【redis源码】（二）Sds

Sds为redis的字符串操作函数，主要依赖于Zmalloc，直接贴代码

Sds.h

#ifndef __SDS_H
#define __SDS_H

#include <sys/types.h>
#include <stdarg.h>

typedef char *sds;


//可变长度结构体,sizeof(sdshdr)=8
struct sdshdr {
    int len;
    int free;
    char buf[];
}; 

sds sdsnewlen(const void *init, size_t initlen);
sds sdsnew(const char *init);
sds sdsempty();
size_t sdslen(const sds s);
sds sdsdup(const sds s);
void sdsfree(sds s);
size_t sdsavail(sds s);
sds sdsgrowzero(sds s, size_t len);
sds sdscatlen(sds s, void *t, size_t len);
sds sdscat(sds s, char *t);
sds sdscpylen(sds s, char *t, size_t len);
sds sdscpy(sds s, 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 sdstrim(sds s, const char *cset);
sds sdsrange(sds s, int start, int end);
void sdsupdatelen(sds s);
int sdscmp(sds s1, sds s2);
sds *sdssplitlen(char *s, int len, char *sep, int seplen, int *count);
void sdsfreesplitres(sds *tokens, int count);
void sdstolower(sds s);
void sdstoupper(sds s);
sds sdsfromlonglong(long long value);
sds sdscatrepr(sds s, char *p, size_t len);
sds *sdssplitargs(char *line, int *argc);

#endif

Sds.c

//是否在内存申请失败时发出SIGABRT信号
#define SDS_ABORT_ON_OOM

#include "sds.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include "zmalloc.h"


//当内存申请失败时发出SIGABRT信号
static void sdsOomAbort(void) {
    fprintf(stderr,"SDS: Out Of Memory (SDS_ABORT_ON_OOM defined)\n");
    abort();
}

//初始化存储长度为initlen的sds结构体，返回sds中buf字段的指针
sds sdsnewlen(const void *init, size_t initlen) {
    struct sdshdr *sh;
    //8 + initlen + 1 = sizeof(int) + sizeof(int) + sizeof('\0')
    sh = zmalloc(sizeof(struct sdshdr)+initlen+1);
#ifdef SDS_ABORT_ON_OOM
    if (sh == NULL) sdsOomAbort();
#else
    if (sh == NULL) return NULL;
#endif
    sh->len = initlen;
    sh->free = 0;
    if (initlen) {
        if (init) memcpy(sh->buf, init, initlen);
        else memset(sh->buf,0,initlen);
    }
    sh->buf[initlen] = '\0';
    return (char*)sh->buf;
}

//初始化一个字符串为空的sds中buf字段的指针
sds sdsempty(void) {
    return sdsnewlen("",0);
}

//将一个char *转化成sds结构，得到sds中buf字段的指针
sds sdsnew(const char *init) {
    size_t initlen = (init == NULL) ? 0 : strlen(init);
    return sdsnewlen(init, initlen);
}

//根据buf的指针-8得到sds结构体的指针，得到len字段
size_t sdslen(const sds s) {
    struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
    return sh->len;
}

//复制一个sds字符串
sds sdsdup(const sds s) {
    return sdsnewlen(s, sdslen(s));
}

//释放sds字符串所在的整个sdshdr的结构体的内存空间
void sdsfree(sds s) {
    if (s == NULL) return;
    zfree(s-sizeof(struct sdshdr));
}

//得到sds结构的可用长度，即s->len - strlen(s->buff)
size_t sdsavail(sds s) {
    struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
    return sh->free;
}

//当sds字符串操作后，更新sds结构体中的len信息
void sdsupdatelen(sds s) {
    struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
    int reallen = strlen(s);
    sh->free += (sh->len-reallen);
    sh->len = reallen;
}

