结合redis设计与实现的redis源码学习-26-工具函数（Util.h/.c）

Redis将很多的公用转换函数独立了出来，放入了Util.h中，包括字符串对比，内存转换，字符串数字转换，获取路径等，Redis的作者都是自己实现的，在这里我将这些函数认真学习，观察是在哪里高效并可以在之后的工作中使用。
因为Util的函数都是完全独立逻辑的，所以我在这里只看.c文件
Util.c

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include <limits.h>
#include <math.h>
#include <unistd.h>
#include <sys/time.h>
#include <float.h>
#include <stdint.h>
#include <errno.h>

#include "sha1.h"//Sha1校验算法的实现文件

/* Glob-style pattern matching. 全局风格的模式对比*/
int stringmatchlen(const char *pattern, int patternLen,
        const char *string, int stringLen, int nocase)
{
    while(patternLen) {
        switch(pattern[0]) {
        case '*'://当模式的第一个字符是*时
            while (pattern[1] == '*') {
                pattern++;//遍历模式字符串，查看模式到哪里不为*
                patternLen--;
            }
            if (patternLen == 1)
                return 1; /* match 如果直到最后都是*的话，那么就是完全匹配，*相当于通配符*/
            while(stringLen) {
                if (stringmatchlen(pattern+1, patternLen-1,
                            string, stringLen, nocase))
                    return 1; /* match 这里递归自己来判断后面的字符，666*/
                string++;//字符串的下一位
                stringLen--;
            }
            return 0; /* no match 如果到这里了，就没有匹配到，因为如果匹配的话前面和下面已经都匹配了*/
            break;
        case '?':
            if (stringLen == 0)
                return 0; /* no match 如果字符串长度是0，那么就不匹配了，因为模式是？*/
            string++;否则到string的下一个
            stringLen--;
            break;
        case '[':
        {
            int not, match;

            pattern++;//模式的下一位
            patternLen--;
            not = pattern[0] == '^';//这里用int来表示bool值，因为在C里没有bool
            if (not) {
                pattern++;//如果模式是^，匹配模式的下一位
                patternLen--;
            }
            match = 0;
            while(1) {
                if (pattern[0] == '\\') {//模式是\
                    pattern++;//匹配下一个
                    patternLen--;
                    if (pattern[0] == string[0])//如果模式等于字符，就是匹配
                        match = 1;
                } else if (pattern[0] == ']') {
                    break;
                } else if (patternLen == 0) {
                    pattern--;
                    patternLen++;
                    break;
                } else if (pattern[1] == '-' && patternLen >= 3) {
                    int start = pattern[0];
                    int end = pattern[2];
                    int c = string[0];
                    if (start > end) {
                        int t = start;
                        start = end;
                        end = t;
                    }
                    if (nocase) {
                        start = tolower(start);//全部变成小写字符
                        end = tolower(end);
                        c = tolower(c);
                    }
                    pattern += 2;
                    patternLen -= 2;
                    if (c >= start && c <= end)
                        match = 1;
                } else {
                    if (!nocase) {
                        if (pattern[0] == string[0])
                            match = 1;
                    } else {
                        if (tolower((int)pattern[0]) == tolower((int)string[0]))
                            match = 1;
                    }
                }
                pattern++;
                patternLen--;
            }
            if (not)
                match = !match;
            if (!match)
                return 0; /* no match */
            string++;
            stringLen--;
            break;
        }
        case '\\':
            if (patternLen >= 2) {
                pattern++;
                patternLen--;
            }
            /* fall through 接着执行下面的*/
        default:
            if (!nocase) {
                if (pattern[0] != string[0])
                    return 0; /* no match */
            } else {
                if (tolower((int)pattern[0]) != tolower((int)string[0]))
                    return 0; /* no match */
            }
            string++;
            stringLen--;
            break;
        }
        pattern++;
        patternLen--;
        if (stringLen == 0) {
            while(*pattern == '*') {
                pattern++;
                patternLen--;
            }
            break;
        }
    }
    if (patternLen == 0 && stringLen == 0)
        return 1;
    return 0;
}
int stringmatch(const char *pattern, const char *string, int nocase) {
    return stringmatchlen(pattern,strlen(pattern),string,strlen(string),nocase);
}
/* Convert a string representing an amount of memory into the number of bytes, so for instance memtoll("1Gb") will return 1073741824 that is (1024*1024*1024).转换一个字符串表示的内存到数字
 On parsing error, if *err is not NULL, it's set to 1, otherwise it's set to 0. On error the function return value is 0, regardless of the fact 'err' is NULL or not. */
 //这里是针对redis自己表示内存的方式来转换的，
long long memtoll(const char *p, int *err) {
    const char *u;
    char buf[128];
    long mul; /* unit multiplier */
    long long val;
    unsigned int digits;

