Build 0.6.1

.classpath

@@ -20,10 +20,6 @@
 	<classpathentry kind="lib" path="lib/catgenerator-core-0.1.7.jar" sourcepath="lib/catgenerator-core-0.1.7-sources.zip"/>
 	<classpathentry kind="lib" path="lib/jOpenDocument-1.3.jar" sourcepath="lib/jOpenDocument-src-1.3.zip"/>
 	<classpathentry kind="lib" path="lib/threeten-extra-1.5.0.jar" sourcepath="lib/threeten-extra-1.5.0-sources.jar"/>
-	<classpathentry kind="lib" path="lib/Logs/slf4j-api-1.7.32.jar" sourcepath="lib/Logs/slf4j-api-1.7.32-sources.jar"/>
-	<classpathentry kind="lib" path="lib/Logs/log4j-api-2.17.1.jar" sourcepath="lib/Logs/log4j-api-2.17.1-sources.jar"/>
-	<classpathentry kind="lib" path="lib/Logs/log4j-core-2.17.1.jar" sourcepath="lib/Logs/log4j-core-2.17.1-sources.jar"/>
-	<classpathentry kind="lib" path="lib/Logs/log4j-slf4j-impl-2.17.1.jar" sourcepath="lib/Logs/log4j-slf4j-impl-2.17.1-sources.jar"/>
 	<classpathentry kind="lib" path="lib/commons-io-2.11.0.jar" sourcepath="lib/commons-io-2.11.0-sources.jar"/>
 	<classpathentry kind="lib" path="lib/json-simple-1.1.1.jar" sourcepath="lib/json-simple-1.1.1-sources.jar"/>
 	<classpathentry kind="lib" path="lib/mariadb-java-client-3.0.3.jar"/>
@@ -41,5 +37,9 @@
 			<attribute name="optional" value="true"/>
 		</attributes>
 	</classpathentry>
+	<classpathentry kind="lib" path="lib/Logs/log4j-api-2.23.1.jar" sourcepath="lib/Logs/log4j-api-2.23.1-sources.jar"/>
+	<classpathentry kind="lib" path="lib/Logs/log4j-core-2.23.1.jar" sourcepath="lib/Logs/log4j-core-2.23.1-sources.jar"/>
+	<classpathentry kind="lib" path="lib/Logs/log4j-slf4j2-impl-2.23.1.jar" sourcepath="lib/Logs/log4j-slf4j2-impl-2.32.1-sources.jar"/>
+	<classpathentry kind="lib" path="lib/Logs/slf4j-api-2.0.16.jar" sourcepath="lib/Logs/slf4j-api-2.0.16-sources.jar"/>
 	<classpathentry kind="output" path="bin"/>
 </classpath>

CHANGELOG.md

@@ -8,6 +8,19 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 - …
 
+## [0.6.1] - 2024-09-23
+
+- Fixed bad log init with no configuration file.
+- Fixed StackOverflowError case in AccessLog regex.
+- Improved Javadoc and added test for isPage method.
+- Fixed Java version in build script.
+- Fixed label in script build.sh.
+- Upgraded log4j libs from 1.7.32 to 2.23.1.
+- Improved main README and resources files.
+- Improved documentation.
+- Improved build script.
+
+
 ## [0.6.0] - 2024-08-17
 Change major number because of split web event.
 
@@ -35,7 +48,6 @@ Changes for metrics:
 - Improved user agent bot list.
 
 
-
 Changes for web building:
 - SPLITWEB: no more web building! See the StatoolInfosWeb project.
 
@@ -45,7 +57,7 @@ Changes for metrics:
 - Added multi sources for Http log file search.
 - Added wrong password metrics for Minetest.
 - Fixed property label in Privatebin patch probe.
-- Added CLI commands to test HttpAccessLog files and lines. 
+- Added CLI commands to test HttpAccessLog files and lines.
 - Moved HttpErrorLog analyzer in dedicated package.
 - Refactored prober call from CLI.
 - Added new metrics analyzers.
@@ -58,7 +70,7 @@ Changes for metrics:
 - Set 401 uptime case as OK.
 - Improved bot pattern list with TinyStatus.
 - Added metrics for GSL.
-- Improved documentation (README)	
+- Improved documentation (README)
 
 Changes for web building:
 - Improved property stats page with only active organizations.
@@ -88,7 +100,7 @@ Changes for web building:
 - Swap columns in htmlizeOrganizationInOutChart.
 - Fixed colors.
 
- 
+
 ## [0.5.0] – 2022-01-23
 
 This release contains many improvments:

README.md

@@ -44,15 +44,43 @@ Read CONCEPT.md and ONTOLOGY.md files.
 
 ## INSTALL
 
-Install Java :
+Install Java on Debian:
 
 ```
 apt-get install openjdk-17-jre-headless
 ```
 
-Download the last release: https://forge.devinsy.fr/statool/statoolinfos/releases
+Download the last release: `https://forge.devinsy.fr/statool/statoolinfos/releases` and unzip the package. 
 
-Unzip the package and move the `statoolinfos.jar` and `statoolinfo.sh` files in `/srv/statoolinfos/bin/`.
+The `srv/` directory is a example of deployment tree:
+
+```
+srv/
+srv/statoolinfos
+srv/statoolinfos/bin
+srv/statoolinfos/bin/refresh
+srv/statoolinfos/bin/probe
+srv/statoolinfos/bin/uptime
+srv/statoolinfos/bin/statoolinfos.sh
+srv/statoolinfos/bin/crawl
+srv/statoolinfos/conf
+srv/statoolinfos/conf/sample-probe-http.conf
+srv/statoolinfos/conf/log4j2-default.properties
+srv/statoolinfos/conf/sample-probe-minetest.conf
+srv/statoolinfos/conf/sample-federation.conf
+srv/statoolinfos/conf/sample-probe-qrcode.conf
+srv/statoolinfos/cache
+srv/statoolinfos/statoolinfos-cron.log
+srv/statoolinfos/well-known
+srv/statoolinfos/well-known/statoolinfos
+srv/statoolinfos/well-known/statoolinfos/organization-template.properties
+srv/statoolinfos/well-known/statoolinfos/services.properties
+srv/statoolinfos/well-known/statoolinfos/BOM
+srv/statoolinfos/well-known/statoolinfos/federation-template.properties
+srv/statoolinfos/well-known/statoolinfos/service-template.properties
+```
+
+Then, move the `statoolinfos.jar` file in `/srv/statoolinfos/bin/`.
 
 Create link:
 
@@ -60,6 +88,15 @@ Create link:
 cd /srv/statoolinfos/bin/ ; ln -s statoolinfos.sh statoolinfos
 ```
 
+Edit script in `/srv/statoolinfos/bin/` to target your federation configuration file.
+
+
+In case of bad language output, add these lines on top of cron file:
+
+```
+LANGUAGE=en_EN.UTF8
+LC_ALL=en_EN.UTF-8
+```
 
 ## Usage
 
@@ -90,18 +127,163 @@ Usage:
     statoolinfos list errlog                 <logfilesorconfigfile>  display http error log lines
 ```
 
-### htmlize removed
+## Simple federation configuration file
-The htmlize command is removed since 2024-07.
 
