Webalizer+GeoIP

9 files changed, 322 insertions, 0 deletions

diff --git a/www/geolizer/Makefile b/www/geolizer/Makefile
new file mode 100644
index 000000000000..5286f47bef56
--- /dev/null
+++ b/www/geolizer/Makefile
@@ -0,0 +1,42 @@
+# New ports collection makefile for:    geolizer
+# Date created:         23 July 2004
+# Whom:                 ache@FreeBSD.org
+#
+# $FreeBSD$
+#
+
+CONFLICTS=	webalizer-2*
+
+MASTERDIR=      ${.CURDIR}/../webalizer
+
+PATCH_SITES+=	http://sysd.org/proj/
+PATCHFILES+=	geolizer_2.01-10-patch.20040216.tar.bz2
+PATCH_DIST_STRIP= -p1
+PATCHDIR=	${.CURDIR}/files
+MD5_FILE=	${.CURDIR}/distinfo
+DESCR=		${.CURDIR}/pkg-descr
+DOCSDIR=	${PREFIX}/share/doc/webalizer
+EXAMPLESDIR=	${PREFIX}/share/examples/webalizer
+
+WEBALIZER_LANG=english
+
+CFLAGS+= -I${LOCALBASE}/include
+CONFIGURE_ARGS+= --enable-geoip \
+		--with-geoip-lib=${LOCALBASE} \
+		--with-geoip-inc=${LOCALBASE}
+
+LIB_DEPENDS=    gd.4:${PORTSDIR}/graphics/gd \
+		GeoIP.4:${PORTSDIR}/net/GeoIP
+
+MAINTAINER=	ports@FreeBSD.org
+
+.include "${MASTERDIR}/Makefile"
+
+# Overwrite section, can't be placed before
+
+PORTNAME=	geolizer
+PORTREVISION=	0
+DISTNAME=       webalizer-2.01-10-src
+
+COMMENT=	A web server log file analysis program, using GeoIP library
+
diff --git a/www/geolizer/distinfo b/www/geolizer/distinfo
new file mode 100644
index 000000000000..f1df75ba561f
--- /dev/null
+++ b/www/geolizer/distinfo
@@ -0,0 +1,4 @@
+MD5 (webalizer-2.01-10-src.tar.bz2) = 26d0a3c142423678daed2d6f579525d8
+SIZE (webalizer-2.01-10-src.tar.bz2) = 252664
+MD5 (geolizer_2.01-10-patch.20040216.tar.bz2) = fa2e960702c72a16707854537053a966
+SIZE (geolizer_2.01-10-patch.20040216.tar.bz2) = 27688
diff --git a/www/geolizer/files/patch-aa b/www/geolizer/files/patch-aa
new file mode 100644
index 000000000000..37e6eb36db24
--- /dev/null
+++ b/www/geolizer/files/patch-aa
@@ -0,0 +1,17 @@
+--- linklist.c.bak	Fri Sep 29 07:51:02 2000
++++ linklist.c	Sat Oct 14 17:22:16 2000
+@@ -197,12 +197,12 @@
+    strncpy(temp_buf,str,79);
+    temp_buf[79]=0;
+ 
+-   while (!isspace((int)*name)&&*name!=0) name++;
++   while (!isspace((unsigned char)*name)&&*name!=0) name++;
+    if (*name==0) name=temp_buf;
+    else
+    {
+       *name++=0;
+-      while (isspace((int)*name)&&*name!=0) name++;
++      while (isspace((unsigned char)*name)&&*name!=0) name++;
+       if (*name==0) name=temp_buf;
+    }
+ 
diff --git a/www/geolizer/files/patch-ab b/www/geolizer/files/patch-ab
new file mode 100644
index 000000000000..f8f53e94cdc3
--- /dev/null
+++ b/www/geolizer/files/patch-ab
@@ -0,0 +1,65 @@
+--- preserve.c.bak	Fri Sep 29 07:51:32 2000
++++ preserve.c	Sat Oct 14 17:34:03 2000
+@@ -492,7 +492,7 @@
+       tmp_buf[strlen(tmp_buf)-1]=0;
+ 
+       if ((fgets(buffer,BUFSIZE,fp)) == NULL) return 10;  /* error exit */
+-      if (!isdigit((int)buffer[0])) return 10;  /* error exit */
++      if (!isdigit((unsigned char)buffer[0])) return 10;  /* error exit */
+ 
+       /* load temporary node data */
+       sscanf(buffer,"%d %lu %lu %lf %lu %lu",
+@@ -523,7 +523,7 @@
+       tmp_buf[strlen(buffer)-1]=0;
+ 
+       if ((fgets(buffer,BUFSIZE,fp)) == NULL) return 8;  /* error exit */
+-      if (!isdigit((int)buffer[0])) return 8;  /* error exit */
