Webbench源码分析之参数输入getopt_long（一）

概述：最近想看一些优秀的开源项目，然后知乎上找到一个列表，说可以看看webbench源码，总共代码也就500多行。所以就开始看开源代码webbench，这也算是笔记吧。今天主要看了参数输入部分，所以就详细了解了getopt_long函数的使用方法。

webbench.c的源码

/*
* (C) Radim Kolar 1997-2004
* This is free software, see GNU Public License version 2 for
* details.
*
* Simple forking WWW Server benchmark:
*
* Usage:
*   webbench --help
*
* Return codes:
*    0 - sucess
*    1 - benchmark failed (server is not on-line)
*    2 - bad param
*    3 - internal error, fork failed
* 
*/ 

#include "socket.c"
#include <unistd.h>
#include <sys/param.h>
#include <rpc/types.h>
#include <getopt.h>
#include <strings.h>
#include <time.h>
#include <signal.h>

/* values */
volatile int timerexpired=0;
int speed=0;
int failed=0;
int bytes=0;

/* globals */
int http10=1; /* 0 - http/0.9, 1 - http/1.0, 2 - http/1.1 */
/* Allow: GET, HEAD, OPTIONS, TRACE */
#define METHOD_GET 0
#define METHOD_HEAD 1
#define METHOD_OPTIONS 2
#define METHOD_TRACE 3
#define PROGRAM_VERSION "1.5"
int method=METHOD_GET;
int clients=1;
int force=0;
int force_reload=0;
int proxyport=80;
char *proxyhost=NULL;
int benchtime=30;

/* internal */
int mypipe[2];
char host[MAXHOSTNAMELEN];
#define REQUEST_SIZE 2048
char request[REQUEST_SIZE];

static const struct option long_options[]=
{
    {"force",no_argument,&force,1},
    {"reload",no_argument,&force_reload,1},
    {"time",required_argument,NULL,'t'},
    {"help",no_argument,NULL,'?'},
    {"http09",no_argument,NULL,'9'},
    {"http10",no_argument,NULL,'1'},
    {"http11",no_argument,NULL,'2'},
    {"get",no_argument,&method,METHOD_GET},
    {"head",no_argument,&method,METHOD_HEAD},
    {"options",no_argument,&method,METHOD_OPTIONS},
    {"trace",no_argument,&method,METHOD_TRACE},
    {"version",no_argument,NULL,'V'},
    {"proxy",required_argument,NULL,'p'},
    {"clients",required_argument,NULL,'c'},
    {NULL,0,NULL,0}
};

/* prototypes */
static void benchcore(const char* host,const int port, const char *request);
static int bench(void);
static void build_request(const char *url);

static void alarm_handler(int signal)
{
    timerexpired=1;
}   

static void usage(void)
{
    fprintf(stderr,
            "webbench [option]... URL\n"
            "  -f|--force               Don't wait for reply from server.\n"
            "  -r|--reload              Send reload request - Pragma: no-cache.\n"
            "  -t|--time <sec>          Run benchmark for <sec> seconds. Default 30.\n"
            "  -p|--proxy <server:port> Use proxy server for request.\n"
            "  -c|--clients <n>         Run <n> HTTP clients at once. Default one.\n"
            "  -9|--http09              Use HTTP/0.9 style requests.\n"
            "  -1|--http10              Use HTTP/1.0 protocol.\n"
            "  -2|--http11              Use HTTP/1.1 protocol.\n"
            "  --get                    Use GET request method.\n"
            "  --head                   Use HEAD request method.\n"
            "  --options                Use OPTIONS request method.\n"
            "  --trace                  Use TRACE request method.\n"
            "  -?|-h|--help             This information.\n"
            "  -V|--version             Display program version.\n"
           );
}

int main(int argc, char *argv[])
{
    int opt=0;
    int options_index=0;
    char *tmp=NULL;