    if (err) *err = 0;

    /* Search the first non digit character. 找到第一个非数字的符号*/
    u = p;
    if (*u == '-') u++;
    while(*u && isdigit(*u)) u++;
    if (*u == '\0' || !strcasecmp(u,"b")) {
        mul = 1;
    } else if (!strcasecmp(u,"k")) {
        mul = 1000;
    } else if (!strcasecmp(u,"kb")) {
        mul = 1024;
    } else if (!strcasecmp(u,"m")) {
        mul = 1000*1000;
    } else if (!strcasecmp(u,"mb")) {
        mul = 1024*1024;
    } else if (!strcasecmp(u,"g")) {
        mul = 1000L*1000*1000;
    } else if (!strcasecmp(u,"gb")) {
        mul = 1024L*1024*1024;
    } else {
        if (err) *err = 1;
        return 0;
    }

    /* Copy the digits into a buffer, we'll use strtoll() to convert the digit (without the unit) into a number. 将数字的字符复制到一个buffer中*/
    digits = u-p;
    if (digits >= sizeof(buf)) {
        if (err) *err = 1;
        return 0;
    }
    memcpy(buf,p,digits);
    buf[digits] = '\0';

    char *endptr;
    errno = 0;
    val = strtoll(buf,&endptr,10);
    if ((val == 0 && errno == EINVAL) || *endptr != '\0') {
        if (err) *err = 1;
        return 0;
    }
    return val*mul;
}

/* Return the number of digits of 'v' when converted to string in radix 10. See ll2string() for more information. 当以10进制转换为字符串时返回v*/
uint32_t digits10(uint64_t v) {
    if (v < 10) return 1;
    if (v < 100) return 2;
    if (v < 1000) return 3;
    if (v < 1000000000000UL) {
        if (v < 100000000UL) {
            if (v < 1000000) {
                if (v < 10000) return 4;
                return 5 + (v >= 100000);
            }
            return 7 + (v >= 10000000UL);
        }
        if (v < 10000000000UL) {
            return 9 + (v >= 1000000000UL);
        }
        return 11 + (v >= 100000000000UL);
    }
    return 12 + digits10(v / 1000000000000UL);
}

/* Like digits10() but for signed values. 类似于上面的函数但是支队标识值*/
uint32_t sdigits10(int64_t v) {
    if (v < 0) {
        /* Abs value of LLONG_MIN requires special handling. */
        uint64_t uv = (v != LLONG_MIN) ?
                      (uint64_t)-v : ((uint64_t) LLONG_MAX)+1;
        return digits10(uv)+1; /* +1 for the minus. */
    } else {
        return digits10(v);
    }
}

ll2string

/* Convert a long long into a string. Returns the number of characters needed to represent the number. If the buffer is not big enough to store the string, 0 is returned.将长整型转换为一个字符串，返回表示使用的字符串，如果缓冲区不足，返回0
 Based on the following article (that apparently does not provide a novel approach but only publicizes an already used technique):
 https://www.facebook.com/notes/facebook-engineering/three-optimization-tips-for-c/10151361643253920 Modified in order to handle signed integers since the original code was designed for unsigned integers. */
int ll2string(char* dst, size_t dstlen, long long svalue) {
    static const char digits[201] =
        "0001020304050607080910111213141516171819"
        "2021222324252627282930313233343536373839"
        "4041424344454647484950515253545556575859"
        "6061626364656667686970717273747576777879"
        "8081828384858687888990919293949596979899";
    int negative;
    unsigned long long value;

