download.c

   1 /*
   2  * SARG Squid Analysis Report Generator      http://sarg.sourceforge.net
   3  *                                                            1998, 2010
   4  *
   5  * SARG donations:
   6  *      please look at http://sarg.sourceforge.net/donations.php
   7  * Support:
   8  *     http://sourceforge.net/projects/sarg/forums/forum/363374
   9  * ---------------------------------------------------------------------
  10  *
  11  *  This program is free software; you can redistribute it and/or modify
  12  *  it under the terms of the GNU General Public License as published by
  13  *  the Free Software Foundation; either version 2 of the License, or
  14  *  (at your option) any later version.
  15  *
  16  *  This program is distributed in the hope that it will be useful,
  17  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  18  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  19  *  GNU General Public License for more details.
  20  *
  21  *  You should have received a copy of the GNU General Public License
  22  *  along with this program; if not, write to the Free Software
  23  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111, USA.
  24  *
  25  */
  26
  27 #include "include/conf.h"
  28 #include "include/defs.h"
  29
  30 static char *DownloadSuffix=NULL;
  31 static char **DownloadSuffixIndex=NULL;
  32 static int NDownloadSuffix=0;
  33
  34 void download_report(void)
  35 {
  36
  37    FILE *fp_in = NULL, *fp_ou = NULL;
  38
  39    char *buf;
  40    char *url;
  41    char report_in[MAXLEN];
  42    char wdirname[MAXLEN];
  43    char report[MAXLEN];
  44    char period[100];
  45    char ip[MAXLEN];
  46    char oip[MAXLEN];
  47    char user[MAXLEN];
  48    char ouser[MAXLEN];
  49    char ouser2[MAXLEN];
  50    char data[15];
  51    char hora[15];
  52    int  z=0;
  53    int  count=0;
  54    int i;
  55    int new_user;
  56    struct getwordstruct gwarea;
  57    struct longlinestruct line;
  58    struct userinfostruct *uinfo;
  59
  60    ouser[0]='\0';
  61    ouser2[0]='\0';
  62
  63    sprintf(report_in,"%s/sarg/download.log",TempDir);
  64    if(access(report_in, R_OK) != 0)
  65       return;
  66
  67    strcpy(wdirname,outdirname);
  68    sprintf(report,"%s/download.html",wdirname);
  69    strcat(wdirname,"/");
  70    strcat(wdirname,"sarg-period");
  71
  72    if ((fp_in = fopen(wdirname, "r")) == 0) {
  73       debuga(_("(download) Cannot open file: %s\n"),wdirname);
  74       exit(1);
  75    }
  76
  77    if (!fgets(period,sizeof(period),fp_in)) {
  78       debuga(_("(download) read error in %s\n"),wdirname);
  79       exit(1);
  80    }
  81    fclose(fp_in);
  82
  83    if((fp_in=MY_FOPEN(report_in,"r"))==NULL) {
  84      fprintf(stderr, "SARG: (download) %s: %s\n",_("Cannot open log file"),report_in);
  85      exit(1);
  86    }
  87
  88    if((fp_ou=MY_FOPEN(report,"w"))==NULL) {
  89      fprintf(stderr, "SARG: (download) %s: %s\n",_("Cannot open log file"),report);
  90      exit(1);
  91    }
  92
  93    write_html_header(fp_ou,(IndexTree == INDEX_TREE_DATE) ? 3 : 1,_("Downloads"));
  94    fprintf(fp_ou,"<tr><td class=\"header_l\">%s: %s</td></tr>\n",_("Period"),period);
  95    fprintf(fp_ou,"<tr><th class=\"header_c\">%s</th></tr>\n",_("Downloads"));
  96    close_html_header(fp_ou);
  97
  98    fputs("<div class=\"report\"><table cellpadding=\"0\" cellspacing=\"2\">\n",fp_ou);
  99    fputs("<tr><td></td></tr>\n",fp_ou);
 100    fprintf(fp_ou,"<tr><th class=\"header_l\">%s</th><th class=\"header_l\">%s</th><th class=\"header_l\">%s</th><th class=\"header_l\">%s</th></tr>\n",_("USERID"),_("IP/NAME"),_("DATE/TIME"),_("ACCESSED SITE"));
 101
 102    if (longline_prepare(&line)<0) {
 103       debuga(_("Not enough memory to read the downloaded files\n"));
 104       exit(1);
 105    }
 106
 107    while((buf=longline_read(fp_in,&line))!=NULL) {
 108       getword_start(&gwarea,buf);
 109       if (getword(data,sizeof(data),&gwarea,'\t')<0 || getword(hora,sizeof(hora),&gwarea,'\t')<0 ||
 110           getword(user,sizeof(user),&gwarea,'\t')<0 || getword(ip,sizeof(ip),&gwarea,'\t')<0) {
 111          debuga(_("There is a broken record or garbage in file %s\n"),report_in);
 112          exit(1);
 113       }
 114       if (getword_ptr(buf,&url,&gwarea,'\t')<0) {
 115          debuga(_("There is a broken url in file %s\n"),report_in);
 116          exit(1);
 117       }
 118
 119       uinfo=userinfo_find_from_id(user);
 120       if (!uinfo) {
 121          debuga(_("Unknown user ID %s in file %s\n"),user,report_in);
 122          exit(1);
 123       }
 124       new_user=0;
 125       if(!z) {
 126          strcpy(ouser,user);
 127          strcpy(oip,ip);
 128          z++;
 129          new_user=1;
 130       } else {
