Updated documentation

diff --git a/docs/awstats.pdf b/docs/awstats.pdf
index 30fe10508c0b8cf8ad254656d6921032e4aa2bc6..f1322390bdcafb438ddd27252f25de4a4948da34 100644 (file)
Binary files a/docs/awstats.pdf and b/docs/awstats.pdf differ

diff --git a/docs/awstats_compare.html b/docs/awstats_compare.html
index 938d82e08451b3751f6e0f19c08e28b936c131a8..7dcfe5cf8bf590b42e13da0265abeae29dbf1968 100644 (file)
--- a/docs/awstats_compare.html
+++ b/docs/awstats_compare.html
@@ -41,7 +41,7 @@
 \r
 <!-- Info -->\r
 <tr align=center bgcolor=#DDDDDD><td align=left><b>Features/Softwares</b></td><td><b>AWStats</b></td><td><b><a href="http://www.analog.cx">Analog</a></b></td><td><b><a href="http://www.mrunix.net/webalizer/">Webalizer</a></b></td><td><b><a href="http://www.hitbox.com">HitBox</a></b></td></tr>\r
-<tr align=center><td align=left>Version - Date</td><td>5.0 - September 2002</td><td>5.24 - July 2002</td><td>2.01-10 - April 2002</td><td>NA</td></tr>\r
+<tr align=center><td align=left>Version - Date</td><td>5.1 - October 2002</td><td>5.24 - July 2002</td><td>2.01-10 - April 2002</td><td>NA</td></tr>\r
 <tr align=center bgcolor=#DDDDDD><td align=left>Language</td><td>Perl</td><td>C</td><td>C</td><td>Embedded HTML tag</td></tr>\r
 <tr align=center><td align=left>Available on all platforms</td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td>NA</td></tr>\r
 <tr align=center bgcolor=#DDDDDD><td align=left>Sources available</td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#660000>No</font></td></tr>\r
@@ -61,9 +61,9 @@
 <tr align=center bgcolor=#DDDDDD><td align=left>Not ordered records tolerance and reorder for visits</td><td><font color=#4444cc>Yes</font></td><td><font color=#660000>Visits not supported</font></td><td><font color=#660000>No</font></td><td>?</td></tr>\r
 <tr align=center><td align=left>Statistics for visits are based on</td><td><font color=#4444cc>Pages *****</font></td><td><font color=#660000>Not supported</font></td><td><font color=#4444cc>Pages *****</font></td><td><font color=#4444cc>Pages *****</font></td></tr>\r
 <tr align=center><td align=left>Statistics for unique visitors are based on</td><td><font color=#4444cc>Pages *****</font></td><td><font color=#660000>Not supported</font></td><td><font color=#660000>Not supported</font></td><td><font color=#4444cc>Pages *****</font></td></tr>\r
-<tr align=center bgcolor=#DDDDDD><td align=left>Report domains/countries (nb detected)</td><td><font color=#4444cc>Yes (259)</font></td><td><font color=#4444cc>Yes (259)</font></td><td><font color=#4444cc>Yes</font><font color=#660000> (252)</font></td><td><font color=#4444cc>Yes (?)</font></td></tr>\r
+<tr align=center bgcolor=#DDDDDD><td align=left>Report domains/countries (nb detected)</td><td><font color=#4444cc>Yes (266)</font></td><td><font color=#4444cc>Yes (266)</font></td><td><font color=#4444cc>Yes</font><font color=#660000> (259)</font></td><td><font color=#4444cc>Yes (?)</font></td></tr>\r
 <tr align=center><td align=left>Report authenticated users</td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#660000>No</font></td><td><font color=#660000>No</font></td></tr>\r
-<tr align=center bgcolor=#DDDDDD><td align=left>Report/Filter robots (nb detected)</td><td><font color=#4444cc>Yes/Yes (291**)</font></td><td><font color=#4444cc>Yes / Yes</font> <font color=#660000>(8)</font></td><td><font color=#660000>No/No (0**)</font></td><td><font color=#660000>No/No (0**)</font></td></tr>\r
+<tr align=center bgcolor=#DDDDDD><td align=left>Report/Filter robots (nb detected)</td><td><font color=#4444cc>Yes/Yes (304**)</font></td><td><font color=#4444cc>Yes / Yes</font> <font color=#660000>(8)</font></td><td><font color=#660000>No/No (0**)</font></td><td><font color=#660000>No/No (0**)</font></td></tr>\r
 \r
 <!-- When -->\r
 <tr align=center><td align=left>Report rush hours</td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td></tr>\r
@@ -82,11 +82,11 @@
 <tr align=center bgcolor=#DDDDDD><td align=left>Report by file size</td><td><font color=#660000>No</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#660000>No</font></td><td><font color=#660000>No</font></td></tr>\r
 \r
 <!-- Referrer -->\r
-<tr align=center><td align=left>Report browsers (nb detected)</td><td><font color=#4444cc>Yes (75*)</font></td><td><font color=#660000>No</font></td><td><font color=#4444cc>Yes</font><font color=#660000> (4*)</font></td><td><font color=#4444cc>Yes</font><font color=#660000> (<20*)</font></td></tr>\r
-<tr align=center bgcolor=#DDDDDD><td align=left>Report details of browsers versions</td><td><font color=#4444cc>Yes</font></td><td><font color=#660000>No</font></td><td><font color=#660000>No</font></td><td><font color=#4444cc>Yes</font></td></tr>\r
+<tr align=center><td align=left>Report browsers (nb detected)</td><td><font color=#4444cc>Yes (76*)</font></td><td><font color=#660000>No</font></td><td><font color=#4444cc>Yes</font><font color=#660000> (4*)</font></td><td><font color=#4444cc>Yes</font><font color=#660000> (<20*)</font></td></tr>\r
+<tr align=center bgcolor=#DDDDDD><td align=left>Report details of browsers versions</td><td><font color=#4444cc>Yes</font></td><td><font color=#660000>No</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td></tr>\r
 <tr align=center><td align=left>Report OS (nb detected)</td><td><font color=#4444cc>Yes (29)</font></td><td><font color=#4444cc>Yes</font><font color=#660000> (25)</font></td><td><font color=#660000>No (0)</font></td><td>?</td></tr>\r
-<tr align=center bgcolor=#DDDDDD><td align=left>Report search engines used (nb detected)</td><td><font color=#4444cc>Yes (63***)</font></td><td><font color=#4444cc>Yes </font><font color=#660000>(24)</font></td><td><font color=#660000>No (0)</font></td><td><font color=#4444cc>Yes</font><font color=#660000> (<20 ***)</font></td></tr>\r