-As a reminder, the htmlize command generated absolutely all the pages needed for a static site.
+Example of `libre-service.eu.conf`:
+
+```
+# [Configuration] conf + organization + services + machines + metrics
+conf.class=federation
+conf.protocol=StatoolInfos-0.6.0
+
+conf.crawl.input=https://www.libre-service.eu/.well-known/statoolinfos/libre-service.eu.properties
+conf.crawl.cache=/srv/statoolinfos/cache/
+
+```
+
+The field `input` gives the federation properties URL file. Reminder, the StatoolInfos Protocol  requires that the federation properties file is exposed on the Web.
+
+The field `cache` gives local directory used as data cache.
+
+
+## Crawl
+
+The `statoolinfos crawl` command loads the federation configuration file, then downloads the federation properties file and download all files set in.
+
+In case of use with StatoolInfosWeb, never forget to give read permissions to Tomcat server. So, create a dedicated script would help.
+
+Example of script `/srv/statoolinfos/bin/crawl`:
+
+```
+#!/bin/bash
+
+echo "========== CRAWL at $(date  --iso-8601=seconds)" 
+cd $(dirname "$0")
+./statoolinfos crawl ../conf/federation.conf
+chmod -R g+r /srv/statoolinfos/cache
+chgrp -R tomcat /srv/statoolinfos/cache
+```
+
+Example of cron configuration `/etc/cron.d/statoolinfos`:
+
+```
+4 * * * * root /srv/statoolinfos/bin/crawl >> /srv/statoolinfos/statoolinfos-cron.log
+```
+
+Adjust your frequency according to your need. In case of large federation, once an hour is a good compromise.
+
+## Uptime
+
+The `statoolinfos uptime` command is very useful to collect the uptime of services. It's just to share  which services are down and since how many time. It is not a monitoring feature because an one hour check is enough for this. Actually, only website are checked.
+
+In case of use with StatoolInfosWeb, never forget to give read permissions to Tomcat server. So, create a dedicated script would help.
+
+Example of script `/srv/statoolinfos/bin/uptime`:
+
+
+```
+#!/bin/bash
+
+echo "========== UPTIME at $(date  --iso-8601=seconds)"
+cd $(dirname "$0")
+./statoolinfos uptime ../conf/federation.conf
+chmod -R g+r /srv/statoolinfos/cache
+chgrp -R tomcat /srv/statoolinfos/cache
+```
+
+Example of cron configuration `/etc/cron.d/statoolinfos`:
+
+```
+4 * * * * root /srv/statoolinfos/bin/uptime >> /srv/statoolinfos/statoolinfos-cron.log
+```
+
+One check per hour is a good idea. In the uptime page, the mouse over a yellow status icon show the list of the check results.
+
+In case of crawl, uptime and probe cron on the same computer, you can have different cron frequencies. It is better to have only script for call all them:
+
+```
+#!/bin/bash
+
+echo "========== REFRESH at $(date  --iso-8601=seconds)" 
+cd $(dirname "$0")
+./probe
+./crawl
+./uptime
+#./htmlize
+chmod -R g+r /srv/statoolinfos/cache
+chgrp -R tomcat /srv/statoolinfos/cache
+
+```
+
+And so your cron can be like that:
+
+```
+4 0,12,23 * * * root /srv/statoolinfos/bin/refresh >> /srv/statoolinfos/statoolinfos-cron.log
+4 1-11,13-22 * * * root /srv/statoolinfos/bin/uptime >> /srv/statoolinfos/statoolinfos-cron.log
+```
+
+
+## Htmlize command **removed**
+
+The `statoolinfos htmlize` command is removed since 2024-07.
+
+As a reminder, the htmlize command generated absolutely all the pages needed for a static website.
 
 As the number of pages generated became too large (> 10000 with 100 organizations), the decision was made to separate the html valuation into a separate project, StatoolInfosWeb.
 
 A dynamic web site allows to generate page only when it is necessary. 
 
-## Generate metrics files
 
-### Basics
+## Probe (Generate metrics files)
+
+###  Basics
+The `statoolinfos probe` command computes data sources to generate metric properties files. In case of already existings file, the data are loaded before the computation to be updated.
+
+In case of use with StatoolInfosWeb, never forget to give read permissions to Tomcat server. So, create a dedicated script would help.
+
+Example of script `/srv/statoolinfos/bin/probe`:
+
+```
+#!/bin/bash
+
+echo "========== PROBE at $(date  --iso-8601=seconds)" 
+cd $(dirname "$0")
+./statoolinfos probe -previousday ../conf/
+chmod -R g+r /srv/statoolinfos/cache
+chgrp -R tomcat /srv/statoolinfos/cache
+```
+
+Note: set a specific configuration file is not necessary, because you can have multiple service to probe. Only probe configuration files will be manage.
+
+Example of cron configuration `/etc/cron.d/statoolinfos`:
+
+```
+4 * * * * root /srv/statoolinfos/bin/probe >> /srv/statoolinfos/statoolinfos-cron.log
+```
+
+### HTTP Server configuration
+
+The probe feature generates properties files to expose on web. StatoolInfos protocol recommends to follow the well-known convention.
+
+Example of `/etc/apache2/statoolinfos.conf` generic configuration file:
+```
+  Alias "/.well-known/statoolinfos/" "/srv/statoolinfos/well-known/statoolinfos/"
+    <Directory "/srv/statoolinfos/well-known/statoolinfos">
+        Options +Indexes
+        Require all granted
+    </Directory>
+```
+
+Example of include directive in `/etc/apache2/sites-enabled/myservice.conf`:
+```
+<VirtualHost *:443>
+			[…]
+        Include statoolinfos.conf
+        […]
+</VirtualHost>
+```
+
+### Sample  configuration file
 
 Create a configuration file `/srv/statoolInfos/conf/foo.bar.org.conf`:
 
@@ -122,7 +304,7 @@ Generate the metric file for the first time:
 
 Create a cron file in `/etc/cron.d/statoolinfos` to update the metric file everyday:
 ```
-1 0,12 * * * root /srv/statoolinfos/bin/statoolinfos probe -previousday /srv/statoolinfos/conf/foo.bar.org.conf >> /srv/statoolinfos/cron.log
+4 0,12 * * * root /srv/statoolinfos/bin/statoolinfos probe -previousday /srv/statoolinfos/conf/foo.bar.org.conf >> /srv/statoolinfos/cron.log
 ```
 
 In case of several configuration files, just set the configuration directory (without wildcard):
@@ -291,6 +473,7 @@ conf.prob.httperrorlog.datetimepattern=
 Warning: to have month metric values, you have to set **retention log to 7 weeks or 50 days** in Nginx or Apache logrotate configuration.
 
 For Nginx, éditer le fichier `/etc/logrotate.d/nginx` :
+
 ```
 /var/log/nginx/*.log {
     weekly
@@ -299,9 +482,23 @@ For Nginx, éditer le fichier `/etc/logrotate.d/nginx` :
 ```
 
 For Apache, éditer le fichier `/etc/logrotate.d/apache2` :
+
 ```
 /var/log/apache2/*.log {
     weekly
     missingok
     rotate 7
 ```
+
+### Cron all task
+
+A situation you will encounter is the need to do several tasks from the same machine. In this case, avoid multiple cron in the same time. Put all in Bash script and call it with only one cron.
+
+Example:
+
+```
+4 0,12,23 * * * root /srv/statoolinfos/bin/refresh >> /srv/statoolinfos/statoolinfos-cron.log
+4 1-11,13-22 * * * root /srv/statoolinfos/bin/statoolinfos uptime /srv/statoolinfos/conf/libre-service.eu.conf >> /srv/statoolinfos/statoolinfos-cron.log
+
+```
+

build-appjar.xml

@@ -126,16 +126,22 @@
 
 			
 	    <!-- Copy stuff -->
+    	<echo message="==========> Copy Stuff" />
         <copy file="resources/scripts/${product.name}.sh" todir="${dist.dir}/" overwrite="true" />
         <chmod file="${dist.dir}/${product.name}.sh" perm="ugo+rx" />
 		<copy file="LICENSE" todir="${dist.dir}/" overwrite="true" failonerror="false" />
 		<!--copy file="README" todir="${dist.dir}/" overwrite="true" failonerror="false" /-->
 		<copy file="README.md" todir="${dist.dir}/" overwrite="true" failonerror="false" />
         <!--copy file="scripts/log4j.properties" todir="${dist.dir}/" overwrite="true" /-->
+    	<mkdir dir="${dist.dir}/srv" />
+    	<copy todir="${dist.dir}/srv/" overwrite="true" failonerror="false">
+    		<fileset dir="resources/srv" includes="**" /> 
+    	</copy>
+    	<echo message="==========>ZZZZ" />
     	