    if(argc==1)
    {
        usage();
        return 2;
    } 

    while((opt=getopt_long(argc,argv,"912Vfrt:p:c:?h",long_options,&options_index))!=EOF )
    {
        switch(opt)
        {
            case  0 : break;
            case 'f': force=1;break;
            case 'r': force_reload=1;break; 
            case '9': http10=0;break;
            case '1': http10=1;break;
            case '2': http10=2;break;
            case 'V': printf(PROGRAM_VERSION"\n");exit(0);
            case 't': benchtime=atoi(optarg);break;      
            case 'p': 
            /* proxy server parsing server:port */
            tmp=strrchr(optarg,':');
            proxyhost=optarg;
            if(tmp==NULL)
            {
                break;
            }
            if(tmp==optarg)
            {
                fprintf(stderr,"Error in option --proxy %s: Missing hostname.\n",optarg);
                return 2;
            }
            if(tmp==optarg+strlen(optarg)-1)
            {
                fprintf(stderr,"Error in option --proxy %s Port number is missing.\n",optarg);
                return 2;
            }
            *tmp='\0';
            proxyport=atoi(tmp+1);
            break;
            case ':':
            case 'h':
            case '?': usage();return 2;break;
            case 'c': clients=atoi(optarg);break;
        }
    }

    if(optind==argc) {
        fprintf(stderr,"webbench: Missing URL!\n");
        usage();
        return 2;
    }

    if(clients==0) clients=1;
    if(benchtime==0) benchtime=30;

    /* Copyright */
    fprintf(stderr,"Webbench - Simple Web Benchmark "PROGRAM_VERSION"\n"
            "Copyright (c) Radim Kolar 1997-2004, GPL Open Source Software.\n"
            );

    build_request(argv[optind]);

    // print request info ,do it in function build_request
    /*printf("Benchmarking: ");

    switch(method)
    {
        case METHOD_GET:
        default:
        printf("GET");break;
        case METHOD_OPTIONS:
        printf("OPTIONS");break;
        case METHOD_HEAD:
        printf("HEAD");break;
        case METHOD_TRACE:
        printf("TRACE");break;
    }

    printf(" %s",argv[optind]);

    switch(http10)
    {
        case 0: printf(" (using HTTP/0.9)");break;
        case 2: printf(" (using HTTP/1.1)");break;
    }

    printf("\n");
    */

    printf("Runing info: ");

    if(clients==1) 
        printf("1 client");
    else
        printf("%d clients",clients);

    printf(", running %d sec", benchtime);

    if(force) printf(", early socket close");
    if(proxyhost!=NULL) printf(", via proxy server %s:%d",proxyhost,proxyport);
    if(force_reload) printf(", forcing reload");

    printf(".\n");

    return bench();
}

void build_request(const char *url)
{
    char tmp[10];
    int i;

    //bzero(host,MAXHOSTNAMELEN);
    //bzero(request,REQUEST_SIZE);
    memset(host,0,MAXHOSTNAMELEN);
    memset(request,0,REQUEST_SIZE);

    if(force_reload && proxyhost!=NULL && http10<1) http10=1;
    if(method==METHOD_HEAD && http10<1) http10=1;
    if(method==METHOD_OPTIONS && http10<2) http10=2;
    if(method==METHOD_TRACE && http10<2) http10=2;

    switch(method)
    {
        default:
        case METHOD_GET: strcpy(request,"GET");break;
        case METHOD_HEAD: strcpy(request,"HEAD");break;
        case METHOD_OPTIONS: strcpy(request,"OPTIONS");break;
        case METHOD_TRACE: strcpy(request,"TRACE");break;
    }

    strcat(request," ");

    if(NULL==strstr(url,"://"))
    {
        fprintf(stderr, "\n%s: is not a valid URL.\n",url);
        exit(2);
    }
    if(strlen(url)>1500)
    {
        fprintf(stderr,"URL is too long.\n");
        exit(2);
    }
    if (0!=strncasecmp("http://",url,7)) 
    { 
        fprintf(stderr,"\nOnly HTTP protocol is directly supported, set --proxy for others.\n");
        exit(2);
    }