-<tr align=center><td align=left>Report keywords/keyphrases used on search engines (nb detected)</td><td><font color=#4444cc>Yes/Yes (65***)</font></td><td><font color=#4444cc>Yes</font>/<font color=#660000>No</font><font color=#660000> (29***)</font></td><td><font color=#660000>No</font>/<font color=#4444cc>Yes</font><font color=#660000> (14***)</font></td><td><font color=#4444cc>Yes</font>/<font color=#660000>No (<20***)</font></td></tr>\r
+<tr align=center bgcolor=#DDDDDD><td align=left>Report search engines used (nb detected)</td><td><font color=#4444cc>Yes (78***)</font></td><td><font color=#4444cc>Yes </font><font color=#660000>(24)</font></td><td><font color=#660000>No (0)</font></td><td><font color=#4444cc>Yes</font><font color=#660000> (<20 ***)</font></td></tr>\r
+<tr align=center><td align=left>Report keywords/keyphrases used on search engines (nb detected)</td><td><font color=#4444cc>Yes/Yes (81***)</font></td><td><font color=#4444cc>Yes</font>/<font color=#660000>No</font><font color=#660000> (29***)</font></td><td><font color=#660000>No</font>/<font color=#4444cc>Yes</font><font color=#660000> (14***)</font></td><td><font color=#4444cc>Yes</font>/<font color=#660000>No (<20***)</font></td></tr>\r
 \r
 <!-- Misc -->\r
 <tr align=center bgcolor=#DDDDDD><td align=left>Report HTTP Errors</td><td><font color=#4444cc>Yes<br></font></td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#660000>No</font></td></tr>\r
@@ -95,7 +95,7 @@
 <tr align=center><td align=left>Daily statistics </td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td></tr>\r
 <tr align=center bgcolor=#DDDDDD><td align=left>Monthly statistics </td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td></tr>\r
 <tr align=center><td align=left>Yearly statistics </td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td></tr>\r
-<tr align=center bgcolor=#DDDDDD><td align=left>Benchmark with no DNS lookup in lines/seconds<br>(full features enabled, with XLF format, on Athlon 1Ghz)</td><td><font color=#660000>4500****</font></td><td><font color=#4444cc>?****</font></td><td><font color=#4444cc>39000****</font></td><td>NA<br>No program to run</td></tr>\r
+<tr align=center bgcolor=#DDDDDD><td align=left>Benchmark with no DNS lookup in lines/seconds<br>(full features enabled, with XLF format, on Athlon 1Ghz)</td><td><font color=#660000>4500****</font></td><td><font color=#4444cc>?****</font></td><td><font color=#4444cc>12000****</font></td><td>NA<br>No program to run</td></tr>\r
 <tr align=center><td align=left>Benchmark with DNS lookup in lines/seconds<br>(full features enabled, with XLF format, on Athlon 1Ghz)</td><td><font color=#4444cc>80****</font></td><td><font color=#4444cc>80****</font></td><td><font color=#4444cc>80****</font></td><td>NA<br>No program to run</td></tr>\r
 <tr align=center bgcolor=#DDDDDD><td align=left>Main graphical statistics in one page</td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#4444cc>Yes</font></td><td><font color=#660000>No</font></td></tr>\r
 \r
@@ -104,17 +104,23 @@
 <font style="font: 7pt arial,helvetica,verdana">\r
 * This number is not really the number of browsers detected. All browsers (known and unknown) can be detected by products\r
 that support this feature (AWStats,Webalizer,HitBox). The number is only the number of known browsers for which different\r
-versions can be grouped in one browser name.<br>\r
+versions are grouped by default in one browser name.<br>\r
 <br>\r
 ** AWStats can detect robots visits: All robots among the most common are detected, list is in <a href="http://www.robotstxt.org/wc/active/all.txt">robotslist.txt</a> (250Kb). Products that are not able to do this give you false information, above all if your site\r
 has few visitors. For example, if you're site was submitted to all famous search engines, robots can make 500 visits a month, to find updates or to see if your site is still online.\r
 So, if you have only 2000 visits a month, products with no robot detection capabilities will report 2500 visits (A 25% error !). AWStats will report 500 visits from robots and 2000 visits from human visitors.<br>\r
 <br>\r
-*** AWStats has url syntax rules for the most popular search engines but AWStats has also an algorithm\r
-to detect keywords of unknown search engines with unknown url syntax rule. Those rules are updated with AWStats updates.<br>\r
+*** AWStats has url syntax rules for the most popular search engines (that's the 'number detected').\r
+Those rules are updated with AWStats updates.\r
+But AWStats has also an algorithm to detect keywords of unknown search engines with unknown url syntax rules. <br>\r
 <br>\r
-**** This rate is for processing log records with full information (combined XLF/ELF or extended W3C log format) but\r
-you must keep in mind that all this times are without reverse DNS lookup. DNS lookup speed depends on your system, network and\r
+**** As you can see, some log analyzers have, by default, very poor (or not at all) robots, search engines, os or\r
+browsers detection capabilities. So to have a benchmark comparison that means something, some log analyzers features\r
+were 'enhanced' with AWStats databases, when it was possible (For example, Webalizer config file was completed with\r
+this <a href="http://awstats.sourceforge.net/files/webalizeradd.txt">file</a>. With that, Webalizer features are a little bit close that thoose of AWStats.\r
+Without that, like using default conf file, Webalizer results are 3 times faster but with a lot of missing features).<br>\r
+Benchmarks was made on a combined (XLF/CLF) log record on an Athlon 1GHz.<br>\r
+You must keep in mind that all this times are without reverse DNS lookup. DNS lookup speed depends on your system, network and\r
 Internet but not on the log analyzer you use. For this reason, DNS lookup is disabled in all log analyzer benchmarks.\r
 Don't forget that DNS lookup is 95% (even with a lookup cache) of the time used by a log analyzer, so if your host is not\r
 already resolved in log file and DNS lookup is enable, the total time of the process will be nearly the same whatever\r

