Redis源码学习
本系列文章基于redis6.0.6版本，详见官网https://redis.io。
根据前人分享，结合源码，本系列将分为11个部分, 详见Redis源码学习，文章为记录个人理解，能力受限，如有偏颇之处请指正。
前言
Redis基础数据结构篇之dict:
SDSLib, A C dynamic strings library, by Salvatore Sanfilippo
一、图示
二、源码理解
1.sds.h
sds是宏定义的一个char*字符串，基于上述数据结构实现了基本的方法包括拼接，拆分等。
/* SDSLib, A C dynamic strings library
*
* Copyright (c) 2006-2010, Salvatore Sanfilippo <antirez at gmail dot com>
* All rights reserved.
*
*/
#ifndef __SDS_H
#define __SDS_H
#define SDS_MAX_PREALLOC (1024*1024)
#ifdef _WIN32
#include "Win32_Interop/Win32_Portability.h"
#include "Win32_Interop/win32_types.h"
#endif
#include <sys/types.h>
#include <stdarg.h>
typedef char *sds;
struct sdshdr {
unsigned int len; // buf中实际已使用长度
unsigned int free; // buf中暂未使用的长度
char buf[]; // buf会被初始化为再末尾填充一个结束符'\0'的数组，且该结束符长度1不包含再len和free的长度中
};
static inline size_t sdslen(const sds s) {
struct sdshdr *sh = (void*)(s-(sizeof(struct sdshdr))); // 偏移到sds的len位置处
return sh->len;
}
static inline size_t sdsavail(const sds s) {
struct sdshdr *sh = (void*)(s-(sizeof(struct sdshdr)));
return sh->free;
}
sds sdsnewlen(const void *init, size_t initlen);
sds sdsnew(const char *init);
sds sdsempty(void);
size_t sdslen(const sds s);
sds sdsdup(const sds s);
void sdsfree(sds s);
size_t sdsavail(const sds s);
sds sdsgrowzero(sds s, size_t len);
sds sdscatlen(sds s, const void *t, size_t len);
sds sdscat(sds s, const char *t);
sds sdscatsds(sds s, const sds t);
sds sdscpylen(sds s, const char *t, size_t len);
sds sdscpy(sds s, const char *t);
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 sdscatfmt(sds s, char const *fmt, ...);
sds sdstrim(sds s, const char *cset);
void sdsrange(sds s, int start, int end);
void sdsupdatelen(sds s);
void sdsclear(sds s);
int sdscmp(const sds s1, const sds s2);
sds *sdssplitlen(const char *s, int len, const char *sep, int seplen, int *count);
void sdsfreesplitres(sds *tokens, int count);
void sdstolower(sds s);
void sdstoupper(sds s);
sds sdsfromlonglong(PORT_LONGLONG value);
sds sdscatrepr(sds s, const char *p, size_t len);
sds *sdssplitargs(const char *line, int *argc);
sds sdsmapchars(sds s, const char *from, const char *to, size_t setlen);
sds sdsjoin(char **argv, int argc, char *sep);
/* Low level functions exposed to the user API */
sds sdsMakeRoomFor(sds s, size_t addlen);
void sdsIncrLen(sds s, int incr);
sds sdsRemoveFreeSpace(sds s);
size_t sdsAllocSize(sds s);
#endif
2.sds.c
#ifdef _WIN32
#include "Win32_Interop/Win32_Portability.h"
#include "Win32_Interop/win32fixes.h"
#endif
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <assert.h>
#include "sds.h"
#include "zmalloc.h"
/* 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) {
struct sdshdr *sh;
if (init) {
sh = zmalloc(sizeof(struct sdshdr)+initlen+1); // 头长度+实际内容长度+1个结束符'\0'
} else {
sh = zcalloc(sizeof(struct sdshdr)+initlen+1);
}
if (sh == NULL) return NULL;
sh->len = (int)initlen; WIN_PORT_FIX /* cast (int) */
sh->free = 0;
if (initlen && init)
memcpy(sh->buf, init, initlen); // 内存拷贝
sh->buf[initlen] = '\0';
return (char*)sh->buf;
}
/* 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);
}
/* 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);
}
/* Duplicate an sds string. */
sds sdsdup(const sds s) {
return sdsnewlen(s, sdslen(s)); // 复制sds的buf内容，此时传递进来的为sds结构的buf地址
}