    /* protocol/host delimiter */
    i=strstr(url,"://")-url+3;

    if(strchr(url+i,'/')==NULL) {
        fprintf(stderr,"\nInvalid URL syntax - hostname don't ends with '/'.\n");
        exit(2);
    }

    if(proxyhost==NULL)
    {
        /* get port from hostname */
        if(index(url+i,':')!=NULL && index(url+i,':')<index(url+i,'/'))
        {
            strncpy(host,url+i,strchr(url+i,':')-url-i);
            //bzero(tmp,10);
            memset(tmp,0,10);
            strncpy(tmp,index(url+i,':')+1,strchr(url+i,'/')-index(url+i,':')-1);
            /* printf("tmp=%s\n",tmp); */
            proxyport=atoi(tmp);
            if(proxyport==0) proxyport=80;
        } 
        else
        {
            strncpy(host,url+i,strcspn(url+i,"/"));
        }
        // printf("Host=%s\n",host);
        strcat(request+strlen(request),url+i+strcspn(url+i,"/"));
    } 
    else
    {
        // printf("ProxyHost=%s\nProxyPort=%d\n",proxyhost,proxyport);
        strcat(request,url);
    }

    if(http10==1)
        strcat(request," HTTP/1.0");
    else if (http10==2)
        strcat(request," HTTP/1.1");

    strcat(request,"\r\n");

    if(http10>0)
        strcat(request,"User-Agent: WebBench "PROGRAM_VERSION"\r\n");
    if(proxyhost==NULL && http10>0)
    {
        strcat(request,"Host: ");
        strcat(request,host);
        strcat(request,"\r\n");
    }

    if(force_reload && proxyhost!=NULL)
    {
        strcat(request,"Pragma: no-cache\r\n");
    }

    if(http10>1)
        strcat(request,"Connection: close\r\n");

    /* add empty line at end */
    if(http10>0) strcat(request,"\r\n"); 

    printf("\nRequest:\n%s\n",request);
}

/* vraci system rc error kod */
static int bench(void)
{
    int i,j,k;  
    pid_t pid=0;
    FILE *f;

    /* check avaibility of target server */
    i=Socket(proxyhost==NULL?host:proxyhost,proxyport);
    if(i<0) { 
        fprintf(stderr,"\nConnect to server failed. Aborting benchmark.\n");
        return 1;
    }
    close(i);

    /* create pipe */
    if(pipe(mypipe))
    {
        perror("pipe failed.");
        return 3;
    }

    /* not needed, since we have alarm() in childrens */
    /* wait 4 next system clock tick */
    /*
    cas=time(NULL);
    while(time(NULL)==cas)
    sched_yield();
    */

    /* fork childs */
    for(i=0;i<clients;i++)
    {
        pid=fork();
        if(pid <= (pid_t) 0)
        {
            /* child process or error*/
            sleep(1); /* make childs faster */
            break;
        }
    }

    if( pid < (pid_t) 0)
    {
        fprintf(stderr,"problems forking worker no. %d\n",i);
        perror("fork failed.");
        return 3;
    }

    if(pid == (pid_t) 0)
    {
        /* I am a child */
        if(proxyhost==NULL)
            benchcore(host,proxyport,request);
        else
            benchcore(proxyhost,proxyport,request);

        /* write results to pipe */
        f=fdopen(mypipe[1],"w");
        if(f==NULL)
        {
            perror("open pipe for writing failed.");
            return 3;
        }
        /* fprintf(stderr,"Child - %d %d\n",speed,failed); */
        fprintf(f,"%d %d %d\n",speed,failed,bytes);
        fclose(f);

        return 0;
    } 
    else
    {
        f=fdopen(mypipe[0],"r");
        if(f==NULL) 
        {
            perror("open pipe for reading failed.");
            return 3;
        }

        setvbuf(f,NULL,_IONBF,0);

        speed=0;
        failed=0;
        bytes=0;

        while(1)
        {
            pid=fscanf(f,"%d %d %d",&i,&j,&k);
            if(pid<2)
            {
                fprintf(stderr,"Some of our childrens died.\n");
                break;
            }

            speed+=i;
            failed+=j;
            bytes+=k;

