webalizer.c

来自「统计日志的工具」· C语言 代码 · 共 1,572 行 · 第 1/5 页

               if (cur_month != rec_month)
               {
                  clear_month();
                  cur_sec   = rec_sec;          /* set current counters     */
                  cur_min   = rec_min;
                  cur_hour  = rec_hour;
                  cur_day   = rec_day;
                  cur_month = rec_month;
                  cur_year  = rec_year;
                  cur_tstamp= rec_tstamp;
                  f_day=l_day=rec_day;          /* reset first and last day */
               }
            }
         }

         /* check for out of sequence records */
         if (rec_tstamp/3600 < cur_tstamp/3600)
         {
            if (!fold_seq_err && ((rec_tstamp+SLOP_VAL)/3600<cur_tstamp/3600) )
               { total_ignore++; continue; }
            else
            {
               rec_sec   = cur_sec;             /* if folding sequence      */
               rec_min   = cur_min;             /* errors, just make it     */
               rec_hour  = cur_hour;            /* look like the last       */
               rec_day   = cur_day;             /* good records timestamp   */
               rec_month = cur_month;
               rec_year  = cur_year;
               rec_tstamp= cur_tstamp;
            }
         }
         cur_tstamp=rec_tstamp;                 /* update current timestamp */

         /*********************************************/
         /* DO SOME PRE-PROCESS FORMATTING            */
         /*********************************************/

         /* fix URL field */
         cp1 = cp2 = log_rec.url;
         /* handle null '-' case here... */
         if (*++cp1 == '-') { *cp2++ = '-'; *cp2 = '\0'; }
         else
         {
            /* strip actual URL out of request */
            while  ( (*cp1 != ' ') && (*cp1 != '\0') ) cp1++;
            if (*cp1 != '\0')
            {
               /* scan to begin of actual URL field */
               while ((*cp1 == ' ') && (*cp1 != '\0')) cp1++;
               /* remove duplicate / if needed */
               if (( *cp1=='/') && (*(cp1+1)=='/')) cp1++;
               while ((*cp1 != ' ')&&(*cp1 != '"')&&(*cp1 != '\0'))
                  *cp2++ = *cp1++;
               *cp2 = '\0';
            }
         }

         /* un-escape URL */
         unescape(log_rec.url);

         /* check for service (ie: http://) and lowercase if found */
         if ( (cp2=strstr(log_rec.url,"://")) != NULL)
         {
            cp1=log_rec.url;
            while (cp1!=cp2)
            {
               if ( (*cp1>='A') && (*cp1<='Z')) *cp1 += 'a'-'A';
               cp1++;
            }
         }

         /* strip query portion of cgi scripts */
         cp1 = log_rec.url;
         while (*cp1 != '\0')
           if (!isurlchar(*cp1)) { *cp1 = '\0'; break; }
           else cp1++;
         if (log_rec.url[0]=='\0')
           { log_rec.url[0]='/'; log_rec.url[1]='\0'; }

         /* strip off index.html (or any aliases) */
         lptr=index_alias;
         while (lptr!=NULL)
         {
            if ((cp1=strstr(log_rec.url,lptr->string))!=NULL)
            {
               if ((cp1==log_rec.url)||(*(cp1-1)=='/'))
               {
                  *cp1='\0';
                  if (log_rec.url[0]=='\0')
                   { log_rec.url[0]='/'; log_rec.url[1]='\0'; }
                  break;
               }
            }
            lptr=lptr->next;
         }

         /* unescape referrer */
         unescape(log_rec.refer);

         /* fix referrer field */
         cp1 = log_rec.refer;
         cp3 = cp2 = cp1++;
         if ( (*cp2 != '\0') && (*cp2 == '"') )
         {
            while ( *cp1 != '\0' )
            {
               cp3=cp2;
               if ((*cp1<32&&*cp1>0) || *cp1==127 || *cp1=='<') *cp1=0;
               else *cp2++=*cp1++;
            }
            *cp3 = '\0';
         }