         <mkdir dir="${dist.dir}/conf" />
 		<copy todir="${dist.dir}/conf">
-			<fileset dir="${basedir}/resources/conf" includes="*" />
+			<fileset dir="${basedir}/resources/conf" includes="**" />
 		</copy>
         <!--
         <mkdir dir="${dist.dir}/man"/>

build.num

@@ -1,3 +1,3 @@
 #Build Number for ANT. Do not edit!
-#Sat Aug 17 23:38:50 CEST 2024
+#Mon Sep 23 04:40:53 CEST 2024
-build.number=1
+build.number=2

build.sh

@@ -5,7 +5,7 @@
 #
 function help
 {
-	echo "StatoolInfos build script."
+	echo "Build script."
 	echo "Usage: build.sh [ -h | -help | --help | -snapshot | -local | -full ]"
 	echo "     -h, -help, --help            display this help."
 	echo "     -snapshot, --snapshot        build a snapshot."
@@ -15,9 +15,9 @@ function help
 }
 
 #
-# Build snapshot.
+# Check env.
 #
-function build_snapshot
+function check_env
 {
 	okCount=0
 	
@@ -40,96 +40,13 @@ function build_snapshot
 	fi
 	
 	# Java version check.
+    JAVA_VERSION=17;
 	javaVersionCheck=`javac -version 2>&1`
-	if [[ "$javaVersionCheck" =~ ^.*\ 11. ]]; then
+	if [[ "$javaVersionCheck" =~ ^.*\ ${JAVA_VERSION}. ]]; then
-		echo "Java 11 version requirement..... OK"
+		echo "Java ${JAVA_VERSION} version requirement..... OK"
 		let "okCount+=1"
 	else
-		echo "Java 11 version requirement..... MISSING"
+		echo "Java ${JAVA_VERSION} version requirement..... MISSING"
-	fi
-	
-	if [ "$okCount" == 3 ]; then
-	    echo "Requirement OK"
-	    ant -f build-snapshot.xml
-	else
-	    echo "Requirement MISSING, build abort"
-	fi
-}
-
-#
-# Build local.
-#
-function build_local
-{
-	okCount=0
-	
-	# Ant check.
-	antCheck=`which ant`
-	if [[ "$antCheck" =~ ^/.* ]]; then
-		echo "Ant requirement................ OK"
-		let "okCount+=1"
-	else
-		echo "Ant requirement................ MISSING"
-	fi
-	
-	# Javac check.
-	javacCheck=`which javac`
-	if [[ "$javacCheck" =~ ^/.* ]]; then
-		echo "Javac requirement.............. OK"
-		let "okCount+=1"
-	else
-		echo "Javac requirement.............. MISSING"
-	fi
-	
-	# Java version check.
-	javaVersionCheck=`javac -version 2>&1`
-	if [[ "$javaVersionCheck" =~ ^.*\ 11. ]]; then
-		echo "Java 11 version requirement..... OK"
-		let "okCount+=1"
-	else
-		echo "Java 11 version requirement..... MISSING"
-	fi
-	
-	if [ "$okCount" == 3 ]; then
-	    echo "Requirement OK"
-	    ant -f build-local.xml
-	else
-	    echo "Requirement MISSING, build abort"
-	fi
-}
-
-#
-# Build tagandpush.
-#
-function build_tagandpush
-{
-	okCount=0
-	
-	# Ant check.
-	antCheck=`which ant`
-	if [[ "$antCheck" =~ ^/.* ]]; then
-		echo "Ant requirement................ OK"
-		let "okCount+=1"
-	else
-		echo "Ant requirement................ MISSING"
-	fi
-	
-	# Javac check.
-	javacCheck=`which javac`
-	if [[ "$javacCheck" =~ ^/.* ]]; then
-		echo "Javac requirement.............. OK"
-		let "okCount+=1"
-	else
-		echo "Javac requirement.............. MISSING"
-	fi
-	
-	# Java version check.
-	javaVersionCheck=`javac -version 2>&1`
-	if [[ "$javaVersionCheck" =~ ^.*\ 11. ]]; then
-		echo "Java 11 version requirement..... OK"
-		let "okCount+=1"
-	else
-		echo "Java 11 version requirement..... MISSING"
 	fi
 	
 	# Git check.
@@ -143,26 +60,28 @@ function build_tagandpush
 
 	if [ "$okCount" == 4 ]; then
 	    echo "Requirement OK"
-	    ant -f build-tagandpush.xml
 	else
 	    echo "Requirement MISSING, build abort"
+	    exit -1
 	fi
 }
 
+
 #
 # Main.
 #
 if [ "$#" -eq 0 ] || [ "$1" == "-h" ]  || [ "$1" == "-help" ]  || [ "$1" == "--help" ]; then
     help
-elif [ "$1" == "-snapshot" ] || [ "$1" == "--snapshot" ] ; then
-    build_snapshot
-elif [ "$1" == "-local" ] || [ "$1" == "--local" ] ; then
-    build_local
-elif [ "$1" == "-tagandpush" ] || [ "$1" == "--tagandpush" ] ; then
-    build_tagandpush
 else
-    echo "Invalid parameters."
+	check_env
-    help
+	if [ "$1" == "-snapshot" ] || [ "$1" == "--snapshot" ] ; then
+	    ant -f build-snapshot.xml
+	elif [ "$1" == "-local" ] || [ "$1" == "--local" ] ; then
+	    ant -f build-local.xml
+	elif [ "$1" == "-tagandpush" ] || [ "$1" == "--tagandpush" ] ; then
+	    ant -f build-tagandpush.xml
+	else
+    	echo "Invalid parameters."
+    	help
+    fi
 fi
-
-

resources/conf/README.md

@@ -0,0 +1 @@
+See the `srv/statoolinfos/conf` directory.