//另外在sds s串中申请长度为addlen长度的空间
static 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;
    len = sdslen(s);
    sh = (void*) (s-(sizeof(struct sdshdr)));
    newlen = (len+addlen)*2; //多申请些，以防止短时内再次申请 ? 有点不明白为什么这么做
    newsh = zrealloc(sh, sizeof(struct sdshdr)+newlen+1);
#ifdef SDS_ABORT_ON_OOM
    if (newsh == NULL) sdsOomAbort();
#else
    if (newsh == NULL) return NULL;
#endif

    newsh->free = newlen - len;
    return newsh->buf;
}

/* 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. */
//扩容s所能容纳的字符串的长度到len
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; //如果当前长度已经满足，直接返回
    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 = len;
    sh->free = totlen-sh->len;
    return s;
}

//将t开头的长度为len的字符串接到s后边
sds sdscatlen(sds s, 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 = curlen+len;
    sh->free = sh->free-len;
    s[curlen+len] = '\0';
    return s;
}

//将t开头字符串接到s后边
sds sdscat(sds s, char *t) {
    return sdscatlen(s, t, strlen(t));
}

//将t开头长度为len的字符串复制给s
sds sdscpylen(sds s, 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 = len;
    sh->free = totlen-len;
    return s;
}

//将t开头的字符串复制给s
sds sdscpy(sds s, char *t) {
    return sdscpylen(s, t, strlen(t));
}


//将fmt格式的字符串接到s后边
sds sdscatvprintf(sds s, const char *fmt, va_list ap) {
    va_list cpy;
    char *buf, *t;
    size_t buflen = 16;

    while(1) {
        buf = zmalloc(buflen);
#ifdef SDS_ABORT_ON_OOM
        if (buf == NULL) sdsOomAbort();
#else
        if (buf == NULL) return NULL;
#endif
        buf[buflen-2] = '\0';
        va_copy(cpy,ap);
        vsnprintf(buf, buflen, fmt, cpy);
        if (buf[buflen-2] != '\0') {
            zfree(buf);
            buflen *= 2;
            continue;
        }
        break;
    }
    t = sdscat(s, buf);
    zfree(buf);
    return t;
}

//将fmt格式的字符串接到s后边
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;
}

//trim....移除s中头尾属于cset串中的字符
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++; //找到头尾
    while(ep > start && strchr(cset, *ep)) ep--;
    len = (sp > ep) ? 0 : ((ep-sp)+1);//计算trim后的长度
    if (sh->buf != sp) memmove(sh->buf, sp, len);
    sh->buf[len] = '\0';
    sh->free = sh->free+(sh->len-len);
    sh->len = len;
    return s;
}

//得到s的start开始，end结束的子串
sds 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 s;
    if (start < 0) {
        start = len+start;
        if (start < 0) start = 0;
    }
    if (end < 0) {
        end = len+end;
        if (end < 0) end = 0;
    }
    newlen = (start > end) ? 0 : (end-start)+1;
    if (newlen != 0) {
        if (start >= (signed)len) {
            newlen = 0;
        } else if (end >= (signed)len) {
            end = len-1;
            newlen = (start > end) ? 0 : (end-start)+1;
        }
    } else {
        start = 0;
    }
    if (start && newlen) memmove(sh->buf, sh->buf+start, newlen);
    sh->buf[newlen] = 0;
    sh->free = sh->free+(sh->len-newlen);
    sh->len = newlen;
    return s;
}

//将s中的字符全变成小写
void sdstolower(sds s) {
    int len = sdslen(s), j;

    for (j = 0; j < len; j++) s[j] = tolower(s[j]);
}

//将s中的字符全变成大写
void sdstoupper(sds s) {
    int len = sdslen(s), j;

    for (j = 0; j < len; j++) s[j] = toupper(s[j]);
}

//比较两个字符串
int sdscmp(sds s1, 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 l1-l2;
    return cmp;
}

//使用sep串作为分隔符，将s串分割，将数量放到count变量，返回sds数组第一个元素的指针
/* 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(char *s, int len, char *sep, int seplen, int *count) {
    int elements = 0, slots = 5, start = 0, j;

    sds *tokens = zmalloc(sizeof(sds)*slots);
#ifdef SDS_ABORT_ON_OOM
    if (tokens == NULL) sdsOomAbort();
#endif
    if (seplen < 1 || len < 0 || 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) {
#ifdef SDS_ABORT_ON_OOM
                sdsOomAbort();
#else
                goto cleanup;
#endif
            }
            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) {
#ifdef SDS_ABORT_ON_OOM
                sdsOomAbort();
#else
                goto cleanup;
#endif
            }
            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) {
#ifdef SDS_ABORT_ON_OOM
                sdsOomAbort();
#else
                goto cleanup;
#endif
    }
    elements++;
    *count = elements;
    return tokens;