/* Free an sds string. No operation is performed if 's' is NULL. */
void sdsfree(sds s) {
if (s == NULL) return; // sdsnewlen返回的sds->buf不可能为NULL，有自动append的结束符
zfree(s-sizeof(struct sdshdr));
}
/* 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) {
struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
int reallen = (int)strlen(s); WIN_PORT_FIX /* cast (int) */
sh->free += (sh->len-reallen);
sh->len = 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. */
void sdsclear(sds s) {
struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
sh->free += sh->len;
sh->len = 0;
sh->buf[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. */
sds sdsMakeRoomFor(sds s, size_t addlen) {
struct sdshdr *sh, *newsh;
size_t free = sdsavail(s);
size_t len, newlen;
if (free >= addlen) return s; // free空间大于addlen，可以装下即将填入的内容，则不扩展
len = sdslen(s);
sh = (void*) (s-(sizeof(struct sdshdr)));
newlen = (len+addlen);
if (newlen < SDS_MAX_PREALLOC) // 控制增长速度
newlen *= 2;
else
newlen += SDS_MAX_PREALLOC;
newsh = zrealloc(sh, sizeof(struct sdshdr)+newlen+1); // 使用realloc尝试附加内存或者重新分配内存再拷贝到新内存，之前的s必须更新
if (newsh == NULL) return NULL;
newsh->free = (int)(newlen - len); WIN_PORT_FIX /* cast (int) */
return newsh->buf;
}
/* 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) {
struct sdshdr *sh;
sh = (void*) (s-(sizeof(struct sdshdr)));
sh = (struct sdshdr *)zrealloc(sh, sizeof(struct sdshdr)+sh->len+1); WIN_PORT_FIX /* cast (struct sdshdr *) */
sh->free = 0;
return sh->buf;
}
/* 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) {
struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
return sizeof(*sh)+sh->len+sh->free+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);
*/
void sdsIncrLen(sds s, int incr) {
struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
if (incr >= 0)
assert(sh->free >= (unsigned int)incr); // 正整数情况从free中减少incr bytes,再向len中增加， 使用断言保护长度
else
assert(sh->len >= (unsigned int)(-incr)); // 负整数情况从len中减少incr bytes,再向free中增加， 使用断言保护长度
sh->len += incr;
sh->free -= incr;
s[sh->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. */
sds sdsgrowzero(sds s, size_t len) {
struct sdshdr *sh = (void*)(s-(sizeof(struct sdshdr)));
size_t totlen, curlen = sh->len;
if (len <= curlen) return s;
s = sdsMakeRoomFor(s,len-curlen);
if (s == NULL) return NULL;
/* Make sure added region doesn't contain garbage */
sh = (void*)(s-(sizeof(struct sdshdr)));
memset(s+curlen,0,(len-curlen+1)); /* also set trailing \0 byte */
totlen = sh->len+sh->free;
sh->len = (int)len; WIN_PORT_FIX /* cast (int) */
sh->free = (int)(totlen-sh->len); WIN_PORT_FIX /* cast (int) */
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. */
sds sdscatlen(sds s, const void *t, size_t len) {
struct sdshdr *sh;
size_t curlen = sdslen(s);
s = sdsMakeRoomFor(s,len);
if (s == NULL) return NULL;
sh = (void*) (s-(sizeof(struct sdshdr)));
memcpy(s+curlen, t, len);
sh->len = (int)(curlen+len); WIN_PORT_FIX /* cast (int) */
sh->free = (int)(sh->free-len); WIN_PORT_FIX /* cast (int) */
s[curlen+len] = '\0';
return s;
}
/* 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));
}
/* 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));
}
/* 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) {
struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
size_t totlen = sh->free+sh->len;