resources/conf/sample-web.conf

@@ -1,14 +0,0 @@
-#
-# Sample StatoolInfos config file.
-#
-# Warning: move this file outside the Git directory.
-
-conf.class=federation
-conf.protocol=StatoolInfos-0.5.0
-
-conf.crawl.input=https://www.libre-service.eu/.well-known/statoolinfos/libre-service.eu.properties
-conf.crawl.cache=/srv/statoolinfos/cache/
-
-conf.htmlize.categories=/srv/statoolinfos/inputs/categories/categories.properties
-conf.htmlize.input=https://www.libre-service.eu/.well-known/statoolinfos/libre-service.eu.properties
-conf.htmlize.directory=/srv/statoolinfos/www/

resources/conf/statoolinfos.cron

@@ -1,3 +0,0 @@
-LANGUAGE=fr_FR.UTF8
-LC_ALL=fr_FR.UTF-8
-/5 * * * * root /srv/statoolinfos/bin/statoolinfo.sh >> /srv/statoolinfos/statoolinfos-cron.log

resources/etc/apache2/statoolinfos.conf

@@ -0,0 +1,5 @@
+  Alias "/.well-known/statoolinfos/" "/srv/statoolinfos/well-known/statoolinfos/"
+    <Directory "/srv/statoolinfos/well-known/statoolinfos">
+        Options +Indexes
+        Require all granted
+    </Directory>

resources/etc/cron.d/statoolinfos

@@ -0,0 +1,2 @@
+4 0,12,23 * * * root /srv/statoolinfos/bin/refresh >> /srv/statoolinfos/statoolinfos-cron.log
+4 1-11,13-22 * * * root /srv/statoolinfos/bin/uptime >> /srv/statoolinfos/statoolinfos-cron.log

resources/srv/statoolinfos/bin/crawl

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+echo "========== CRAWL at $(date  --iso-8601=seconds)" 
+cd $(dirname "$0")
+./statoolinfos crawl ../conf/federation.conf
+chmod -R g+r /srv/statoolinfos/cache
+chgrp -R tomcat /srv/statoolinfos/cache

resources/srv/statoolinfos/bin/probe

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+echo "========== PROBE at $(date  --iso-8601=seconds)" 
+cd $(dirname "$0")
+./statoolinfos probe -previousday ../conf/
+chmod -R g+r /srv/statoolinfos/cache
+chgrp -R tomcat /srv/statoolinfos/cache

resources/srv/statoolinfos/bin/refresh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+echo "========== REFRESH at $(date  --iso-8601=seconds)" 
+cd $(dirname "$0")
+./probe
+./crawl
+./uptime
+#./htmlize
+chmod -R g+r /srv/statoolinfos/cache
+chgrp -R tomcat /srv/statoolinfos/cache

resources/srv/statoolinfos/bin/statoolinfos.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+
+# Optional environment settings:
+#   export LOG4J_CONFIGURATION_FILE="toto.properties"
+#   export LOG4J_LEVEL=ERROR
+# https://logging.apache.org/log4j/log4j-2.11.2/manual/configuration.html#System_Properties
+
+# Java check.
+javaCheck=`which java`
+if [[ "$javaCheck" =~ ^/.* ]]; then
+    #echo "Java requirement............... OK"
+    
+    # Optional system properties:
+    #   LOGFILE="-Dlog4j2.configurationFile=../../log4j2.properties"
+    #   LOGLEVEL="-Dlog4j2.level=ERROR"
+    #   IPV6ONLY="-Djava.net.preferIPv4Stack=false -Djava.net.preferIPv6Addresses=true"
+    # https://logging.apache.org/log4j/log4j-2.11.2/manual/configuration.html#System_Properties
+
+    java -Djava.awt.headless=true $IPV6ONLY $LOGFILE $LOGLEVEL -jar  "$(dirname "$0")"/statoolinfos.jar $@
+else
+    echo "Java requirement............... MISSING"
+fi

resources/srv/statoolinfos/bin/uptime

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+echo "========== UPTIME at $(date  --iso-8601=seconds)"
+cd $(dirname "$0")
+./statoolinfos uptime ../conf/federation.conf
+chmod -R g+r /srv/statoolinfos/cache
+chgrp -R tomcat /srv/statoolinfos/cache

resources/srv/statoolinfos/conf/sample-federation.conf

@@ -0,0 +1,8 @@
+# [Configuration]
+conf.class=federation
+conf.protocol=StatoolInfos-0.6.0
+
+conf.crawl.input=https://www.libre-service.eu/.well-known/statoolinfos/libre-service.eu.properties
+conf.crawl.cache=/srv/statoolinfos/cache/
+
+

resources/srv/statoolinfos/conf/sample-probe-http.conf

@@ -0,0 +1,8 @@
+# [Configuration]
+conf.class=service
+conf.protocol=StatoolInfos-0.6.0
+
+conf.probe.types=HttpAccessLog, HttpErrorLog
+conf.probe.httpaccesslog.file=/var/log/apache2/www.libre-service.eu/www.libre-service.eu-access.log*
+conf.probe.httperrorlog.file=/var/log/apache2/www.libre-service.eu/www.libre-service.eu-error.log*
+conf.probe.target=/srv/statoolinfos/well-known/statoolinfos/www.libre-service.eu-metrics.properties

resources/srv/statoolinfos/conf/sample-probe-minetest.conf

@@ -20,4 +20,4 @@ conf.probe.minetest.players.db.password=
 conf.probe.minetest.datafilepath=
 
 # Target file to write computed metrics. If file exists then it is renamed with '.bak'.
-conf.probe.target=/home/cpm/Projets/StatoolInfos/EnvTest/minetest/test.metrics
+conf.probe.target=/srv/statoolinfos/well-known/statoolinfo/www.myservice.org-metrics.properties

resources/srv/statoolinfos/conf/sample-probe-qrcode.conf

@@ -19,6 +19,6 @@ conf.probe.httpaccesslog.pattern=
 conf.probe.httperrorlog.file=/var/log/apache2/qrcode.libre-service.eu/qrcode.libre-service.eu-error.log*
 
 # Target file to write computed metrics. If file exists then it is renamed with '.bak'.
-conf.probe.target=/srv/statoolinfos/well-known/statoolinfos/qrcode.libre-service.eu.metrics
+conf.probe.target=/srv/statoolinfos/well-known/statoolinfos/qrcode.libre-service.eu-metrics.properties
 
 

resources/srv/statoolinfos/well-known/statoolinfos/BOM

@@ -0,0 +1 @@
+

resources/srv/statoolinfos/well-known/statoolinfos/federation-template.properties

@@ -0,0 +1,87 @@
+# federation.properties
+
+# [File]
+# Classe du fichier (valeur parmi {Federation, Organization, Service, Device}, obligatoire).
+file.class = federation
+
+# Version de l'ontologie utilisée utilisé (type STRING, recommandé).
+file.protocol = ChatonsInfos-0.5
+
+# Date et horaire de génération du fichier (type DATETIME, recommandé, ex. 2020-07-06T14:23:20).
+file.datetime = 
+
+# Nom du générateur du fichier (type STRING, recommandé).
+file.generator = 
+
+
+# [Federation]
+# Nom de la fédération (type STRING, obligatoire).
+federation.name= 
+
+# Description de la fédération (type STRING, recommandé). 
+federation.description = 
+
+# Lien du site web de la fédération (type URL, recommandé).
+federation.website = 
+
+# Lien du logo de la fédération (type URL, recommandé).
+federation.logo = 
+
+# Lien de la page web de contact de la fédération (type URL, recommandé).
+federation.contact.url = 
+
+# Courriel de contact de la fédération (type EMAIL, recommandé).
+federation.contact.email = 
+
+# Lien du compte Twitter de la fédération (type URL, optionnel).
+federation.socialnetworks.twitter =
+
+# Lien de la page Facebook de la fédération (type URL, optionnel).
+federation.socialnetworks.facebook =
+
+# Lien du compte Mastodon de la fédération (type URL, optionnel).
+federation.socialnetworks.mastodon =
+
+# Lien du compte Diaspora de la fédération (type URL, optionnel).
+federation.socialnetworks.diaspora =
+
+# Lien du compte PeerTube de la fédération(type URL, optionnel).
+federation.socialnetworks.peertube =
+
+# Lien du compte Funkwhale de la fédération (type URL, optionnel).
+federation.socialnetworks.funkwhale =
+
+# Lien du compte Pixelfeld de la fédération (type URL, optionnel).
+federation.socialnetworks.pixelfeld =
+
+# Lien du compte Mobilizon de la fédération (type URL, optionnel).
+federation.socialnetworks.mobilizon =
+
+# Lien de la page web des mentions légales de la fédération (type URL, recommandé).
+federation.legal.url = 
+
+# Lien de la documentation web de la fédération (type URL, recommandé).
+federation.documentation.url = 
+
+# Lien de la documentation technique de la fédération (type URL, recommandé).
+federation.guide.technical = 
+
+# Lien des tutoriels web de la fédération (type URL, recommandé).
+federation.guide.technical = 
+
+# Date de naissance de la fédération (type DATE (AAAA-MM-JJ ou JJ/MM/AAAA), recommandé).
+federation.startdate = 
+
+
+# [Subs]
+# Un lien vers un fichier properties complémentaire (type URL, optionnel)
+# Une clé (nomination libre) pour chacune de vos organisations,
+# par exemple : subs.monchaton = https://www.monchaton.ext/.well-known/monchaton.properties 
+subs.01 =
+
+
+# [Metrics]
+
+
+
+

resources/srv/statoolinfos/well-known/statoolinfos/organization-template.properties