#ifndef SDS_ABORT_ON_OOM
cleanup:
    {
        int i;
        for (i = 0; i < elements; i++) sdsfree(tokens[i]);
        zfree(tokens);
        return NULL;
    }
#endif
}

//释放tokens的内存
void sdsfreesplitres(sds *tokens, int count) {
    if (!tokens) return;
    while(count--)
        sdsfree(tokens[count]);
    zfree(tokens);
}

//从long long转换成sds字符串
sds sdsfromlonglong(long long value) {
    char buf[32], *p;
    unsigned long long v;

    v = (value < 0) ? -value : value;
    p = buf+31; /* point to the last character */
    do {
        *p-- = '0'+(v%10);
        v /= 10;
    } while(v);
    if (value < 0) *p-- = '-';
    p++;
    return sdsnewlen(p,32-(p-buf));
}

//将p串接到s后边，保留转义符
sds sdscatrepr(sds s, 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",1); break;
        case '\r': s = sdscatlen(s,"\\r",1); break;
        case '\t': s = sdscatlen(s,"\\t",1); break;
        case '\a': s = sdscatlen(s,"\\a",1); break;
        case '\b': s = sdscatlen(s,"\\b",1); break;
        default:
            if (isprint(*p))
                s = sdscatprintf(s,"%c",*p);
            else
                s = sdscatprintf(s,"\\x%02x",(unsigned char)*p);
            break;
        }
        p++;
    }
    return sdscatlen(s,"\"",1);
}

//是否是十六进制数字
/* 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');
}

//十六进制字符转成十进制
/* Helper function for sdssplitargs() that converts an 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 sdsfree() all the returned
 * strings and finally zfree() the array itself.
 *
 * Note that sdscatrepr() is able to convert back a string into
 * a quoted string in the same format sdssplitargs() is able to parse.
 */
sds *sdssplitargs(char *line, int *argc) {
    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 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 */
                        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;
                    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 {
            return vector;
        }
    }

err:
    while((*argc)--)
        sdsfree(vector[*argc]);
    zfree(vector);
    if (current) sdsfree(current);
    return NULL;
}

#ifdef SDS_TEST_MAIN
#include <stdio.h>
#include "testhelp.h"

int main(void) {
    {
        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 = sdstrim(sdsnew("xxciaoyyy"),"xy");
        test_cond("sdstrim() correctly trims characters",
            sdslen(x) == 4 && memcmp(x,"ciao\0",5) == 0)

        y = sdsrange(sdsdup(x),1,1);
        test_cond("sdsrange(...,1,1)",
            sdslen(y) == 1 && memcmp(y,"i\0",2) == 0)

        sdsfree(y);
        y = sdsrange(sdsdup(x),1,-1);
        test_cond("sdsrange(...,1,-1)",
            sdslen(y) == 3 && memcmp(y,"iao\0",4) == 0)

        sdsfree(y);
        y = sdsrange(sdsdup(x),-2,-1);
        test_cond("sdsrange(...,-2,-1)",
            sdslen(y) == 2 && memcmp(y,"ao\0",3) == 0)

        sdsfree(y);
        y = sdsrange(sdsdup(x),2,1);
        test_cond("sdsrange(...,2,1)",
            sdslen(y) == 0 && memcmp(y,"\0",1) == 0)

        sdsfree(y);
        y = sdsrange(sdsdup(x),1,100);
        test_cond("sdsrange(...,1,100)",
            sdslen(y) == 3 && memcmp(y,"iao\0",4) == 0)

        sdsfree(y);
        y = sdsrange(sdsdup(x),100,100);
        test_cond("sdsrange(...,100,100)",
            sdslen(y) == 0 && memcmp(y,"\0",1) == 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)
    }
    test_report()
}
#endif

哦了，越看越费力，基础很差~路漫漫~加油