- added robots.txt to nginx container

- sitemaps are now generated in the entrypoint script

clarin-dev2clarin.sh

@@ -6,10 +6,11 @@ perl -pi -e 's/clarin-dev/clarin/g' dockerfiles/commul-customization/local.prope
 perl -pi -e 's/clarin-dev/clarin/g' dockerfiles/commul-customization/default-ssl
 
 perl -pi -e 's/clarin-dev/clarin/g' dockerfiles/commul-customization/aai.js
-perl -pi -e 's/clarin-dev/clarin/g' dockerfiles/commul-customization/aai_config.js 
+perl -pi -e 's/clarin-dev/clarin/g' dockerfiles/commul-customization/aai_config.js
 perl -pi -e 's/clarin-dev/clarin/g' dockerfiles/commul-customization/aa-statistics.php
 perl -pi -e 's/clarin-dev/clarin/g' dockerfiles/commul-customization/clarin.eurac.edu.template.metadata.xml
-perl -pi -e 's/clarin-dev/clarin/g' dockerfiles/commul-customization/webpage/index.html 
+perl -pi -e 's/clarin-dev/clarin/g' dockerfiles/commul-customization/webpage/index.html
+perl -pi -e 's/clarin-dev/clarin/g' dockerfiles/commul-customization/robots.txt
 
 # adapt URL and prefix for handle server
 perl -pi -e 's/20.500.12084/20.500.12124/g' dockerfiles/commul-customization/config.dct
@@ -22,5 +23,5 @@ perl -pi -e 's/clarin-dev/clarin/g' dockerfiles/docker-compose.yml
 echo "Modified all files to point to clarin.eurac.edu instead of clarin-dev.eurac.edu."
 
 # adapt namespace in kubernetes yaml files
-sed -i 's/dspace-dev/dspace/' kubernetes/*.yaml 
+sed -i 's/dspace-dev/dspace/' kubernetes/*.yaml
 perl -pi -e 's/clarin-dev/clarin/g' kubernetes/dspace-ingress.yaml

dockerfiles/Dockerfile.nginx

@@ -49,6 +49,9 @@ RUN chmod a+x /etc/init.d/nginx
 RUN ln -s /opt/nginx/sbin/nginx /usr/sbin/nginx
 # copy over static html
 COPY commul-customization/webpage/ /opt/nginx/html/
+# copy over robots.txt
+COPY commul-customization/robots.txt /opt/nginx/html/
+RUN chown www-data:www-data /opt/nginx/html/robots.txt
 
 #RUN mkdir /opt/nginx/html/img
 #COPY commul-customization/index.html /opt/nginx/html/

dockerfiles/commul-customization/default-ssl

@@ -145,8 +145,8 @@ server {
 	}
 
   # remove the robots and favicon from the logs
-  location ~ /robots.txt$  { access_log off; log_not_found off; }
-#  location ~ ^/favicon.ico$ { access_log off; log_not_found off; }
+#  location ~ /robots.txt$  { access_log off; log_not_found off; }
+  location ~ ^/favicon.ico$ { access_log off; log_not_found off; }
 
   # this prevents hidden files (beginning with a period) from being served
   location ~ /\.           { access_log off; log_not_found off; deny all; }

dockerfiles/commul-customization/entrypoint.sh

@@ -2,7 +2,7 @@
 
 # replace environment variables in config files
 perl -pi -e 's/\$\{DSPACE_USER\}/$ENV{DSPACE_USER}/; s/\$\{DSPACE_PASSWORD\}/$ENV{DSPACE_PASSWORD}/; s/\$\{MAIL_USER\}/$ENV{MAIL_USER}/; s/\$\{MAIL_PASSWORD\}/$ENV{MAIL_PASSWORD}/; s/\$\{DSPACE_DBNAME\}/$ENV{DSPACE_DBNAME}/; s/\$\{DSPACE_UTILSDBNAME\}/$ENV{DSPACE_UTILSDBNAME}/;' /opt/repository/sources/dspace/local.properties
-perl -pi -e 's/\$\{DSPACE_USER\}/$ENV{DSPACE_USER}/; s/\$\{DSPACE_PASSWORD\}/$ENV{DSPACE_PASSWORD}/; s/\$\{MAIL_USER\}/$ENV{MAIL_USER}/; s/\$\{MAIL_PASSWORD\}/$ENV{MAIL_PASSWORD}/; s/\$\{DSPACE_DBNAME\}/$ENV{DSPACE_DBNAME}/; s/\$\{DSPACE_UTILSDBNAME\}/$ENV{DSPACE_UTILSDBNAME}/;' /opt/repository/sources/dspace/target/local.properties 
+perl -pi -e 's/\$\{DSPACE_USER\}/$ENV{DSPACE_USER}/; s/\$\{DSPACE_PASSWORD\}/$ENV{DSPACE_PASSWORD}/; s/\$\{MAIL_USER\}/$ENV{MAIL_USER}/; s/\$\{MAIL_PASSWORD\}/$ENV{MAIL_PASSWORD}/; s/\$\{DSPACE_DBNAME\}/$ENV{DSPACE_DBNAME}/; s/\$\{DSPACE_UTILSDBNAME\}/$ENV{DSPACE_UTILSDBNAME}/;' /opt/repository/sources/dspace/target/local.properties
 perl -pi -e 's/\$\{DSPACE_USER\}/$ENV{DSPACE_USER}/; s/\$\{DSPACE_PASSWORD\}/$ENV{DSPACE_PASSWORD}/; s/\$\{MAIL_USER\}/$ENV{MAIL_USER}/; s/\$\{MAIL_PASSWORD\}/$ENV{MAIL_PASSWORD}/; s/\$\{DSPACE_DBNAME\}/$ENV{DSPACE_DBNAME}/; s/\$\{DSPACE_UTILSDBNAME\}/$ENV{DSPACE_UTILSDBNAME}/;' /opt/lindat-dspace/installation/config/dspace.cfg
 perl -pi -e 's/\$\{DSPACE_USER\}/$ENV{DSPACE_USER}/; s/\$\{DSPACE_PASSWORD\}/$ENV{DSPACE_PASSWORD}/; s/\$\{MAIL_USER\}/$ENV{MAIL_USER}/; s/\$\{MAIL_PASSWORD\}/$ENV{MAIL_PASSWORD}/; s/\$\{DSPACE_DBNAME\}/$ENV{DSPACE_DBNAME}/; s/\$\{DSPACE_UTILSDBNAME\}/$ENV{DSPACE_UTILSDBNAME}/;' /opt/lindat-dspace/installation/config/modules/lr.cfg
 