    /* The main loop works with 64bit unsigned integers for simplicity, so we convert the number here and remember if it is negative. 为了简单起见，主循环与64位无符号整数一起使用，所以我们在这里转换数字并记住它是否为负数*/
    if (svalue < 0) {
        if (svalue != LLONG_MIN) {
            value = -svalue;
        } else {
            value = ((unsigned long long) LLONG_MAX)+1;
        }
        negative = 1;
    } else {
        value = svalue;
        negative = 0;
    }

    /* Check length. */
    uint32_t const length = digits10(value)+negative;
    if (length >= dstlen) return 0;

    /* Null term. */
    uint32_t next = length;
    dst[next] = '\0';
    next--;
    while (value >= 100) {
        int const i = (value % 100) * 2;
        value /= 100;
        dst[next] = digits[i + 1];
        dst[next - 1] = digits[i];
        next -= 2;
    }

    /* Handle last 1-2 digits. */
    if (value < 10) {
        dst[next] = '0' + (uint32_t) value;
    } else {
        int i = (uint32_t) value * 2;
        dst[next] = digits[i + 1];
        dst[next - 1] = digits[i];
    }

    /* Add sign. */
    if (negative) dst[0] = '-';
    return length;
}

string2ll

/* Convert a string into a long long. Returns 1 if the string could be parsed
 * into a (non-overflowing) long long, 0 otherwise. The value will be set to
 * the parsed value when appropriate. */
int string2ll(const char *s, size_t slen, long long *value) {
    const char *p = s;
    size_t plen = 0;
    int negative = 0;
    unsigned long long v;

    if (plen == slen)
        return 0;

    /* Special case: first and only digit is 0. */
    if (slen == 1 && p[0] == '0') {
        if (value != NULL) *value = 0;
        return 1;
    }

    if (p[0] == '-') {
        negative = 1;
        p++; plen++;

        /* Abort on only a negative sign. */
        if (plen == slen)
            return 0;
    }

    /* First digit should be 1-9, otherwise the string should just be 0. */
    if (p[0] >= '1' && p[0] <= '9') {
        v = p[0]-'0';
        p++; plen++;
    } else if (p[0] == '0' && slen == 1) {
        *value = 0;
        return 1;
    } else {
        return 0;
    }

    while (plen < slen && p[0] >= '0' && p[0] <= '9') {
        if (v > (ULLONG_MAX / 10)) /* Overflow. */
            return 0;
        v *= 10;

        if (v > (ULLONG_MAX - (p[0]-'0'))) /* Overflow. */
            return 0;
        v += p[0]-'0';

        p++; plen++;
    }

    /* Return if not all bytes were used. */
    if (plen < slen)
        return 0;

    if (negative) {
        if (v > ((unsigned long long)(-(LLONG_MIN+1))+1)) /* Overflow. */
            return 0;
        if (value != NULL) *value = -v;
    } else {
        if (v > LLONG_MAX) /* Overflow. */
            return 0;
        if (value != NULL) *value = v;
    }
    return 1;
}

getrandomhexchar

/* Generate the Redis "Run ID", a SHA1-sized random number that identifies a given execution of Redis, so that if you are talking with an instance having run_id == A, and you reconnect and it has run_id == B, you can be sure that it is either a different instance or it was restarted. 生成redis运行id，这是一个sha1大小的随机数，用于标识给定的Redis执行情况*/
void getRandomHexChars(char *p, unsigned int len) {
    char *charset = "0123456789abcdef";
    unsigned int j;

    /* Global state. */
    static int seed_initialized = 0;
    static unsigned char seed[20]; /* The SHA1 seed, from /dev/urandom. */
    static uint64_t counter = 0; /* The counter we hash with the seed. */

    if (!seed_initialized) {
        /* Initialize a seed and use SHA1 in counter mode, where we hash the same seed with a progressive counter. For the goals of this function we just need non-colliding strings, there are no cryptographic security needs. 在计数器模式下初始化一个种子并使用SHA1，在那里我们用一个累进计数器对相同的种子进行哈希处理*/
        FILE *fp = fopen("/dev/urandom","r");
        if (fp && fread(seed,sizeof(seed),1,fp) == 1)
            seed_initialized = 1;
        if (fp) fclose(fp);
    }

    if (seed_initialized) {
        while(len) {
            unsigned char digest[20];
            SHA1_CTX ctx;
            unsigned int copylen = len > 20 ? 20 : len;