         /* strip query portion of cgi referrals */
         cp1 = log_rec.refer;
         if (*cp1 != '\0')
         {
            while (*cp1 != '\0')
            {
               if (!isurlchar(*cp1))
               {
                  /* Save query portion in log.rec.srchstr */
                  strncpy(log_rec.srchstr,cp1,MAXSRCH);
                  *cp1++='\0';
                  break;
               }
               else cp1++;
            }
            /* handle null referrer */
            if (log_rec.refer[0]=='\0')
              { log_rec.refer[0]='-'; log_rec.refer[1]='\0'; }
         }

         /* if HTTP request, lowercase http://sitename/ portion */
         cp1 = log_rec.refer;
         if ( (*cp1=='h') || (*cp1=='H'))
         {
            while ( (*cp1!='/') && (*cp1!='\0'))
            {
               if ( (*cp1>='A') && (*cp1<='Z')) *cp1 += 'a'-'A';
               cp1++;
            }
            /* now do hostname */
            if ( (*cp1=='/') && ( *(cp1+1)=='/')) {cp1++; cp1++;}
            while ( (*cp1!='/') && (*cp1!='\0'))
            {
               if ( (*cp1>='A') && (*cp1<='Z')) *cp1 += 'a'-'A';
               cp1++;
            }
         }

         /* Do we need to mangle? */
         if (mangle_agent)
         {
            str=cp2=log_rec.agent;
	    cp1=strstr(str,"ompatible"); /* check known fakers */
	    if (cp1!=NULL) {
		while (*cp1!=';'&&*cp1!='\0') cp1++;
		/* kludge for Mozilla/3.01 (compatible;) */
		if (*cp1++==';' && strcmp(cp1,")\"")) { /* success! */
		    while (*cp1 == ' ') cp1++; /* eat spaces */
		    while (*cp1!='.'&&*cp1!='\0'&&*cp1!=';') *cp2++=*cp1++;
		    if (mangle_agent<5)
		    {
			while (*cp1!='.'&&*cp1!=';'&&*cp1!='\0') *cp2++=*cp1++;
			if (*cp1!=';'&&*cp1!='\0') {
			    *cp2++=*cp1++;
			    *cp2++=*cp1++;
			}
		    }
		    if (mangle_agent<4)
			if (*cp1>='0'&&*cp1<='9') *cp2++=*cp1++;
		    if (mangle_agent<3)
			while (*cp1!=';'&&*cp1!='\0'&&*cp1!='(') *cp2++=*cp1++;
		    if (mangle_agent<2)
		    {
			/* Level 1 - try to get OS */
			cp1=strstr(str,")");
			if (cp1!=NULL)
			{
			    *cp2++=' ';
			    *cp2++='(';
			    while (*cp1!=';'&&*cp1!='('&&cp1!=str) cp1--;
			    if (cp1!=str&&*cp1!='\0') cp1++;
			    while (*cp1==' '&&*cp1!='\0') cp1++;
			    while (*cp1!=')'&&*cp1!='\0') *cp2++=*cp1++;
			    *cp2++=')';
			}
		    }
		    *cp2='\0';
		} else { /* nothing after "compatible", should we mangle? */
		    /* not for now */
		}
	    } else {
		cp1=strstr(str,"Opera");  /* Opera flavor         */
		if (cp1!=NULL)
		{
		    while (*cp1!='/'&&*cp1!=' '&&*cp1!='\0') *cp2++=*cp1++;
		    while (*cp1!='.'&&*cp1!='\0') *cp2++=*cp1++;
		    if (mangle_agent<5)
		    {
			while (*cp1!='.'&&*cp1!='\0') *cp2++=*cp1++;
			*cp2++=*cp1++;
			*cp2++=*cp1++;
		    }
		    if (mangle_agent<4)
			if (*cp1>='0'&&*cp1<='9') *cp2++=*cp1++;
		    if (mangle_agent<3)
			while (*cp1!=' '&&*cp1!='\0'&&*cp1!='(') 
			    *cp2++=*cp1++;
		    if (mangle_agent<2)
		    {
			cp1=strstr(str,"(");
			if (cp1!=NULL)
			{
			    cp1++;
			    *cp2++=' ';
			    *cp2++='(';
			    while (*cp1!=';'&&*cp1!=')'&&*cp1!='\0') 
				*cp2++=*cp1++;
			    *cp2++=')';
			}
		    }
		    *cp2='\0';
		} else { 
		    cp1=strstr(str,"Mozilla");  /* Netscape flavor      */
		    if (cp1!=NULL)
		    {
			while (*cp1!='/'&&*cp1!=' '&&*cp1!='\0') *cp2++=*cp1++;
			if (*cp1==' ') *cp1='/';
			while (*cp1!='.'&&*cp1!='\0') *cp2++=*cp1++;
			if (mangle_agent<5)
			{
			    while (*cp1!='.'&&*cp1!='\0') *cp2++=*cp1++;
			    *cp2++=*cp1++;
			    *cp2++=*cp1++;
			}
			if (mangle_agent<4)
			    if (*cp1>='0'&&*cp1<='9') *cp2++=*cp1++;
			if (mangle_agent<3)
			    while (*cp1!=' '&&*cp1!='\0'&&*cp1!='(') 
				*cp2++=*cp1++;
			if (mangle_agent<2)
			{
			    /* Level 1 - Try to get OS */
			    cp1=strstr(str,"(");
			    if (cp1!=NULL)
			    {
				cp1++;
				*cp2++=' ';
				*cp2++='(';
				while (*cp1!=';'&&*cp1!=')'&&*cp1!='\0') 
				    *cp2++=*cp1++;
				*cp2++=')';
			    }
			}
			*cp2='\0';
		    }
		}
	    }
	 }