@@ -18,9 +18,8 @@ cd /opt/repository/workspace/scripts
 make init_statistics
 make update_discovery
 make update_oai
-/opt/tomcat8/bin/shutdown.sh 
+/opt/lindat-dspace/installation/bin/dspace generate-sitemaps
+/opt/tomcat8/bin/shutdown.sh
 
 # start tomcat
 /opt/tomcat8/bin/catalina.sh run
-
-

dockerfiles/commul-customization/robots.txt

+# The FULL URL to the DSpace sitemaps
+# The https://clarin-dev.eurac.edu/repository/xmlui will be auto-filled with the value in dspace.cfg
+# XML sitemap is listed first as it is preferred by most search engines
+Sitemap: https://clarin-dev.eurac.edu/repository/xmlui/sitemap
+Sitemap: https://clarin-dev.eurac.edu/repository/xmlui/htmlmap
+
+##########################
+# Default Access Group
+# (NOTE: blank lines are not allowable in a group record)
+##########################
+User-agent: *
+# Disable access to Discovery search and filters
+Disallow: /discover
+Disallow: /search-filter
+#
+# Optionally uncomment the following line ONLY if sitemaps are working
+# and you have verified that your site is being indexed correctly.
+# Disallow: /browse
+#
+# If you have configured DSpace (Solr-based) Statistics to be publicly 
+# accessible, then you may not want this content to be indexed
+# Disallow: /statistics
+#
+# You also may wish to disallow access to the following paths, in order
+# to stop web spiders from accessing user-based content
+# Disallow: /contact
+# Disallow: /feedback
+# Disallow: /forgot
+# Disallow: /login
+# Disallow: /register
+
+
+##############################
+# Section for misbehaving bots
+# The following directives to block specific robots were borrowed from Wikipedia's robots.txt
+##############################
+
+# advertising-related bots:
+User-agent: Mediapartners-Google*
+Disallow: /
+
+# Crawlers that are kind enough to obey, but which we'd rather not have
+# unless they're feeding search engines.
+User-agent: UbiCrawler
+Disallow: /
+
+User-agent: DOC
+Disallow: /
+
+User-agent: Zao
+Disallow: /
+
+# Some bots are known to be trouble, particularly those designed to copy
+# entire sites. Please obey robots.txt.
+User-agent: sitecheck.internetseer.com
+Disallow: /
+
+User-agent: Zealbot
+Disallow: /
+
+User-agent: MSIECrawler
+Disallow: /
+
+User-agent: SiteSnagger
+Disallow: /
+
+User-agent: WebStripper
+Disallow: /
+
+User-agent: WebCopier
+Disallow: /
+
+User-agent: Fetch
+Disallow: /
+
+User-agent: Offline Explorer
+Disallow: /
+
+User-agent: Teleport
+Disallow: /
+
+User-agent: TeleportPro
+Disallow: /
+
+User-agent: WebZIP
+Disallow: /
+
+User-agent: linko
+Disallow: /
+
+User-agent: HTTrack
+Disallow: /
+
+User-agent: Microsoft.URL.Control
+Disallow: /
+
+User-agent: Xenu
+Disallow: /
+
+User-agent: larbin
+Disallow: /
+
+User-agent: libwww
+Disallow: /
+
+User-agent: ZyBORG
+Disallow: /
+
+User-agent: Download Ninja
+Disallow: /
+
+# Misbehaving: requests much too fast:
+User-agent: fast
+Disallow: /
+
+#
+# If your DSpace is going down because of someone using recursive wget, 
+# you can activate the following rule.
+#
+# If your own faculty is bringing down your dspace with recursive wget,
+# you can advise them to use the --wait option to set the delay between hits.
+#
+#User-agent: wget
+#Disallow: /
+
+#
+# The 'grub' distributed client has been *very* poorly behaved.
+#
+User-agent: grub-client
+Disallow: /
+
+#
+# Doesn't follow robots.txt anyway, but...
+#
+User-agent: k2spider
+Disallow: /
+
+#
+# Hits many times per second, not acceptable
+# http://www.nameprotect.com/botinfo.html
+User-agent: NPBot
+Disallow: /
+
+# A capture bot, downloads gazillions of pages with no public benefit
+# http://www.webreaper.net/
+User-agent: WebReaper
+Disallow: /