++      if (!isdigit((unsigned char)buffer[0])) return 8;  /* error exit */
+ 
+       /* load temporary node data */
+       sscanf(buffer,"%d %lu %lu %lf %lu %lu",
+@@ -563,7 +563,7 @@
+       tmp_buf[strlen(buffer)-1]=0;
+ 
+       if ((fgets(buffer,BUFSIZE,fp)) == NULL) return 9;  /* error exit */
+-      if (!isdigit((int)buffer[0])) return 9;  /* error exit */
++      if (!isdigit((unsigned char)buffer[0])) return 9;  /* error exit */
+ 
+       /* load temporary node data */
+       sscanf(buffer,"%d %lu %lu %lf %lu %lu",
+@@ -602,7 +602,7 @@
+       tmp_buf[strlen(buffer)-1]=0;
+ 
+       if ((fgets(buffer,BUFSIZE,fp)) == NULL) return 11;  /* error exit */
+-      if (!isdigit((int)buffer[0])) return 11;  /* error exit */
++      if (!isdigit((unsigned char)buffer[0])) return 11;  /* error exit */
+ 
+       /* load temporary node data */
+       sscanf(buffer,"%d %lu",&t_rnode.flag,&t_rnode.count);
+@@ -627,7 +627,7 @@
+       tmp_buf[strlen(buffer)-1]=0;
+ 
+       if ((fgets(buffer,BUFSIZE,fp)) == NULL) return 12;  /* error exit */
+-      if (!isdigit((int)buffer[0])) return 12;  /* error exit */
++      if (!isdigit((unsigned char)buffer[0])) return 12;  /* error exit */
+ 
+       /* load temporary node data */
+       sscanf(buffer,"%d %lu",&t_anode.flag,&t_anode.count);
+@@ -652,7 +652,7 @@
+       tmp_buf[strlen(buffer)-1]=0;
+ 
+       if ((fgets(buffer,BUFSIZE,fp)) == NULL) return 13;  /* error exit */
+-      if (!isdigit((int)buffer[0])) return 13;  /* error exit */
++      if (!isdigit((unsigned char)buffer[0])) return 13;  /* error exit */
+ 
+       /* load temporary node data */
+       sscanf(buffer,"%lu",&t_snode.count);
+@@ -677,7 +677,7 @@
+       tmp_buf[strlen(buffer)-1]=0;
+ 
+       if ((fgets(buffer,BUFSIZE,fp)) == NULL) return 14;  /* error exit */
+-      if (!isdigit((int)buffer[0])) return 14;  /* error exit */
++      if (!isdigit((unsigned char)buffer[0])) return 14;  /* error exit */
+ 
+       /* load temporary node data */
+       sscanf(buffer,"%d %lu %lu %lf %lu %lu",
diff --git a/www/geolizer/files/patch-ac b/www/geolizer/files/patch-ac
new file mode 100644
index 000000000000..2723bff29eb1
--- /dev/null
+++ b/www/geolizer/files/patch-ac
@@ -0,0 +1,71 @@
+--- webalizer.c.orig	Wed Oct 24 10:24:51 2001
++++ webalizer.c	Tue Feb 12 05:29:59 2002
+@@ -231,7 +231,7 @@
+ int main(int argc, char *argv[])
+ {
+    int      i;                           /* generic counter             */
+-   char     *cp1, *cp2, *cp3, *str;      /* generic char pointers       */
++   unsigned char *cp1, *cp2, *cp3, *str;      /* generic char pointers       */
+    NLISTPTR lptr;                        /* generic list pointer        */
+ 
+    extern char *optarg;                  /* used for command line       */
+@@ -569,7 +569,7 @@
+ 
+          /* convert month name to lowercase */
+          for (i=4;i<7;i++)
+-            log_rec.datetime[i]=tolower(log_rec.datetime[i]);
++	    log_rec.datetime[i]=tolower((unsigned char)log_rec.datetime[i]);
+ 
+          /* get year/month/day/hour/min/sec values    */
+          for (i=0;i<12;i++)
+@@ -713,7 +713,7 @@
+          {
+             if ((cp1=strstr(log_rec.url,lptr->string))!=NULL)