@@ -0,0 +1,136 @@
+# membres.properties
+
+# [File]
+# Classe du fichier (valeur parmi {Federation, Organization, Service, Device}, obligatoire).
+file.class = organization
+
+# Version de l'ontologie utilisée utilisé (type STRING, recommandé, ex. ChatonsInfos-0.1).
+file.protocol = ChatonsInfos-0.5
+
+# Date et horaire de génération du fichier (type DATETIME, recommandé, ex. 2020-07-06T14:23:20).
+file.datetime = 
+
+# Nom du générateur du fichier (type STRING, recommandé, ex. Christian avec ses doigts).
+file.generator = 
+
+
+# [Organisation]
+# Nom de l'organisation (type STRING, obligatoire, ex. LibreServiceEU).
+organization.name = 
+
+# Description de l'organisation (type STRING, recommandé, ex. LibreServiceEU est le chaton de Devinsy).
+organization.description = 
+
+# Type d'organisation (un parmi {ASSOCIATION, INFORMAL, COOPERATIVE, MICROCOMPANY, COMPANY, INDIVIDUAL, OTHER}, obligatoire).
+organization.type =
+
+# Lien du site web de l'organisation (type URL, recommandé, ex. https://www.libre-service.eu/).
+organization.website = 
+
+# Lien du logo de l'organisation (type URL, recommandé, ex. https://www.libre-service.eu/.well-known/statoolinfos/libre-service.eu-logo-carre.svg).
+organization.logo = 
+
+# Liens vers les comptes réseaux sociaux de l'organisation (type URL, optionnel).
+# Liste non exhaustive à laquelle vous pouvez ajouter d'autres services.
+organization.socialnetworks.diaspora =
+organization.socialnetworks.facebook =
+organization.socialnetworks.funkwhale =
+organization.socialnetworks.mastodon =
+organization.socialnetworks.pleroma = 
+organization.socialnetworks.mobilizon =
+organization.socialnetworks.peertube =
+organization.socialnetworks.pixelfeld =
+organization.socialnetworks.twitter =
+
+# Adresse vers les salons/équipes de discussion publics de l'organisation (type STRING, optionnel).
+# Liste non exhaustive à laquelle vous pouvez ajouter d'autres services.
+organization.chatrooms.xmpp =
+organization.chatrooms.irc = 
+organization.chatrooms.matrix =
+organization.chatrooms.rocketchat =
+organization.chatrooms.mattermost =
+
+# Nom du propriétaire de l'organisation (type STRING, optionnel, ex. Devinsy).
+organization.owner.name = 
+
+# Lien du site web du propriétaire de l'organisation (type URL, optionnel, ex. https://www.devinsy.fr/).
+organization.owner.website = 
+
+# Lien du logo du propriétaire de l'organisation (type URL, optionnel, ex. https://www.devinsy.fr/logo_devinsy.svg).
+organization.owner.logo = 
+
+# Lien de la page web de contact de l'organisation (type URL, recommandé, ex. https://www.libre-service.eu/contact.html).
+organization.contact.url = 
+
+# Courriel de contact de l'organisation (type EMAIL, recommandé, ex. contact@libre-service.eu).
+organization.contact.email = 
+
+# Lien de la page des mentions légales de l'organisation (type URL, recommandé, ex. https://www.libre-service.eu/mentions_legales.html).
+organization.legal.url = 
+
+# Lien de la documentation technique de l'organisation (type URL, recommandé, ex. https://forge.devinsy.fr/libre-service.eu/documentation).
+organization.guide.technical = 
+
+# Lien de la documentation utilisateur de l'organisation (type URL, recommandé, ex. https://www.libre-service.eu/services.xhtml).
+organization.guide.user = 
+
+# Statut de l'organisation (un parmi {ACTIVE, IDLE, AWAY}, obligatoire).
+organization.status.level =
+
+# Description du statut de l'organisation (type STRING, optionnel, ex. en sommeil).
+organization.status.description = 
+
+# Date de création de l'organisation (type DATE, recommandé, ex. 08/11/2018).
+organization.startdate = 
+
+# Date de fermeture de l'organisation (type DATE, optionnel, ex. 22/02/2022).
+organization.enddate =
+
+# Date d'entrée dans le collectif (type DATE, obligatoire, ex. 08/11/2018).
+organization.memberof.chatons.startdate =
+
+# Date de sortie du collectif (type DATE, optionnel, ex. 08/11/2019).
+organization.memberof.chatons.enddate =
+
+# Statut en tant que membre de l'organisation (un parmi {ACTIVE, IDLE, AWAY}, obligatoire).
+organization.memberof.chatons.status.level =
+
+# Description du statut en tant que membre de l'organisation (type STRING, optionnel, ex. en sommeil).
+organization.memberof.chatons.status.description =
+
+# Pays de l'organisation (type STRING, recommandé, ex. France).
+organization.country.name =
+
+# Code pays de l'organisation (type COUNTRY_CODE sur 2 caractères, obligatoire, ex.ex. FR ou BE ou CH ou DE ou GB).
+# Table ISO 3166-1 alpha-2 : https://fr.wikipedia.org/wiki/ISO_3166-1#Table_de_codage
+organization.country.code =
+
+# Géolocalisation de l'organisation
+# Coordonnées GPS
+# Latitude (type DECIMAL_DEGREE, recommandé, format DD, ex. 15,23456).
+organization.geolocation.latitude =
+
+# Longitude (type DECIMAL_DEGREE, recommandé, format DD, ex. -30,67890).
+organization.geolocation.longitude =
+
+# Adresse (type STRING, recommandé, ex. 1 rue croquette, 92370 Chaville).
+organization.geolocation.address =
+
+# Liens vers les services de paiement permettant de récolter des donations pour votre chaton (type URL, optionnel).
+# Dans le cas d'une solution maison (exemple : pont vers votre banque), choisir "organization.funding.custom".
+# Liste non exhaustive à laquelle vous pouvez ajouter d'autres services.
+organization.funding.liberapay =
+organization.funding.tipee = 
+organization.funding.helloasso =
+organization.funding.paypal =
+organization.funding.custom =
+
+
+# [Subs]
+# Un lien vers un fichier properties complémentaire (type URL, optionnel)
+# Une clé (nomination libre) pour chacun de vos services,
+# par exemple pour un service etherpad : subs.etherpad = https://www.monchaton.ext/.well-known/etherpad.properties 
+subs.foo1 = 
+
+
+# [Metrics]

