From: eldy <> Date: Sat, 31 May 2003 15:04:00 +0000 (+0000) Subject: Can add regex values for a lot of list parameters (HostAliases, SkipDNSLookupFor... X-Git-Tag: AWSTATS_5_6_BETA~45 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=20eb947289dd6b83cdcc7f1938687e5652efe998;p=thirdparty%2FAWStats.git Can add regex values for a lot of list parameters (HostAliases, SkipDNSLookupFor, ...) Fixes: Added the "Other" line when list for unkown os and browsers were limited to a lower value than number of unknown os or browsers. --- diff --git a/wwwroot/cgi-bin/awstats.model.conf b/wwwroot/cgi-bin/awstats.model.conf index 0b8bdef7..486b6346 100644 --- a/wwwroot/cgi-bin/awstats.model.conf +++ b/wwwroot/cgi-bin/awstats.model.conf @@ -132,13 +132,14 @@ SiteDomain="" # aliases someone can use to access your site. Try to keep only the minimum # number of possible names/addresses to have the best performances. # You can repeat the "SiteDomain" value in this list. -# Use space between each value. # This parameter is used to analyze referer field in log file and to help # AWStats to know if a referer URL is a local URL of same site or an URL of # another site. -# Example: "www.myserver.com x.y.z.w localhost 127.0.0.1" +# Note: Use space between each value. +# Note: You can use regular expression values writing value with REGEX[value]. +# Example: "www.myserver.com localhost 127.0.0.1 REGEX[\.mydomain\.(net|org)$]" # -HostAliases="www.myserver.com x.y.z.w localhost 127.0.0.1" +HostAliases="localhost 127.0.0.1 REGEX[^.*\.myserver\.com$]" # If you want to have hosts reported by name instead of ip address, AWStats @@ -258,13 +259,12 @@ DNSStaticCacheFile="dnscache.txt" DNSLastUpdateCacheFile="dnscachelastupdate.txt" -# You can specify specific IP addresses that should NOT be looked up in -# the DNS. You may specify partial addresses (ie 163.85. for everything -# behind the usual firewall setup, etc)... +# You can specify specific IP addresses that should NOT be looked up in DNS. # This option is used only if DNSLookup=1. # Note: Use space between each value. +# Note: You can use regular expression values writing value with REGEX[value]. # Change : Effective for new updates only -# Example: "163.85. 201.101.51.2" +# Example: "123.123.123.123 REGEX[^192\.168\.]" # Default: "" # SkipDNSLookupFor="" @@ -388,11 +388,10 @@ DefaultFile="index.html" # criteria, else enter ip address criteria. # The opposite parameter of "SkipHosts" is "OnlyHosts". # Note: Use space between each value. -# Note: ^xxx means hosts starting with xxx -# Note: xxx$ means hosts ending with xxx +# Note: You can use regular expression values writing value with REGEX[value]. # Change : Effective for new updates only -# Example: "^127.0.0.1$ ^192.168. ^10.0." -# Example: "localhost abcxyz" +# Example: "127.0.0.1 REGEX[^192\.168\.] REGEX[^10\.0\.]" +# Example: "localhost REGEX[^.*\.localdomain$]" # Default: "" # SkipHosts="" @@ -402,8 +401,9 @@ SkipHosts="" # criteria. If you want to exclude a robot, you should update the robots.pm # file instead of this parameter. # Note: Use space between each value. This parameter is not case sensitive. +# Note: You can use regular expression values writing value with REGEX[value]. # Change : Effective for new updates only -# Example: "konqueror" +# Example: "konqueror REGEX[ua_test_v\d\.\d]" # Default: "" # SkipUserAgents="" @@ -413,32 +413,30 @@ SkipUserAgents="" # You can, with this option, add a list of not important frame pages (like # menus, etc...) to exclude them from statistics. # For example, to ignore a whole directory tree, just add "directorytoignore", -# to ignore "users" pages in your stats, you can add "/~". +# to ignore "users" web site pages in your stats, you can add "/~". # The opposite parameter of "SkipFiles" is "OnlyFiles". # Note: This parameter is not case sensitive. # Note: Use space between each value and do not remove default values. -# Note: ^xxx means url starting with xxx. -# Note: xxx$ means url ending with xxx. +# Note: You can use regular expression values writing value with REGEX[value]. # Change : Effective for new updates only -# Example: "robots.txt$ favicon.ico$ badpage.html$ /~" -# Default: "robots.txt$ favicon.ico$" +# Example: "REGEX[robots\.txt$] REGEX[favicon\.ico$] /badpage.html /~" +# Default: "REGEX[robots\.txt$] REGEX[favicon\.ico$]" # -SkipFiles="robots.txt$ favicon.ico$" +SkipFiles="REGEX[robots\.txt$] REGEX[favicon\.ico$]" # Include in stats, only accesses from hosts that match one of following # entries. For example, if you want AWStats to filter access to keep only -# stats for visits from particular hosts, you can add thoose hosts names -# in this parameter. +# stats for visits from particular hosts, you can add those hosts names in +# this parameter. # If DNS lookup is already done in your log file, you must enter here hostname # criteria, else enter ip address criteria. # The opposite parameter of "OnlyHosts" is "SkipHosts". # Note: This parameter is not case sensitive. # Note: Use space between each value. -# Note: ^xxx means hosts starting with xxx. -# Note: xxx$ means hosts ending with xxx. +# Note: You can use regular expression values writing value with REGEX[value]. # Change : Effective for new updates only -# Example: "^123.123.123.123$ ^10.0." +# Example: "127.0.0.1 REGEX[^192\.168\.] REGEX[^10\.0\.]" # Default: "" # OnlyHosts="" @@ -451,10 +449,9 @@ OnlyHosts="" # The opposite parameter of "OnlyFiles" is "SkipFiles". # Note: This parameter is not case sensitive. # Note: Use space between each value and do not remove default values -# Note: ^xxx means url starting with xxx. -# Note: xxx$ means url ending with xxx. +# Note: You can use regular expression values writing value with REGEX[value]. # Change : Effective for new updates only -# Example: "marketing_directory" +# Example: "marketing_directory REGEX[office\/.*\.(csv|sxw)$]" # Default: "" # OnlyFiles="" diff --git a/wwwroot/cgi-bin/awstats.pl b/wwwroot/cgi-bin/awstats.pl index 25fa763a..4043bbad 100644 --- a/wwwroot/cgi-bin/awstats.pl +++ b/wwwroot/cgi-bin/awstats.pl @@ -34,7 +34,7 @@ $DEBUGFORCED=0; # Force debug level to log lesser level into debug.log file $NBOFLINESFORBENCHMARK=8192; # Benchmark info are printing every NBOFLINESFORBENCHMARK lines (Must be a power of 2) $FRAMEWIDTH=260; # Width of left frame when UseFramesWhenCGI is on $NBOFLASTUPDATELOOKUPTOSAVE=200; # Nb of records to save in DNS last update cache file -$LIMITFLUSH=4000; # Nb of records in data arrays after how we need to flush data on disk +$LIMITFLUSH=5000; # Nb of records in data arrays after how we need to flush data on disk $NEWDAYVISITTIMEOUT=764041; # Delay between 01-23:59:59 and 02-00:00:00 $VISITTIMEOUT=10000; # Laps of time to consider a page load as a new visit. 10000 = 1 hour (Default = 10000) $NOTSORTEDRECORDTOLERANCE=10000; # Laps of time to accept a record if not in correct order. 10000 = 1 hour (Default = 10000) @@ -1108,7 +1108,7 @@ sub Parse_Config { } if ($param =~ /^HostAliases/) { foreach my $elem (split(/\s+/,$value)) { - if ($elem!~s/^REGEX://i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. + if ($elem!~s/^REGEX\[(.*)\]$/$1/i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. if ($elem) { push @HostAliases,$elem; } } next; @@ -1116,7 +1116,7 @@ sub Parse_Config { # Special optional setup params if ($param =~ /^SkipDNSLookupFor/) { foreach my $elem (split(/\s+/,$value)) { - if ($elem!~s/^REGEX://i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. + if ($elem!~s/^REGEX\[(.*)\]$/$1/i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. if ($elem) { push @SkipDNSLookupFor,$elem; } } next; @@ -1126,43 +1126,43 @@ sub Parse_Config { next; } if ($param =~ /^DefaultFile/) { - foreach my $elem (split(/\s+/,$value)) { - if ($elem!~s/^REGEX://i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. + foreach my $elem (split(/\s+/,$value)) { # No REGEX for this option + $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; # Replace . into \. if ($elem) { push @DefaultFile,$elem; } } next; } if ($param =~ /^SkipHosts/) { foreach my $elem (split(/\s+/,$value)) { - if ($elem!~s/^REGEX://i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. + if ($elem!