diff --git a/wwwroot/cgi-bin/awstats.pl b/wwwroot/cgi-bin/awstats.pl
index 445608798f2587776585952732a50e66099dfe9c..128c515b8c2a422f2634dce924893b528a363ed8 100644 (file)
--- a/wwwroot/cgi-bin/awstats.pl
+++ b/wwwroot/cgi-bin/awstats.pl
@@ -4404,6 +4404,8 @@ if ($Debug) {
 if ($Debug) { debug("UpdateStats is $UpdateStats",2); }
 if ($UpdateStats && $FrameName ne "index" && $FrameName ne "mainleft") {       # Update only on index page or when not framed to avoid update twice
 
+       print "Update for config '$FileConfig'\nWith data in log file '$LogFile'...\n";
+
        my $lastprocessedyear=$lastyearbeforeupdate;
        my $lastprocessedmonth=$ListOfYears{$lastyearbeforeupdate}||0;
        my $lastprocessedyearmonth=sprintf("%04i%02i",$lastprocessedyear,$lastprocessedmonth);
@@ -4679,6 +4681,9 @@ if ($UpdateStats && $FrameName ne "index" && $FrameName ne "mainleft") {  # Updat
        if ($Debug) { debug("Open log file \"$LogFile\""); }
        open(LOG,"$LogFile") || error("Error: Couldn't open server log file \"$LogFile\" : $!");
 
+       # Avoid premature EOF due to log files corrupted with \cZ or bin chars
+       binmode LOG;
+
        my @field=();
        my $counter=0;
        # Reset counter for benchmark (first call to GetDelaySinceStart)