2,-1)",
sdslen(y) == 2 && memcmp(y,"ao\0",3) == 0);
sdsfree(y);
y = sdsdup(x);
sdsrange(y,2,1);
test_cond("sdsrange(...,2,1)",
sdslen(y) == 0 && memcmp(y,"\0",1) == 0);
sdsfree(y);
y = sdsdup(x);
sdsrange(y,1,100);
test_cond("sdsrange(...,1,100)",
sdslen(y) == 3 && memcmp(y,"iao\0",4) == 0);
sdsfree(y);
y = sdsdup(x);
sdsrange(y,100,100);
test_cond("sdsrange(...,100,100)",
sdslen(y) == 0 && memcmp(y,"\0",1) == 0);
sdsfree(y);
y = sdsdup(x);
sdsrange(y,4,6);
test_cond("sdsrange(...,4,6)",
sdslen(y) == 0 && memcmp(y,"\0",1) == 0);
sdsfree(y);
y = sdsdup(x);
sdsrange(y,3,6);
test_cond("sdsrange(...,3,6)",
sdslen(y) == 1 && memcmp(y,"o\0",2) == 0);
sdsfree(y);
sdsfree(x);
x = sdsnew("foo");
y = sdsnew("foa");
test_cond("sdscmp(foo,foa)", sdscmp(x,y) > 0);
sdsfree(y);
sdsfree(x);
x = sdsnew("bar");
y = sdsnew("bar");
test_cond("sdscmp(bar,bar)", sdscmp(x,y) == 0);
sdsfree(y);
sdsfree(x);
x = sdsnew("aar");
y = sdsnew("bar");
test_cond("sdscmp(bar,bar)", sdscmp(x,y) < 0);
sdsfree(y);
sdsfree(x);
x = sdsnewlen("\a\n\0foo\r",7);
y = sdscatrepr(sdsempty(),x,sdslen(x));
test_cond("sdscatrepr(...data...)",
memcmp(y,"\"\\a\\n\\x00foo\\r\"",15) == 0);
{
unsigned int oldfree;
char *p;
int i;
size_t step = 10, j;
sdsfree(x);
sdsfree(y);
x = sdsnew("0");
test_cond("sdsnew() free/len buffers", sdslen(x) == 1 && sdsavail(x) == 0);
/* Run the test a few times in order to hit the first two
* SDS header types. */
for (i = 0; i < 10; i++) {
size_t oldlen = sdslen(x);
x = sdsMakeRoomFor(x,step);
int type = x[-1]&SDS_TYPE_MASK;
test_cond("sdsMakeRoomFor() len", sdslen(x) == oldlen);
if (type != SDS_TYPE_5) {
test_cond("sdsMakeRoomFor() free", sdsavail(x) >= step);
oldfree = sdsavail(x);
UNUSED(oldfree);
}
p = x+oldlen;
for (j = 0; j < step; j++) {
p[j] = 'A'+j;
}
sdsIncrLen(x,step);
}
test_cond("sdsMakeRoomFor() content",
memcmp("0ABCDEFGHIJABCDEFGHIJABCDEFGHIJABCDEFGHIJABCDEFGHIJABCDEFGHIJABCDEFGHIJABCDEFGHIJABCDEFGHIJABCDEFGHIJ",x,101) == 0);
test_cond("sdsMakeRoomFor() final length",sdslen(x)==101);
sdsfree(x);
}
/* Simple template */
x = sdstemplate("v1={variable1} v2={variable2}", sdsTestTemplateCallback, NULL);
test_cond("sdstemplate() normal flow",
memcmp(x,"v1=value1 v2=value2",19) == 0);
sdsfree(x);
/* Template with callback error */
x = sdstemplate("v1={variable1} v3={doesnotexist}", sdsTestTemplateCallback, NULL);
test_cond("sdstemplate() with callback error", x == NULL);
/* Template with empty var name */
x = sdstemplate("v1={", sdsTestTemplateCallback, NULL);
test_cond("sdstemplate() with empty var name", x == NULL);
/* Template with truncated var name */
x = sdstemplate("v1={start", sdsTestTemplateCallback, NULL);
test_cond("sdstemplate() with truncated var name", x == NULL);
/* Template with quoting */
x = sdstemplate("v1={{{variable1}} {{} v2={variable2}", sdsTestTemplateCallback, NULL);
test_cond("sdstemplate() with quoting",
memcmp(x,"v1={value1} {} v2=value2",24) == 0);
sdsfree(x);
}
test_report();
return 0;
}
#endif