resources/srv/statoolinfos/well-known/statoolinfos/service-template.properties

@@ -0,0 +1,163 @@
+# service.properties
+
+#WARNING : cette fiche service ne concerne que les services logiciels
+
+# [File]
+# Classe du fichier (valeur parmi {Federation, Organization, Service, Device}, obligatoire).
+file.class = service
+
+# Version de l'ontologie utilisée utilisé (type STRING, recommandé).
+file.protocol = ChatonsInfos-0.5
+
+# Date et horaire de génération du fichier (type DATETIME, recommandé, ex. 2020-07-06T14:23:20).
+file.datetime = 
+
+# Nom du générateur du fichier (type STRING, recommandé).
+file.generator = 
+
+
+# [Service]
+# Nom du service (type STRING, obligatoire).
+service.name = 
+
+# Description du service (type STRING, recommandé).
+service.description = 
+
+# Lien du site web du service (type URL, obligatoire - si pas possible, merci de créer une page de présentation du service).
+service.website = 
+
+# Lien du logo du service (type URL, recommandé, ex. https://www.libre-service.eu/.well-known/statoolinfos/logo.svg).
+service.logo = 
+
+# Lien de la page web des mentions légales du service (type URL, recommandé).
+service.legal.url = 
+
+# Lien de la documentation web du service (type URL, recommandé).
+service.guide.technical = 
+
+# Lien des aides web pour le service (type URL, recommandé).
+service.guide.user = 
+
+# Lien de la page de support du service (type URL, recommandé).
+service.contact.url = 
+
+# Courriel du support du service (type EMAIL, recommandé).
+service.contact.email = 
+
+# Date d'ouverture du service (type DATE, obligatoire, ex. 22/02/2022).
+service.startdate = 
+
+# Date de fermeture du service (type DATE, optionnel, ex. 22/02/2022).
+service.enddate = 
+
+# Statut du service (un parmi {OK, WARNING, ALERT, ERROR, OVER, VOID}, obligatoire).
+# OK : tout va bien (service en fonctionnement nominal).
+# WARNING : attention (service potentiellement incomplet, maintenance prévue, etc.).
+# ALERT : alerte (le service connait des dysfonctionnements, le service va bientôt fermer, etc.).
+# ERROR : problème majeur (service en panne).
+# OVER : terminé (le service n'existe plus).
+# VOID : indéterminé (service non ouvert officiellement, configuration ChatonsInfos en cours, etc.).
+service.status.level = 
+
+# Description du statut du service (type STRING, optionnel, ex. mise à jour en cours)
+service.status.description = 
+
+# Inscriptions requises pour utiliser le service (un ou plusieurs parmi {None, Free, Member, Client}, obligatoire, ex. Free,Member).
+# None : le service s'utilise sans inscription.
+# Free : inscription ouverte à tout le monde et gratuite.
+# Member : inscription restreinte aux membres (la notion de membre pouvant être très relative, par exemple, une famille, un cercle d’amis, adhérents d'association…).
+# Client : inscription liée à une relation commerciale (facture…).
+service.registration =
+
+# Capacité à accueillir de nouveaux utilisateurs (un parmi {OPEN, FULL}, obligatoire).
+# OPEN : le service accueille de nouveaux comptes.
+# FULL : le service n'accueille plus de nouveau compte pour l'instant.
+service.registration.load = 
+
+# Type d'installation du service, une valeur parmi {DISTRIBUTION, PROVIDER, PACKAGE, TOOLING, CLONEREPO, ARCHIVE, SOURCES, CONTAINER}, obligatoire.
+# DISTRIBUTION : installation via le gestionnaire d'une distribution (apt, yum, etc.).
+# PROVIDER : installation via le gestionnaire d'une distribution configuré avec une source externe (ex. /etc/apt/source.list.d/foo.list).
+# PACKAGE : installation manuelle d'un paquet compatible distribution (ex. dpkg -i foo.deb).
+# TOOLING : installation via un gestionnaire de paquets spécifique, différent de celui de la distribution (ex. pip…).
+# CLONEREPO : clone manuel d'un dépôt (git clone…).
+# ARCHIVE : application récupérée dans un tgz ou un zip ou un bzip2…
+# SOURCES : compilation manuelle à partir des sources de l'application.
+# CONTAINER : installation par containeur (Docker, Snap, Flatpak, etc.).
+# L'installation d'un service via un paquet Snap avec apt sous Ubuntu doit être renseigné CONTAINER.
+# L'installation d'une application ArchLinux doit être renseignée DISTRIBUTION.
+# L'installation d'une application Yunohost doit être renseignée DISTRIBUTION.
+service.install.type =
+
+
+# [Software]
+# Nom du logiciel (type STRING, obligatoire).
+software.name =
+
+# Lien du site web du logiciel (type URL, recommandé).
+software.website =
+
+# Lien web vers la licence du logiciel (type URL, obligatoire).
+software.license.url = 
+
+# Nom de la licence du logiciel (type STRING, obligatoire).
+software.license.name =
+
+# Version du logiciel (type STRING, recommandé).
+software.version = 
+
+# Lien web vers les sources du logiciel (type URL, recommandé).
+software.source.url =
+
+# Liste de modules optionnels installés (type VALUES, optionnel, ex. Nextcloud-Calendar,Nextcloud-Talk).
+software.modules =
+
+
+# [Host]
+# Nom de l'hébergeur de la machine qui fait tourner le service, dans le cas d'un auto-hébergement c'est vous ! (type STRING, obligatoire).
+host.name = 
+
+# Description de l'hébergeur (type STRING, optionnel).
+host.description = 
+
+# Nom générique de la distribution installée sur le serveur (type STRING, obligatoire, ex. YunoHost).
+host.server.distribution = 
+
+# Type de serveur (un parmi {NANO, PHYSICAL, VIRTUAL, SHARED, CLOUD}, obligatoire, ex. PHYSICAL).
+#   NANO : nano-ordinateur (Raspberry Pi, Olimex…)
+#   PHYSICAL : machine physique
+#   VIRTUAL : machine virtuelle
+#   SHARED : hébergement mutualisé
+#   CLOUD : infrastructure multi-serveurs
+host.server.type = 
+
+# Type d'hébergement (un parmi {HOME, HOSTEDBAY, HOSTEDSERVER, OUTSOURCED}, obligatoire, ex. HOSTEDSERVER).
+#   HOME : hébergement à domicile
+#   HOSTEDBAY : serveur personnel hébergé dans une baie d'un fournisseur
+#   HOSTEDSERVER : serveur d'un fournisseur
+#   OUTSOURCED : infrastructure totalement sous-traitée
+host.provider.type =
+
+# Si vous avez du mal à remplir les champs précédents, ce tableau pourra vous aider :
+#                  NANO    PHYSICAL    VIRTUAL    SHARED    CLOUD
+# HOME              pm        pm          vm      shared    cloud
+# HOSTEDBAY         pm        pm          vm      shared    cloud
+# HOSTEDSERVER      --        pm          vm      shared    cloud
+# OUTSOURCED        --        --         vps      shared    cloud
+# Légendes : pm : physical machine ; vm : virtual machine ; vps : virtual private server.
+
+# Nom du logiciel hyperviseur (type STRING, optionnel, ex. KVM).
+host.provider.hypervisor = 
+
+# Pays de l'hébergeur (type STRING, recommandé).
+host.country.name =
+
+# Code pays de l'hébergeur (type COUNTRY_CODE sur 2 caractères, obligatoire, ex. FR ou BE ou CH ou DE ou GB).
+# Table ISO 3166-1 alpha-2 : https://fr.wikipedia.org/wiki/ISO_3166-1#Table_de_codage
+host.country.code =
+
+
+# [Subs]
+# Un lien vers un fichier properties complémentaire (type URL, optionnel).
+# Une clé (nomination libre) pour chacun de vos métriques spécifiques,
+# par exemple pour un service etherpad : subs.metrics-etherpad = https://www.monchaton.ext/.well-known/metrics-etherpad.properties 
+subs.foo = 