            /* fprintf(stderr,"*Knock* %d %d read=%d\n",speed,failed,pid); */
            if(--clients==0) break;
        }

        fclose(f);

        printf("\nSpeed=%d pages/min, %d bytes/sec.\nRequests: %d susceed, %d failed.\n",
            (int)((speed+failed)/(benchtime/60.0f)),
            (int)(bytes/(float)benchtime),
            speed,
            failed);
    }

    return i;
}

void benchcore(const char *host,const int port,const char *req)
{
    int rlen;
    char buf[1500];
    int s,i;
    struct sigaction sa;

    /* setup alarm signal handler */
    sa.sa_handler=alarm_handler;
    sa.sa_flags=0;
    if(sigaction(SIGALRM,&sa,NULL))
        exit(3);

    alarm(benchtime); // after benchtime,then exit

    rlen=strlen(req);
    nexttry:while(1)
    {
        if(timerexpired)
        {
            if(failed>0)
            {
                /* fprintf(stderr,"Correcting failed by signal\n"); */
                failed--;
            }
            return;
        }

        s=Socket(host,port);                          
        if(s<0) { failed++;continue;} 
        if(rlen!=write(s,req,rlen)) {failed++;close(s);continue;}
        if(http10==0) 
        if(shutdown(s,1)) { failed++;close(s);continue;}
        if(force==0) 
        {
            /* read all available data from socket */
            while(1)
            {
                if(timerexpired) break; 
                i=read(s,buf,1500);
                /* fprintf(stderr,"%d\n",i); */
                if(i<0) 
                { 
                    failed++;
                    close(s);
                    goto nexttry;
                }
                else
                if(i==0) break;
                else
                bytes+=i;
            }
        }
        if(close(s)) {failed++;continue;}
        speed++;
    }
}

参数输入部分解析
对于执行程序，我们经常有各种选项配置，比如我们使用webbench时，执行如下命令。

$ webbench -c 10 -t 20 http://www.baidu.com/

其中-c -t 就是选项，后面的10 20 就是对应的参数，今天看了源码，发现这些参数的输入识别都是通过getopt_long()函数进行解析的。因为之前也没用过，所以就详细的把这里看了，记录下来。

getopt_long()函数使用方法
1，函数定义

int getopt_long (int argc, char *const *argv, const char *shortopts, const struct option *longopts, int *indexptr)

2，各项参数解析
argc：int main(int argc, char *argv[])的argc的值。
argv：char *argv[] 中argv的值。
shortopts：我们定义的短选项的值，如我们输入的-t -c都属于短选项。这个短选项的定义规则如下：

如 char *shortopts = "abc:t:?h"
1.单个字符，表示选项。
2.单个字符后接一个冒号：表示该选项后必须跟一个参数。参数紧跟在选项后或者以空格隔开。该参数的指针赋给optarg。
3.单个字符后跟两个冒号，表示该选项后必须跟一个参数。参数必须紧跟在选项后不能以空格隔开。该参数的指针赋给optarg。

我们使用的webbench -c 10 -t 20 中c就是一个选项，10就是对应的参数，会赋值给optarg。

longopts：这就是对应的长选项的一个结构体了，比如我们输入webbench –get 像–get就属于长选项了。那我们首先看一下struct option结构体的定义。

struct option {
    /*长选项名称*/
    const char *name;  
    /*标志位，表示后面是否有参数。有三个参数可选，no_argument, required_argument 和 optional_argument.，分别表示无参数，必须后跟参数，参数可有可无*/
    int has_arg;
    /*一个int指针，若不为空，会将val值赋给*flag，函数返回值为0.若为空，函数返回val值*/      
    int *flag;
    /*对应的长选项的值，通常是其对应的短选项字符*/
    int val;
};