if (totlen < len) {
s = sdsMakeRoomFor(s,len-sh->len);
if (s == NULL) return NULL;
sh = (void*) (s-(sizeof(struct sdshdr)));
totlen = sh->free+sh->len;
}
memcpy(s, t, len);
s[len] = '\0';
sh->len = (int)len; WIN_PORT_FIX /* cast (int) */
sh->free = (int)(totlen-len); WIN_PORT_FIX /* cast (int) */
return s;
}
/* 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));
}
/* 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 // 有符号数64位转换为str,除开符号位总共有21个符号值
int sdsll2str(char *s, PORT_LONGLONG value) {
char *p, aux;
PORT_ULONGLONG v;
size_t l;
/* Generate the string representation, this method produces
* an reversed string. */
v = (value < 0) ? -value : value;
p = s;
do {
*p++ = '0'+(v);
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 (int)l; WIN_PORT_FIX /* cast (int) */
}
/* Identical sdsll2str(), but for PORT_ULONGLONG type. */
int sdsull2str(char *s, PORT_ULONGLONG v) {
char *p, aux;
size_t l;
/* Generate the string representation, this method produces
* an reversed string. */
p = s;
do {
*p++ = '0'+(v);
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 (int)l;
}
/* Create an sds string from a long long value. It is much faster than:
*
* sdscatprintf(sdsempty(),"%lld\n", value);
*/
sds sdsfromlonglong(PORT_LONGLONG value) {
char buf[SDS_LLSTR_SIZE];
int len = sdsll2str(buf,value);
return sdsnewlen(buf,len);
}
/* 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;
size_t buflen = strlen(fmt)*2; // 为什么是2倍长度? 不知道起始位置时应该以多大的基数size来尝试装下format后的数据,
// 基于format本身的大小做2次幂来扩大申请的数组大小，不断重试去vsnprintf
/* We try to start using a static buffer for speed. // 性能优化选择
* If not possible we revert to heap allocation. */
if (buflen > sizeof(staticbuf)) {
buf = zmalloc(buflen);
if (buf == NULL) return NULL;
} else {
buflen = sizeof(staticbuf);
}
/* Try with buffers two times bigger every time we fail to
* fit the string in the current buffer size. */
while(1) {
buf[buflen - 2] = '\0'; // 为什么再最后预留一个字节的位置？ 从下文的WIN32_ONLY(-1)看是考虑跨平台时的表现不同而做
// 的适配;如果不考虑跨平台也可以直接设置 buf[fuflen-1]='\0',同时丢弃虾米那的WIN32_ONLY(-1)
va_copy(cpy,ap);
vsnprintf(buf, buflen WIN32_ONLY(-1), fmt, cpy); // WIN_PORT_FIX: see comment below
// vsnprintf 用法参考 http://www.cplusplus.com/reference/cstdio/vsnprintf/
va_end(cpy);
if (buf[buflen-2] != '\0') {
if (buf != staticbuf) zfree(buf);
buflen *= 2;
// WIN_PORT_FIX: from the vsnprintf documentation in MSDN:
// "To ensure that there is room for the terminating null, be sure
// that count is strictly less than the buffer length and
// initialize the buffer to null prior to calling the function."
buf = IF_WIN32(zcalloc,zmalloc)(buflen);
if (buf == NULL) return NULL;
continue;
}
break;
}
/* Finally concat the obtained string to the SDS string and return it. */
t = sdscat(s, buf); // 将format后的buf追加到s后
if (buf != staticbuf) zfree(buf); // 若没使用栈里的临时变量则位动态申请的数组，释放之
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);
*/
sds sdscatprintf(sds s, const char *fmt, ...) {
va_list ap;
char *t;
va_start(ap, fmt); // va系列函数利用c语言中函数参数压栈的顺序，巧妙的定义宏从而来获取变参地址，根据fmt获取变参的类型来取得数据
// 可以参考 https://blog.csdn.net/costa100/article/details/5787068
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 (PORT_LONGLONG, int64_t)
* %u - unsigned int
* %U - 64 bit unsigned integer (PORT_ULONGLONG, uint64_t)
* %% - Verbatim "%" character.