~s/^REGEX\[(.*)\]$/$1/i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. if ($elem) { push @SkipHosts,$elem; } } next; } if ($param =~ /^SkipUserAgents/) { foreach my $elem (split(/\s+/,$value)) { - if ($elem!~s/^REGEX://i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. + if ($elem!~s/^REGEX\[(.*)\]$/$1/i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. if ($elem) { push @SkipUserAgents,$elem; } } next; } if ($param =~ /^SkipFiles/) { foreach my $elem (split(/\s+/,$value)) { - if ($elem!~s/^REGEX://i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. + if ($elem!~s/^REGEX\[(.*)\]$/$1/i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. if ($elem) { push @SkipFiles,$elem; } } next; } if ($param =~ /^OnlyHosts/) { foreach my $elem (split(/\s+/,$value)) { - if ($elem!~s/^REGEX://i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. + if ($elem!~s/^REGEX\[(.*)\]$/$1/i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. if ($elem) { push @OnlyHosts,$elem; } } next; } if ($param =~ /^OnlyFiles/) { foreach my $elem (split(/\s+/,$value)) { - if ($elem!~s/^REGEX://i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. + if ($elem!~s/^REGEX\[(.*)\]$/$1/i) { $elem =~ s/\\\./\./g; $elem =~ s/([^\\])\./$1\\\./g; $elem =~ s/^\./\\\./; } # Replace . into \. if ($elem) { push @OnlyFiles,$elem; } } next; @@ -5733,7 +5733,7 @@ if ($UpdateStats && $FrameName ne 'index' && $FrameName ne 'mainleft') { # Updat } else { foreach my $key (@HostAliases) { - if ($refererserver =~ /^$key$/i) { + if ($refererserver =~ /$key/i) { # Intern (This hit came from another page of the site) if ($Debug) { debug(" Server '$refererserver' is added to TmpRefererServer with value '='",2); } $TmpRefererServer{$refererserver}='='; @@ -6059,9 +6059,9 @@ if ($UpdateStats && $FrameName ne 'index' && $FrameName ne 'mainleft') { # Updat if (scalar keys %HTMLOutput) { my $max_p; my $max_h; my $max_k; my $max_v; - my $total_u; my $total_v; my $total_p; my $total_h; my $total_k; my $total_e; my $total_x; my $total_s; + my $total_u; my $total_v; my $total_p; my $total_h; my $total_k; my $total_e; my $total_x; my $total_s; my $total_l; my $average_u; my $average_v; my $average_p; my $average_h; my $average_k; my $average_s; - my $rest_p; my $rest_h; my $rest_k; my $rest_e; my $rest_x; my $rest_s; + my $rest_p; my $rest_h; my $rest_k; my $rest_e; my $rest_x; my $rest_s; my $rest_l; my $average_nb; # Define the NewLinkParams for main chart @@ -7106,13 +7106,23 @@ if (scalar keys %HTMLOutput) { my $title="$Message[46]"; &tab_head("$title",19); print "User agent (".(scalar keys %_unknownreferer_l).")$Message[9]\n"; + $total_l=0; my $count=0; &BuildKeyList($MaxRowsInHTMLOutput,1,\%_unknownreferer_l,\%_unknownreferer_l); foreach my $key (@keylist) { my $useragent=CleanFromCSSA($key); - print "$useragent".Format_Date($_unknownreferer_l{$key},1)."\n"; + print "$useragent"; + print "".Format_Date($_unknownreferer_l{$key},1).""; + print "\n"; + $total_l+=1; $count++; } + $rest_l=(scalar keys %_unknownreferer_l)-$total_l; + if ($rest_l > 0) { + print "$Message[2]"; + print "-"; + print "\n"; + } &tab_end; &html_end; } @@ -7121,13 +7131,21 @@ if (scalar keys %HTMLOutput) { my $title="$Message[50]"; &tab_head("$title",19); print "User agent (".(scalar keys %_unknownrefererbrowser_l).")$Message[9]\n"; + $total_l=0; my $count=0; &BuildKeyList($MaxRowsInHTMLOutput,1,\%_unknownrefererbrowser_l,\%_unknownrefererbrowser_l); foreach my $key (@keylist) { my $useragent=CleanFromCSSA($key); print "$useragent".Format_Date($_unknownrefererbrowser_l{$key},1)."\n"; + $total_l+=1; $count++; } + $rest_l=(scalar keys %_unknownrefererbrowser_l)-$total_l; + if ($rest_l > 0) { + print "$Message[2]"; + print "-"; + print "\n"; + } &tab_end; &html_end; } @@ -7329,7 +7347,7 @@ if (scalar keys %HTMLOutput) { if ($TotalSearchEnginesHits) { $p_h=int($rest_h/$TotalSearchEnginesHits*1000)/10; } print "$Message[2]"; print "".($rest_p?$rest_p:' ').""; - print "".($rest_p?"%p_p %":' ').""; + print "".($rest_p?"$p_p %":' ').""; print "$rest_h"; print "$p_h %"; print "\n";