            SHA1Init(&ctx);
            SHA1Update(&ctx, seed, sizeof(seed));
            SHA1Update(&ctx, (unsigned char*)&counter,sizeof(counter));
            SHA1Final(digest, &ctx);
            counter++;

            memcpy(p,digest,copylen);
            /* Convert to hex digits. */
            for (j = 0; j < copylen; j++) p[j] = charset[p[j] & 0x0F];
            len -= copylen;
            p += copylen;
        }
    } else {
        /* If we can't read from /dev/urandom, do some reasonable effort in order to create some entropy, since this function is used to generate run_id and cluster instance IDs 如果我们不能正常读取数据，创建一些熵*/
        char *x = p;
        unsigned int l = len;
        struct timeval tv;
        pid_t pid = getpid();

        /* Use time and PID to fill the initial array. */
        gettimeofday(&tv,NULL);
        if (l >= sizeof(tv.tv_usec)) {
            memcpy(x,&tv.tv_usec,sizeof(tv.tv_usec));
            l -= sizeof(tv.tv_usec);
            x += sizeof(tv.tv_usec);
        }
        if (l >= sizeof(tv.tv_sec)) {
            memcpy(x,&tv.tv_sec,sizeof(tv.tv_sec));
            l -= sizeof(tv.tv_sec);
            x += sizeof(tv.tv_sec);
        }
        if (l >= sizeof(pid)) {
            memcpy(x,&pid,sizeof(pid));
            l -= sizeof(pid);
            x += sizeof(pid);
        }
        /* Finally xor it with rand() output, that was already seeded with time() at startup, and convert to hex digits. */
        for (j = 0; j < len; j++) {
            p[j] ^= rand();
            p[j] = charset[p[j] & 0x0F];
        }
    }
}

getabsolutepath

/* Given the filename, return the absolute path as an SDS string, or NULL
 * if it fails for some reason. Note that "filename" may be an absolute path
 * already, this will be detected and handled correctly.
 *
 * The function does not try to normalize everything, but only the obvious
 * case of one or more "../" appearning at the start of "filename"
 * relative path. */
sds getAbsolutePath(char *filename) {
    char cwd[1024];
    sds abspath;
    sds relpath = sdsnew(filename);

    relpath = sdstrim(relpath," \r\n\t");
    if (relpath[0] == '/') return relpath; /* Path is already absolute. */

    /* If path is relative, join cwd and relative path. */
    if (getcwd(cwd,sizeof(cwd)) == NULL) {
        sdsfree(relpath);
        return NULL;
    }
    abspath = sdsnew(cwd);
    if (sdslen(abspath) && abspath[sdslen(abspath)-1] != '/')
        abspath = sdscat(abspath,"/");

    /* At this point we have the current path always ending with "/", and
     * the trimmed relative path. Try to normalize the obvious case of
     * trailing ../ elements at the start of the path.
     *
     * For every "../" we find in the filename, we remove it and also remove
     * the last element of the cwd, unless the current cwd is "/". */
    while (sdslen(relpath) >= 3 &&
           relpath[0] == '.' && relpath[1] == '.' && relpath[2] == '/')
    {
        sdsrange(relpath,3,-1);
        if (sdslen(abspath) > 1) {
            char *p = abspath + sdslen(abspath)-2;
            int trimlen = 1;

            while(*p != '/') {
                p--;
                trimlen++;
            }
            sdsrange(abspath,0,-(trimlen+1));
        }
    }

    /* Finally glue the two parts together. */
    abspath = sdscatsds(abspath,relpath);
    sdsfree(relpath);
    return abspath;
}

/* Return true if the specified path is just a file basename without any
 * relative or absolute path. This function just checks that no / or \
 * character exists inside the specified path, that's enough in the
 * environments where Redis runs. */
int pathIsBaseName(char *path) {
    return strchr(path,'/') == NULL && strchr(path,'\\') == NULL;
}