resources/srv/statoolinfos/well-known/statoolinfos/services.properties

@@ -0,0 +1,43 @@
+# File + organization + services + machines + metrics
+
+# [File]
+file.class=organization
+file.generator=Cpm
+file.datetime=2022-07-22T17:35:58
+file.protocol=StatoolInfos-0.5
+
+# [Organization]
+organization.name=Services au public
+organization.description=Les services publics de Libre-service.eu
+organization.website=https://www.libre-service.eu/
+organization.logo=https://www.libre-service.eu/.well-known/statoolinfos/libre-service.eu-logo-public.png
+organization.status.level=ACTIVE
+organization.status.description=En activité
+organization.owner.name=Libre-service.eu
+organization.owner.website=https://www.libre-service.eu/
+organization.owner.logo=https://www.libre-service.eu/.well-known/statoolinfos/libre-service.eu-logo-carre.png
+organization.contact.url=https://www.libre-service.eu/contact.xhtml
+organization.contact.email=contact@libre-service.eu
+organization.socialnetworks.mastodon=
+organization.legal.url=https://www.libre-service.eu/mentions-legales.xhtml
+organization.guide.user=https://www.libre-service.eu/
+organization.guide.technical=https://forge.devinsy.fr/libre-service.eu/documentation
+organization.startdate=01/10/2021
+organization.enddate=
+organization.memberof.libreserviceeu.status.level=ACTIVE
+organization.memberof.libreserviceeu.status.description=
+organization.memberof.libreserviceeu.startdate=01/10/2021
+organization.memberof.libreserviceeu.enddate=
+organization.country.name=France
+organization.country.code=FR
+organization.type=INFORMAL
+
+# [Subs]
+subs.audio=https://audio.libre-service.eu/.well-known/statoolinfos/audio.libre-service.eu.properties
+subs.minetest=https://minetest.libre-service.eu/.well-known/statoolinfos/minetest.libre-service.eu.properties
+subs.pad=https://pad.libre-service.eu/.well-known/statoolinfos/pad.libre-service.eu.properties
+subs.paste=https://paste.libre-service.eu/.well-known/statoolinfos/paste.libre-service.eu.properties
+subs.qrcode=https://qrcode.libre-service.eu/.well-known/statoolinfos/qrcode.libre-service.eu.properties
+subs.visio=https://visio.libre-service.eu/.well-known/statoolinfos/visio.libre-service.eu.properties
+
+# [Metrics]

src/fr/devinsy/statoolinfos/StatoolInfosLauncher.java

@@ -72,8 +72,8 @@ public final class StatoolInfosLauncher
             else
             {
                 //
-                Level logEnvLevel = Level.getLevel(StringUtils.defaultString(System.getenv().get("LOG4J_LEVEL"), ""));
+                Level logEnvLevel = Level.getLevel(StringUtils.defaultString(System.getenv().get("LOG4J_LEVEL"), " "));
-                Level logPropertyLevel = Level.getLevel(StringUtils.defaultString(System.getProperty("log4j2.level", "")));
+                Level logPropertyLevel = Level.getLevel(StringUtils.defaultString(System.getProperty("log4j2.level", " ")));
 
                 Level level;
                 if (logPropertyLevel != null)

src/fr/devinsy/statoolinfos/metrics/httpaccess/HttpAccessLogAnalyzer.java

@@ -307,7 +307,21 @@ public class HttpAccessLogAnalyzer
 
     /**
      * Checks if is page.
-     *
+     * 
+     * <pre>
+     * null             => false
+     * ""               => false
+     * "     "          => false
+     * "GET /foo"       => true
+     * "GET /foo42"     => true
+     * "GET /foo.cgi"   => true
+     * "GET /foo.htm"  => true
+     * "GET /foo.html"  => true
+     * "GET /foo.php"   => true
+     * "GET /foo.xhtml"  => true
+     * "GET /foo.jpg"   => false
+     * </pre>
+     * 
      * @param request
      *            the request
      * @return true, if is page

src/fr/devinsy/statoolinfos/metrics/httpaccess/HttpAccessLogParser.java

@@ -34,7 +34,7 @@ public class HttpAccessLogParser
     // '"$request" $status $body_bytes_sent '
     // '"$http_referer" "$http_user_agent"';
     public static final Pattern COMBINED_PATTERN = Pattern.compile(
-            "^(?<remoteAddress>[a-fA-F0-9\\:\\.]+) - (?<remoteUser>[^\\[]+) \\[(?<time>[^\\]]+)\\] \"(?<request>([^\"]|\\\")*)\" (?<status>\\d+) (?<bodyBytesSent>\\d+) \"(?<referer>([^\"]|\\\")*)\" \"(?<userAgent>([^\"]|\\\")*)\".*$");
+            "^(?<remoteAddress>[a-fA-F0-9\\:\\.]+) - (?<remoteUser>[^\\[]+) \\[(?<time>[^\\]]+)\\] \"(?<request>(?>[^\"]|\\\")*)\" (?<status>\\d+) (?<bodyBytesSent>\\d+) \"(?<referer>(?>[^\"]|\\\")*)\" \"(?<userAgent>(?>[^\"]|\\\")*)\".*$");
 
     public static final DateTimeFormatter DATETIME_FORMATTER = DateTimeFormatter.ofPattern("dd/MMM/yyyy:HH:mm:ss Z").withLocale(Locale.ENGLISH);
 

test/fr/devinsy/statoolinfos/metrics/httpaccess/HttpAccessLogParserTest.java

@@ -40,7 +40,7 @@ public class HttpAccessLogParserTest
      *             the exception
      */
     @Test
-    public void test01() throws Exception
+    public void testParseLog01() throws Exception
     {
         // Nominal line.
         String line = "172.104.137.47 - - [30/Apr/2023:23:25:15 +0200] \"GET /default.jsp HTTP/1.1\" 302 534 \"-\" \"curl/7.54.0\"";
@@ -59,6 +59,22 @@ public class HttpAccessLogParserTest
 