*/
sds sdscatfmt(sds s, char const *fmt, ...) {
struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
size_t initlen = sdslen(s);
const char *f = fmt;
int i;
va_list ap;
va_start(ap,fmt);
f = fmt; /* Next format specifier byte to process. */
i = (int)initlen; /* Position of the next byte to write to dest str. */
while(*f) {
char next, *str;
unsigned int l;
PORT_LONGLONG num;
PORT_ULONGLONG unum;
/* Make sure there is always space for at least 1 char. */
if (sh->free == 0) {
s = sdsMakeRoomFor(s,1);
sh = (void*) (s-(sizeof(struct sdshdr)));
}
switch(*f) {
case '%': // format开始标识
next = *(f+1);
f++;
switch(next) {
case 's':
case 'S':
str = va_arg(ap,char*); // 按字符串类型处理
l = (int)((next == 's') ? strlen(str) : sdslen(str)); WIN_PORT_FIX /* cast (int) */
if (sh->free < l) {
s = sdsMakeRoomFor(s,l);
sh = (void*) (s-(sizeof(struct sdshdr)));
}
memcpy(s+i,str,l);
sh->len += l;
sh->free -= l;
i += l;
break;
case 'i':
case 'I':
if (next == 'i')
num = va_arg(ap,int);
else
num = va_arg(ap,PORT_LONGLONG);
{
char buf[SDS_LLSTR_SIZE];
l = sdsll2str(buf,num);
if (sh->free < l) {
s = sdsMakeRoomFor(s,l);
sh = (void*) (s-(sizeof(struct sdshdr)));
}
memcpy(s+i,buf,l);
sh->len += l;
sh->free -= l;
i += l;
}
break;
case 'u':
case 'U':
if (next == 'u')
unum = va_arg(ap,unsigned int);
else
unum = va_arg(ap,PORT_ULONGLONG);
{
char buf[SDS_LLSTR_SIZE];
l = sdsull2str(buf,unum);
if (sh->free < l) {
s = sdsMakeRoomFor(s,l);
sh = (void*) (s-(sizeof(struct sdshdr)));
}
memcpy(s+i,buf,l);
sh->len += l;
sh->free -= l;
i += l;
}
break;
default: /* Handle %% and generally %<unknown>. */
s[i++] = next;
sh->len += 1;
sh->free -= 1;
break;
}
break;
default:
s[i++] = *f;
sh->len += 1;
sh->free -= 1;
break;
}
f++;
}
va_end(ap);
/* 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 "Hello World".
*/
sds sdstrim(sds s, const char *cset) {
struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
char *start, *end, *sp, *ep;
size_t len;
sp = start = s;
ep = end = s+sdslen(s)-1;
while(sp <= end && strchr(cset, *sp)) sp++; // 从字符串头开始向字符串位开时连续匹配到的cset字符
while(ep > start && strchr(cset, *ep)) ep--; // 从字符串尾向字符串头方向开始连续匹配到的cset字符
len = (sp > ep) ? 0 : ((ep-sp)+1); // 计算中间没去除字符的长度
if (sh->buf != sp) memmove(sh->buf, sp, len); // 将匹配到的数据移动到开始位置
sh->buf[len] = '\0'; // 设置结束标志
sh->free = sh->free+(int)(sh->len-len); WIN_PORT_FIX /* cast (int) */
sh->len = (int)len; WIN_PORT_FIX /* cast (int) */
return s;
}
/* 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.
*
* Example:
*
* s = sdsnew("Hello World");
* sdsrange(s,1,-1); => "ello World"
*/
void sdsrange(sds s, int start, int end) {
struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
size_t newlen, len = sdslen(s);
if (len == 0) return;
if (start < 0) {
start = (int)len+start; WIN_PORT_FIX /* cast (int) */
if (start < 0) start = 0;
}
if (end < 0) {
end = (int)len+end; WIN_PORT_FIX /* cast (int) */
if (end < 0) end = 0;
}
newlen = (start > end) ? 0 : (end-start)+1; // 计算负值转换后的留存真实长度
if (newlen != 0) {
if (start >= (signed)len) {
newlen = 0;
} else if (end >= (signed)len) {
end = (int)len-1; WIN_PORT_FIX /* cast (int) */
newlen = (start > end) ? 0 : (end-start)+1;
}
} else {
start = 0;
}
if (start && newlen) memmove(sh->buf, sh->buf+start, newlen); // 对start和newlen的情况做笛卡尔积分析，只有两者都非0时才需移动内存
sh->buf[newlen] = 0; // 笛卡尔积其他的三种情况在此处一起处理了
sh->free = (int)(sh->free+(sh->len-newlen)); WIN_PORT_FIX /* cast (int) */
sh->len = (int)newlen; WIN_PORT_FIX /* cast (int) */
}
/* Apply tolower() to every character of the sds string 's'. */
void sdstolower(sds s) {
int len = (int)sdslen(s), j; WIN_PORT_FIX /* cast (int) */
for (j = 0; j < len; j++) s[j] = tolower(s[j]);
}
/* Apply toupper() to every character of the sds string 's'. */
void sdstoupper(sds s) {
int len = (int)sdslen(s), j; WIN_PORT_FIX /* cast (int) */
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. */
int sdscmp(const sds s1, const sds s2) {
size_t l1, l2, minlen;
int cmp;
l1 = sdslen(s1);
l2 = sdslen(s2);
minlen = (l1 < l2) ? l1 : l2;
cmp = memcmp(s1,s2,minlen);
if (cmp == 0) return (int)(l1-l2); WIN_PORT_FIX /* cast (int) */
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.