定义此结构体时最后一定要以0填充结束。webbench中的定义如下：
static const struct option long_options[]=
{
    {"force",no_argument,&force,1},
    {"reload",no_argument,&force_reload,1},
    {"time",required_argument,NULL,'t'},
    {"help",no_argument,NULL,'?'},
    {"http09",no_argument,NULL,'9'},
    {"http10",no_argument,NULL,'1'},
    {"http11",no_argument,NULL,'2'},
    {"get",no_argument,&method,METHOD_GET},
    {"head",no_argument,&method,METHOD_HEAD},
    {"options",no_argument,&method,METHOD_OPTIONS},
    {"trace",no_argument,&method,METHOD_TRACE},
    {"version",no_argument,NULL,'V'},
    {"proxy",required_argument,NULL,'p'},
    {"clients",required_argument,NULL,'c'},
    {NULL,0,NULL,0}
};

indexptr：当我们使用的长选项时，我们可以通过这个返回的值，找出输入的对应长选项的名称。注意：此选项值只对输入的长选项有效。

3，注意事项

1，在我们使用getopt_long函数时，有两个参数optarg，optind。optarg容易理解，就是所对应选项的参数值，optind则是一个int型的数值，它则是代表第一个非定义选项的一个选项的位置，在后面的示例中详细说一下。
2，使用getopt_long函数后，argv的排序会改变，后面例子详说。
3，当输入选项与参数不对应，返回'?',在输入短选项时，shortopts起作用，当输入长选项时，longopts起作用。

webbench输入部分代码抠出来解析
下面是我抠出来的源代码，输入功能不变，只是单独拉出来，这样便于理解。

#include <getopt.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

/* globals */
int http10=1; /* 0 - http/0.9, 1 - http/1.0, 2 - http/1.1 */
/* Allow: GET, HEAD, OPTIONS, TRACE */
#define METHOD_GET 0
#define METHOD_HEAD 1
#define METHOD_OPTIONS 2
#define METHOD_TRACE 3
#define PROGRAM_VERSION "1.5"

int method=METHOD_GET;
int clients=1;
int force=0;
int force_reload=0;
int proxyport=80;
char *proxyhost=NULL;
int benchtime=30;

/*struct option一个结构体的定义赋值*/
static const struct option long_options[]=
{
    {"force",no_argument,&force,1},
    {"reload",no_argument,&force_reload,1},
    {"time",required_argument,NULL,'t'},
    {"help",no_argument,NULL,'?'},
    {"http09",no_argument,NULL,'9'},
    {"http10",no_argument,NULL,'1'},
    {"http11",no_argument,NULL,'2'},
    {"get",no_argument,&method,METHOD_GET},
    {"head",no_argument,&method,METHOD_HEAD},
    {"options",no_argument,&method,METHOD_OPTIONS},
    {"trace",no_argument,&method,METHOD_TRACE},
    {"version",no_argument,NULL,'V'},
    {"proxy",required_argument,NULL,'p'},
    {"clients",required_argument,NULL,'c'},
    {NULL,0,NULL,0}
};

/*各选项的具体解释及使用帮助信息*/
static void usage(void)
{
    fprintf(stderr,
            "webbench [option]... URL\n"
            "  -f|--force               Don't wait for reply from server.\n"
            "  -r|--reload              Send reload request - Pragma: no-cache.\n"
            "  -t|--time <sec>          Run benchmark for <sec> seconds. Default 30.\n"
            "  -p|--proxy <server:port> Use proxy server for request.\n"
            "  -c|--clients <n>         Run <n> HTTP clients at once. Default one.\n"
            "  -9|--http09              Use HTTP/0.9 style requests.\n"
            "  -1|--http10              Use HTTP/1.0 protocol.\n"
            "  -2|--http11              Use HTTP/1.1 protocol.\n"
            "  --get                    Use GET request method.\n"
            "  --head                   Use HEAD request method.\n"
            "  --options                Use OPTIONS request method.\n"
            "  --trace                  Use TRACE request method.\n"
            "  -?|-h|--help             This information.\n"
            "  -V|--version             Display program version.\n"
           );
}