+             {
+-               if ((cp1==log_rec.url)||(*(cp1-1)=='/'))
++	       if ((cp1==(unsigned char *)log_rec.url)||(*(cp1-1)=='/'))
+                {
+                   *cp1='\0';
+                   if (log_rec.url[0]=='\0')
+@@ -1466,19 +1466,19 @@
+    while ( (fgets(buffer,BUFSIZE,fp)) != NULL)
+    {
+       /* skip comments and blank lines */
+-      if ( (buffer[0]=='#') || isspace((int)buffer[0]) ) continue;
++      if ( (buffer[0]=='#') || isspace((unsigned char)buffer[0]) ) continue;
+ 
+       /* Get keyword */
+       cp1=buffer;cp2=keyword;
+-      while ( isalnum((int)*cp1) ) *cp2++ = *cp1++;
++      while ( isalnum((unsigned char)*cp1) ) *cp2++ = *cp1++;
+       *cp2='\0';
+ 
+       /* Get value */
+       cp2=value;
+-      while ( (*cp1!='\n')&&(*cp1!='\0')&&(isspace((int)*cp1)) ) cp1++;
++      while ( (*cp1!='\n')&&(*cp1!='\0')&&(isspace((unsigned char)*cp1)) ) cp1++;
+       while ( (*cp1!='\n')&&(*cp1!='\0') ) *cp2++ = *cp1++;
+       *cp2--='\0';
+-      while ( (isspace((int)*cp2)) && (cp2 != value) ) *cp2--='\0';
++      while ( (isspace((unsigned char)*cp2)) && (cp2 != value) ) *cp2--='\0';
+ 
+       /* check if blank keyword/value */
+       if ( (keyword[0]=='\0') || (value[0]=='\0') ) continue;
+@@ -1820,7 +1820,7 @@
+          if (*cp1=='+') *cp1=' ';                      /* change + to space  */
+          if (sp_flg && *cp1==' ') { cp1++; continue; } /* compress spaces    */
+          if (*cp1==' ') sp_flg=1; else sp_flg=0;       /* (flag spaces here) */
+-         *cp2++=tolower(*cp1);                         /* normal character   */
++	 *cp2++= *cp1;                               /* normal character   */
+          cp1++;
+       }
+    }
+@@ -1855,7 +1855,7 @@
+    int  i=group_domains+1;
+ 
+    cp = str+strlen(str)-1;
+-   if (isdigit((int)*cp)) return NULL;   /* ignore IP addresses */
++   if (isdigit((unsigned char)*cp)) return NULL;   /* ignore IP addresses */
+ 
+    while (cp!=str)
+    {
diff --git a/www/geolizer/files/patch-ad b/www/geolizer/files/patch-ad
new file mode 100644
index 000000000000..b0d97e824a8a
--- /dev/null
+++ b/www/geolizer/files/patch-ad
@@ -0,0 +1,42 @@
+--- output.c.orig	Fri Jul 23 23:13:47 2004
++++ output.c	Sat Jul 24 00:26:37 2004
+@@ -1543,10 +1543,17 @@
+       rptr=*pointer++;
+       if (rptr->flag == OBJ_REG)
+       {
+-         fprintf(out_fp,"%-8lu %6.02f%%  %s\n",
+-            rptr->count,
+-            (t_hit==0)?0:((float)rptr->count/t_hit)*100.0,
+-            rptr->string);
++	 if (strstr(rptr->string,"://")!=NULL)
++	    fprintf(out_fp,"%-8lu %6.02f%%  <A HREF=\"%s\">%s</A>\n",
++	       rptr->count,
++	       (t_hit==0)?0:((float)rptr->count/t_hit)*100.0,
++	       rptr->string,
++	       rptr->string);
++	 else
++	    fprintf(out_fp,"%-8lu %6.02f%%  %s\n",
++	       rptr->count,
++	       (t_hit==0)?0:((float)rptr->count/t_hit)*100.0,
++	       rptr->string);
+          r_reg--;
+       }
+    }
+@@ -2033,7 +2040,7 @@
+             while ( (*domain!='.')&&(domain!=hptr->string)) domain--;
+             if (domain==hptr->string)
+ 	       country=NULL;
+-            else if (isdigit((int)*++domain))
++	    else if (isdigit((unsigned char)*++domain))