         line = "10.9.74.87 - - [03/Aug/2023:21:11:59 +0200] \"GET /plus/flink.php?dopost=save&c=cat%20/etc/passwd HTTP/1.1\" 302 5438 \"<?php \\\"system\\\"($c);die;/*ref\" \"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML like Gecko) Chrome/44.0.2403.155 Safari/537.36\"";
         Assert.assertNotNull(HttpAccessLogParser.parseLog(line));
+
+        line = "41.80.118.70 - - [04/Jan/2024:00:38:58 +0100] \"GET /services/audio.xhtml?url=http://go.a.gle.email.2.%5C%5Cn1@sarahjohttonw.estbrooxxertrew.e.r@hu.fe.ng.k.ua.ngniu.bi..uk41@www.zaxxle@silxxa.wooxx.o.r.t.h@ba.tt.le9.578@jxd.1.4.7m.nb.v.3.6.9.cx.z.9"
+                + "51.4@ex.p.lo.si.v.edhq.g@sixxia.wooxx.o.r.t.h@r.eces.si.v.e.x.g.z@leaxxa.lanxxon@vi.rt.u.ali.rd.j@h.att.ie.m.c.d.o.w.e.ll2.56.6.3@buxxon.rene@fullxxuestickyriddl.edyxxmi.c.t.r.a@johndf.gfjhfgjf.ghfdjfhjhjhjfdgh@sybbr%3Er.eces.si.v.e.x.g.z@lexxna.l"
+                + "axxton@c.o.nne.c.t.tn.tu@go.a.gle.email.2.%5C%5C%5C%5C%5C%5C%5C%5Cn1@saxxhjohxxonw.estbxxokbertrew.e.r@hu.fe.ng.k.ua.nxxiu.bi..uk41@www.zxxele@sixxia.woxxw.o.r.t.h@fullgluxxtickyriddl.edyxxmi.c.t.r.a@johndf.gfjhfgjf.ghfdjfhjhjhjfdgh@sybbr%3Er.eces"
+                + ".si.v.e.x.g.z@lexxna.lxxgton@c.o.nne.c.t.tn.tu@go.a.gle.email.2.%5C%5C%5C%5C%5C%5C%5C%5Cn1@sarahxxnsonw.estbrookbxxtrew.e.r@hu.fe.ng.k.ua.nxxiu.bi..uk41@www.zaxxle@silxxa.wooxx.o.r.t.h@p.a.r.a.ju.mp.e.r.sj.a.s.s.en20.14@maxxalena.tuxx@h.att.ie.m."
+                + "c.d.o.w.e.ll2.56.6.3buxxon.rene@c.o.nne.c.t.tn.tu@go.a.gle.email.2.%5C%5Cn1@saxxhjohnsonw.estbrooxxertrew.e.r@hu.fe.ng.k.ua.nxxiu.bi..uk41@www.zxxele@silvxx.wooxx.o.r.t.h@winkxxr-sanxxini.it/info/mwst01i.pdf/rk=0/rs=fzqfiq9omocv.7bggtuxxnthpge-%3F"
+                + "a%5B%5D=%3Ca+href%3Dhttps%3A%2F%2Fwww.rssxxg.com%2Frequest.php%3Freq%3Dfurl%26i%3D3759037%26r%3D17559%26url%3Dhttp%253A%252F%252Fbuxxssayuk.us%3xxuy+essays%3C%2Fa%3E%3Cmeta+http-equiv%3Drefresh+content%3D0%3Burl%3Dhttps%3A%2F%2Fwww.spxxtsbook.ag%2"
+                + "Fctr%2Facctmgt%2Fpl%2FopxxLink.ctr%3FctrPage%3Dhttps%3A%2F%2Fbuxxssayuk.us%2F+%2F%3E HTTP/1.0\" 200 4521 \"https://www.toxoyz.com/t/spip_cookie.php?url=http://go.a.gle.email.2.%5C%5Cn1@sarxxxohnsonw.estbrxxkbertrew.e.r@hu.fe.ng.k.ua.nxxiu.bi..uk"
+                + "41@www.zaxxle@silvia.wooxx.o.r.t.h@ba.tt.le9.578@jxd.1.4.7m.nb.v.3.6.9.cx.z.951.4@ex.p.lo.si.v.edhq.g@sixxia.wooxx.o.r.t.h@r.eces.si.v.e.x.g.z@xxnna.lxxxton@vi.rt.u.ali.rd.j@h.att.ie.m.c.d.o.w.e.ll2.56.6.3@burton.rene@fullgxxestickyriddl.exxxami."
+                + "c.t.r.a@johndf.gfjhfgjf.ghfdjfhjhjhjfdgh@sybbr%3Er.eces.si.v.e.x.g.z@leaxxa.laxxton@c.o.nne.c.t.tn.tu@go.a.gle.email.2.%5C%5C%5C%5C%5C%5C%5C%5Cn1@sarxxjohnxxnw.estbroxxbertrew.e.r@hu.fe.ng.k.ua.ngxxu.bi..uk41@www.zxxele@silxxa.woxxw.o.r.t.h@fullgl"
+                + "uesxxckyriddl.exxnami.c.t.r.a@johxxf.gfjhfgjf.ghfdjfhjhjhjfdgh@sybbr%3Er.eces.si.v.e.x.g.z@lexxna.laxxton@c.o.nne.c.t.tn.tu@go.a.gle.email.2.%5C%5C%5C%5C%5C%5C%5C%5Cn1@sarxxjohnxxnw.estbxxokbertrew.e.r@hu.fe.ng.k.ua.ngniu.bi..ux41@www.zaxxle@sxxvi"
+                + "a.wooxx.o.r.t.h@p.a.r.a.ju.mp.e.r.sj.a.s.s.en20.14@magxxlena.txxn@h.att.ie.m.c.d.o.w.e.ll2.56.6.3burxxn.rene@c.o.nne.c.t.tn.tu@go.a.gle.email.2.%5C%5Cn1@sarahjohxxonw.estbrookxxrtrew.e.r@hu.fe.ng.k.ua.nxxiu.bi..ux41@www.zxxele@sixxia.woxxw.o.r.t.h"
+                + "@winxxer-sanxxini.it/info/mwst01i.pdf/rk=0/rs=fzqfixxomocv.7bggtuxxnthpge-%3Fa%5B%5D=%3Ca+href%3Dhttps%3A%2F%2Fwww.rsxxng.com%2Frequest.php%3Freq%3Dfurl%26i%3D3759037%26r%3D17559%26url%3Dhttp%253A%252F%252Fbuyexxayuk.us%3Ebuy+essays%3C%2Fa%3E%3Cme"
+                + "ta+http-equiv%3Drefresh+content%3D0%3Burl%3Dhttps%3A%2F%2Fwww.sportxxook.ag%2Fctr%2Facctmgt%2Fpl%2Fopenxxnk.ctr%3FctrPage%3Dhttps%3A%2F%2Fbuxxssayuk.us%2F+%2F%3E\" \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Ch"
+                + "rome/114.0.0.0 Safari/537.36\"";
+        Assert.assertNotNull(HttpAccessLogParser.parseLog(line));
     }
 
     /**

test/fr/devinsy/statoolinfos/metrics/httpaccess/HttpAccessLogsAnalyzerTest.java

@@ -38,6 +38,27 @@ import fr.devinsy.statoolinfos.util.FilesUtils;
  */
 public class HttpAccessLogsAnalyzerTest
 {
+    /**
+     * Checks if is page test 01.
+     */
+    @Test
+    public void isPageTest01()
+    {
+        Assert.assertFalse(HttpAccessLogAnalyzer.isPage(null));
+        Assert.assertFalse(HttpAccessLogAnalyzer.isPage(""));
+        Assert.assertFalse(HttpAccessLogAnalyzer.isPage("     "));
+
+        Assert.assertTrue(HttpAccessLogAnalyzer.isPage("GET /foo"));
+        Assert.assertTrue(HttpAccessLogAnalyzer.isPage("GET /foo42"));
+        Assert.assertTrue(HttpAccessLogAnalyzer.isPage("GET /foo.html"));
+        Assert.assertTrue(HttpAccessLogAnalyzer.isPage("GET /foo.HTML"));
+        Assert.assertTrue(HttpAccessLogAnalyzer.isPage("GET /foo.HtMl"));
+        Assert.assertTrue(HttpAccessLogAnalyzer.isPage("GET /foo.HtMl"));
+
+        Assert.assertTrue(HttpAccessLogAnalyzer.isPage("GET /foo/bar/foo.php"));
+        Assert.assertFalse(HttpAccessLogAnalyzer.isPage("GET /foo.jpg"));
+    }
+
     /**
      * @throws Exception
      */