         /* if necessary, shrink referrer to fit storage */
         if (strlen(log_rec.refer)>=MAXREFH)
         {
            if (verbose) fprintf(stderr,"%s [%lu]\n",
                msg_big_ref,total_rec);
            log_rec.refer[MAXREFH-1]='\0';
         }

         /* if necessary, shrink URL to fit storage */
         if (strlen(log_rec.url)>=MAXURLH)
         {
            if (verbose) fprintf(stderr,"%s [%lu]\n",
                msg_big_req,total_rec);
            log_rec.url[MAXURLH-1]='\0';
         }

         /* fix user agent field */
         cp1 = log_rec.agent;
         cp3 = cp2 = cp1++;
         if ( (*cp2 != '\0') && ((*cp2 == '"')||(*cp2 == '(')) )
         {
            while (*cp1 |= '\0') { cp3 = cp2; *cp2++ = *cp1++; }
            *cp3 = '\0';
         }
         cp1 = log_rec.agent;    /* CHANGE !!! */
         while (*cp1 != 0)       /* get rid of more common _bad_ chars ;)   */
         {
            if ( (*cp1 < 32) || (*cp1==127) || (*cp1=='<') || (*cp1=='>') )
               { *cp1='\0'; break; }
            else cp1++;
         }

         /* fix username if needed */
         if (log_rec.ident[0]==0)
          {  log_rec.ident[0]='-'; log_rec.ident[1]='\0'; }
         else
         {
            cp3=log_rec.ident;
            while (*cp3>=32 && *cp3!='"') cp3++;
            *cp3='\0';
         }
         /* unescape user name */
         unescape(log_rec.ident);

         /********************************************/
         /* PROCESS RECORD                           */
         /********************************************/

         /* first time through? */
         if (cur_month == 0)
         {
             /* if yes, init our date vars */
             cur_month=rec_month; cur_year=rec_year;