+             {
+ #ifdef USE_GEOIP
+                if (use_geoip)
+@@ -2918,7 +2925,7 @@
+    static char warpbuf[32][32];
+    static int index = -1;
+ 
+-   if (index<0 || index>32)
++   if (index<0 || index>=32)
+       index=0;
+ 
+    while (n>=base && usesuf<=10)
diff --git a/www/geolizer/files/patch-linklist b/www/geolizer/files/patch-linklist
new file mode 100644
index 000000000000..7320ad7233a5
--- /dev/null
+++ b/www/geolizer/files/patch-linklist
@@ -0,0 +1,42 @@
+--- linklist.c.orig	Sat Jun 23 11:12:40 2001
++++ linklist.c	Sat Jun 23 11:19:54 2001
+@@ -190,12 +190,12 @@
+ int add_glist(char *str, GLISTPTR *list)
+ {
+    GLISTPTR newptr,cptr,pptr;
+-   char temp_buf[80];
++   char temp_buf[LINKLIST_MAX_STRING];
+    char *name=temp_buf;
+ 
+    /* make local copy of string */
+-   strncpy(temp_buf,str,79);
+-   temp_buf[79]=0;
++   strncpy(temp_buf,str,LINKLIST_MAX_STRING - 1);
++   temp_buf[LINKLIST_MAX_STRING - 1]=0;
+ 
+    while (!isspace((unsigned char)*name)&&*name!=0) name++;
+    if (*name==0) name=temp_buf;
+--- linklist.h.orig	Fri Sep 29 05:50:30 2000
++++ linklist.h	Sat Jun 23 11:15:57 2001
+@@ -1,12 +1,18 @@
+ #ifndef _LINKLIST_H
+ #define _LINKLIST_H
+ 
+-struct nlist {  char string[80];           /* list struct for HIDE items   */
++#ifndef	LINKLIST_MAX_STRING
++#define	LINKLIST_MAX_STRING	80
++#endif
++
++struct nlist {                             /* list struct for HIDE items   */
++              char string[LINKLIST_MAX_STRING];
+               struct nlist *next; };
+ typedef struct nlist *NLISTPTR;
+ 
+-struct glist {  char string[80];           /* list struct for GROUP items  */
+-                char name[80];
++struct glist {                             /* list struct for GROUP items  */
++              char string[LINKLIST_MAX_STRING];
++              char name[LINKLIST_MAX_STRING];
+               struct glist *next; };
+ typedef struct glist *GLISTPTR;
+ 
diff --git a/www/geolizer/files/patch-lowercase-url-bug b/www/geolizer/files/patch-lowercase-url-bug
new file mode 100644
index 000000000000..29d7ac8710ef
--- /dev/null
+++ b/www/geolizer/files/patch-lowercase-url-bug
@@ -0,0 +1,32 @@
+--- webalizer.c	2002-04-16 18:11:31.000000000 -0400
++++ webalizer.c.new	2003-07-07 12:35:45.000000000 -0400
+@@ -688,6 +688,14 @@
+          /* un-escape URL */
+          unescape(log_rec.url);
+ 
++         /* 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'; }
++
+          /* check for service (ie: http://) and lowercase if found */
+          if ( (cp2=strstr(log_rec.url,"://")) != NULL)
+          {
+@@ -699,14 +707,6 @@
+             }
+          }
+ 
+-         /* 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)
diff --git a/www/geolizer/pkg-descr b/www/geolizer/pkg-descr
new file mode 100644
index 000000000000..d24c25e196fe
--- /dev/null
+++ b/www/geolizer/pkg-descr
@@ -0,0 +1,7 @@
+Patch for Webalizer to generate faster and more reliable geographic 
+statistics than using default DNS suffix method. It uses GeoIP library to 
+do that. In fact, if you disable DNS reversal on your HTTP server, it will 
+work faster and your stats get more accuracy when processed by patched 
+Webalizer.
+
+WWW: http://sysd.org/proj/log.php#glzr