 131          if(strcmp(ouser,user) != 0) {
 132             strcpy(ouser,user);
 133             new_user=1;
 134          }
 135          if(strcmp(oip,ip) != 0) {
 136             strcpy(oip,ip);
 137             new_user=1;
 138          }
 139       }
 140
 141       if(DownloadReportLimit) {
 142          if(strcmp(ouser2,uinfo->label) == 0) {
 143             count++;
 144          } else {
 145             count=1;
 146             strcpy(ouser2,uinfo->label);
 147          }
 148          if(count >= DownloadReportLimit)
 149             continue;
 150       }
 151
 152       for (i=strlen(url)-1 ; i>=0 && (unsigned char)url[i]<' ' ; i--) url[i]=0;
 153
 154       fputs("<tr>",fp_ou);
 155       if (new_user)
 156          fprintf(fp_ou,"<td class=\"data\">%s</td><td class=\"data\">%s</td>",uinfo->label,ip);
 157       else
 158          fputs("<td class=\"data\"></td><td class=\"data\"></td>",fp_ou);
 159       fprintf(fp_ou,"<td class=\"data\">%s-%s</td><td class=\"data2\">",data,hora);
 160       if(BlockIt[0]!='\0') {
 161          fprintf(fp_ou,"<a href=\"%s%s?url=\"",wwwDocumentRoot,BlockIt);
 162          output_html_url(fp_ou,url);
 163          fprintf(fp_ou,"\"><img src=\"%s/sarg-squidguard-block.png\"></a>&nbsp;",ImageFile);
 164       }
 165       fputs("<a href=\"http://",fp_ou);
 166       output_html_url(fp_ou,url);
 167       fputs("\">http://",fp_ou);
 168       output_html_string(fp_ou,url,100);
 169       fputs("</a></td></tr>\n",fp_ou);
 170    }
 171    fclose(fp_in);
 172    longline_free(&line);
 173
 174    fputs("</table></div>\n",fp_ou);
 175    write_html_trailer(fp_ou);
 176    fclose(fp_ou);
 177
 178    unlink(report_in);
 179
 180    return;
 181 }
 182
 183 void free_download(void)
 184 {
 185    if (DownloadSuffix) {
 186       free(DownloadSuffix);
 187       DownloadSuffix=NULL;
 188    }
 189    if (DownloadSuffixIndex) {
 190       free(DownloadSuffixIndex);
 191       DownloadSuffixIndex=NULL;
 192    }
 193    NDownloadSuffix=0;
 194 }
 195
 196 void set_download_suffix(const char *list)
 197 {
 198    char *str;
 199    int i, j, k;
 200    int cmp;
 201
 202    free_download();
 203
 204    DownloadSuffix=strdup(list);
 205    if (!DownloadSuffix) {
 206       fprintf(stderr,"SARG: Download suffix list too long\n");
 207       exit(1);
 208    }
 209    j = 1;
 210    for (i=0 ; list[i] ; i++)
 211       if (list[i] == ',') j++;
 212    DownloadSuffixIndex=malloc(j*sizeof(char *));
 213    if (!DownloadSuffixIndex) {
 214       fprintf(stderr,"SARG: Too many download suffixes\n");
 215       exit(1);
 216    }
 217
 218    str = DownloadSuffix;
 219    for (i=0 ; DownloadSuffix[i] ; i++) {
 220       if (DownloadSuffix[i] == ',') {
 221          DownloadSuffix[i] = '\0';
 222          if (*str) {
 223             cmp = -1;
 224             for (j=0 ; j<NDownloadSuffix && (cmp=strcasecmp(str,DownloadSuffixIndex[j]))>0 ; j++);
 225             if (cmp != 0) {
 226                for (k=NDownloadSuffix ; k>j ; k--)
 227                   DownloadSuffixIndex[k]=DownloadSuffixIndex[k-1];
 228                NDownloadSuffix++;
 229                DownloadSuffixIndex[j]=str;
 230             }
 231          }
 232          str=DownloadSuffix+i+1;
 233       }
 234    }
 235
 236    if (*str) {
 237       cmp = -1;
 238       for (j=0 ; j<NDownloadSuffix && (cmp=strcasecmp(str,DownloadSuffixIndex[j]))>0 ; j++);
 239       if (cmp != 0) {
 240          for (k=NDownloadSuffix ; k>j ; k--)
 241             DownloadSuffixIndex[k]=DownloadSuffixIndex[k-1];
 242          NDownloadSuffix++;
 243          DownloadSuffixIndex[j]=str;
 244       }
 245    }
 246 }
 247
 248 int is_download_suffix(const char *url)
 249 {
 250    int urllen;
 251    int i;
 252    int down, up, center;
 253    const char *suffix;
 254    int cmp;
 255    const int max_suffix=10;
 256
 257    if (DownloadSuffix == NULL || NDownloadSuffix == 0) return(0);
 258
 259    urllen=strlen(url)-1;
 260    if (urllen<=0) return(0);
 261    if (url[urllen] == '.') return(0); //reject a single trailing dot
 262    for (i=0 ; i<urllen && (url[i]!='/' || url[i+1]=='/') && url[i]!='?' ; i++);
 263    if (i>=urllen) return(0); // url is a hostname without any path or file to download
 264
 265    for (i=0 ; i<=max_suffix && i<urllen && url[urllen-i]!='.' ; i++)
 266       if (url[urllen-i] == '/' || url[urllen-i] == '?') return(0);
 267    if (i>max_suffix || i>=urllen) return(0);
 268
 269    suffix=url+urllen-i+1;
 270    down=0;
 271    up=NDownloadSuffix-1;
 272    while (down<=up) {
 273       center=(down+up)/2;
 274       cmp=strcasecmp(suffix,DownloadSuffixIndex[center]);
 275       if (cmp == 0) return(1);
 276       if (cmp < 0)
 277          up = center-1;
 278       else
 279          down = center+1;
 280    }
 281    return(0);
 282 }
 283