*/
sds *sdssplitlen(const char *s, int len, const char *sep, int seplen, int *count) {
int elements = 0, slots = 5, start = 0, j;
sds *tokens;
if (seplen < 1 || len < 0) return NULL;
tokens = zmalloc(sizeof(sds)*slots);
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 */
if (slots < elements+2) {
sds *newtokens;
slots *= 2;
newtokens = zrealloc(tokens,sizeof(sds)*slots);
if (newtokens == NULL) goto cleanup;
tokens = newtokens;
}
/* search the separator */
if ((seplen == 1 && *(s+j) == sep[0]) || (memcmp(s+j,sep,seplen) == 0)) {
tokens[elements] = sdsnewlen(s+start,j-start);
if (tokens[elements] == NULL) goto cleanup;
elements++;
start = j+seplen;
j = j+seplen-1; /* skip the separator */
}
}
/* Add the final element. We are sure there is room in the tokens array. */
tokens[elements] = sdsnewlen(s+start,len-start);
if (tokens[elements] == NULL) goto cleanup;
elements++;
*count = elements;
return tokens;
cleanup:
{
int i;
for (i = 0; i < elements; i++) sdsfree(tokens[i]);
zfree(tokens);
*count = 0;
return NULL;
}
}
/* 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]);
zfree(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. */
sds sdscatrepr(sds s, const char *p, size_t len) {
s = sdscatlen(s,"\"",1);
while(len--) {
switch(*p) {
case '\\':
case '"':
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:
if (isprint((unsigned char)*p)) WIN_PORT_FIX /* cast (unsigned char) */
s = sdscatprintf(s,"%c",*p);
else
s = sdscatprintf(s,"\\xx",(unsigned char)*p);
break;
}
p++;
}
return sdscatlen(s,"\"",1);
}
/* 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');
}
/* 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'
*/
sds *sdssplitargs(const char *line, int *argc) {
const char *p = line;
char *current = NULL;
char **vector = NULL;
*argc = 0;
while(1) {
/* skip blanks */
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;
if (current == NULL) current = sdsempty();
while(!done) {
if (inq) {
if (*p == '\\' && *(p+1) == 'x' &&
is_hex_digit(*(p+2)) &&
is_hex_digit(*(p+3)))
{
unsigned char byte;
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)) {
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) {
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:
current = sdscatlen(current,p,1);
break;
}
}
if (*p) p++;
}
/* add the token to the vector */
vector = zrealloc(vector,((*argc)+1)*sizeof(char*));
vector[*argc] = current;
(*argc)++;
current = NULL;
} else {
/* Even on empty input string return something not NULL. */
if (vector == NULL) vector = zmalloc(sizeof(void*));
return vector;
}
}
err:
while((*argc)--)
sdsfree(vector[*argc]);
zfree(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. */
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. */
sds sdsjoin(char **argv, int argc, char *sep) {
sds join = sdsempty();
int j;
for (j = 0; j < argc; j++) {
join = sdscat(join, argv[j]);
if (j != argc-1) join = sdscat(join,sep);
}
return join;
}
sdscatprintf的实现比较有意思，使用va系列的宏定义实现了函数可变参数入栈后的寻址，根据fmt的类型调用vsnprintf系列来实现参数拼接，具体用法参考以上源码，另外还实现了简易版本的sdscatfmt方法，性能相对sprintf系列要快很多。
总结
本文介绍了sds的数据结构，相对简单，在比较感兴趣的几个API处做了注释介绍，如vsdscatprintf等。
使用sds使用len和free来记录当前sds的空间大小，在扩展场景的时候优先使用free里的空闲内存，以提升性能，同时在调用者使用时只返回buf指针，只能感知到buf部分，有一定的安全性。