int main(int argc, char *argv[])
{
  int opt=0;
  int options_index=0;
  char *tmp=NULL;

  if (1 == argc) {
    usage();
    return -1;
  }
  while((opt=getopt_long(argc,argv,"912Vfrt:p:c:?h",long_options,&options_index))!=EOF )
    {
        /*打印getopt_long的返回值*/
        if ( 0 != opt)
          printf("opt = %c\n", opt);
        switch(opt)
        {
            case  0 :
              /*如果是长选项，options_index值对应long_options[options_index].name表示的
              就是该长选项名称，因为这里长选项设置的都是flag指针不为空，所以都返回0*/
              printf("opt-name = %s\n",long_options[options_index].name);
              break;
            case 'f': force=1;break;
            case 'r': force_reload=1;break;
            case '9': http10=0;break;
            case '1': http10=1;break;
            case '2': http10=2;break;
            case 'V': printf(PROGRAM_VERSION"\n");exit(0);
            case 't': benchtime=atoi(optarg);break;
            case 'p':
            /*optarg 对应选项的参数值*/
            printf("case p:%s\n",optarg);
            /* proxy server parsing server:port */
            tmp=strrchr(optarg,':');
            proxyhost=optarg;
            if(tmp==NULL)
            {
                break;
            }
            if(tmp==optarg)
            {
                fprintf(stderr,"Error in option --proxy %s: Missing hostname.\n",optarg);
                return 2;
            }
            if(tmp==optarg+strlen(optarg)-1)
            {
                fprintf(stderr,"Error in option --proxy %s Port number is missing.\n",optarg);
                return 2;
            }
            *tmp='\0';
            proxyport=atoi(tmp+1);
            printf("server:%s,port:%d\n",proxyhost,proxyport);
            break;
            case ':':
            case 'h':
            case '?': usage();return 2;break;
            case 'c': clients=atoi(optarg);break;
        }

    }
    /*打印新的argv的排序*/
    printf("new argv sort: ");
    int i;
    for (i = 1; i < argc ; i ++) {
      printf("%s ", argv[i]);
    }
    printf("\n");
    /*打印optind值及对应的选项值，optind指向的是第一个非定义参数的值*/
    printf("optind = %d,argc = %d,optind_str = %s\n",optind, argc, argv[optind]);
    if(optind==argc) {
        fprintf(stderr,"webbench: Missing URL!\n");
        usage();
        return 2;
    }
    printf("url:%s\n",argv[optind]);
  return 0;
}

1，验证optind指向的是非定义选项的第一个选项值，且执行完getopt_long后argv会重新排序。执行如下指令。

$ ./getopt_long_test http://www.baidu.com/ -c 10 sky -t 20 

执行结果：

从结果中我们可以看到，argv输入的顺序，执行完后被重新排序了。同时optind对应的也是第一个非定义的选项中的第一个选项，如果我们把sky放在前面，那么输出就是sky。如图：

我们在使用webbench时最后加一个url地址，其实就是非定义选项的第一个，所以作者就是这样认为输入的是url。

2，验证optarg就是对应的输入参数，我们这里假设加上代理服务器参数。执行如下指令。

$ ./getopt_long_test -p 192.168.10.222:56  http://www.baidu.com/ 

执行结果如下：

可以看到我们输入的选项-p 对应的参数就是192.168.10.222:56。

3，验证输入长选项时，指针flag为空时返回val值，指针不为空时会赋值到flag并返回0值。

在我们的while循环后加上一句，之前也加上这一句。
 printf("method = %d\n",method);

执行结果如下：

我们可以看到，验证成功，method本来是0，我们用了–head选项，程序就将METHOD_HEAD值赋给了method。同时我们用了–http10，返回了对应的值’1’.

总结：
这里主要就是先把第一部分选项参数输入的部分搞懂了，其实也就是getopt_long（）函数的使用，因为没有用过，所以才这么详细的看了，这样看别的源码，有类似内容就可以省略不看啦。这算是个序吧，未完待续……….Peace&Love！

参考官方文档地址：getopt_long()