Deal with url without scheme or path in a squidGuard log

Some url in a squidGuard log don't start with a scheme:// and may not
even contain a path. Those bare minimum url are not parsed correctly
by the redirector_log_format suggested in sarg.conf.

To parse those log entries correctly, we grab the whole url in the
buffer and strip it down to keep the host name.

diff --git a/redirector.c b/redirector.c
index 81a0de758e568d90b166f1e1e950bf1b4d345093..1fd63393534abbeba3e47326a548165a578f8ac9 100644 (file)
--- a/redirector.c
+++ b/redirector.c
@@ -124,12 +124,11 @@ static void parse_log(FILE *fp_ou,char *buf)
                                        }
                                        strcpy(user,res);
                                } else if(strcmp(leks,"url") == 0) {
-                                       if (strlen(res)>=sizeof(full_url)) {
-                                               debuga(_("URL too long in redirector log file %s\n"),wentp);
-                                               RedirectorErrors++;
-                                               return;
-                                       }
-                                       strcpy(full_url,res);
+                                       /*
+                                        * Don't worry about the url being truncated as we only keep the host name
+                                        * any way...
+                                        */
+                                       safe_strcpy(full_url,res,sizeof(full_url));
                                }
                        }
                }

diff --git a/sarg.conf b/sarg.conf
index 30a0e457d7a13c89a42c214e237b6682ea39aef1..a405476bbdcf896a5bc2613c3641efefda162d4a 100644 (file)
--- a/sarg.conf
+++ b/sarg.conf
@@ -549,8 +549,8 @@
 #      Format string for web proxy redirector logs.
 #      This option was named squidguard_log_format before sarg 2.3.
 #      REJIK       #year#-#mon#-#day# #hour# #list#:#tmp# #ip# #user# #tmp#/#tmp#/#url#/#end#
-#      SQUIDGUARD  #year#-#mon#-#day# #hour# #tmp#/#list#/#tmp#/#tmp#/#url#/#tmp# #ip#/#tmp# #user# #end#
-#redirector_log_format #year#-#mon#-#day# #hour# #tmp#/#list#/#tmp#/#tmp#/#url#/#tmp# #ip#/#tmp# #user# #end#
+#      SQUIDGUARD  #year#-#mon#-#day# #hour# #tmp#/#list#/#tmp# #url# #ip#/#tmp# #user# #end#
+#redirector_log_format #year#-#mon#-#day# #hour# #tmp#/#list#/#tmp# #url# #ip#/#tmp# #user# #end#
 
 # TAG: show_sarg_info yes|no
 #      shows sarg information and site path on each report bottom