![[at]](at.gif)
example![[dot]](dot.gif)
com
CFG_WEBSTYLE_EMAIL_ADDRESSES_OBFUSCATION_MODE = 2
## CFG_WEBSTYLE_INSPECT_TEMPLATES -- Do we want to debug all template
## functions so that they would return HTML results wrapped in
## comments indicating which part of HTML page was created by which
## template function? Useful only for debugging Pythonic HTML
## template. See WebStyle Admin Guide for more information.
CFG_WEBSTYLE_INSPECT_TEMPLATES = 0
## (deprecated) CFG_WEBSTYLE_CDSPAGEBOXLEFTTOP -- eventual global HTML
## left top box:
CFG_WEBSTYLE_CDSPAGEBOXLEFTTOP =
## (deprecated) CFG_WEBSTYLE_CDSPAGEBOXLEFTBOTTOM -- eventual global
## HTML left bottom box:
CFG_WEBSTYLE_CDSPAGEBOXLEFTBOTTOM =
## (deprecated) CFG_WEBSTYLE_CDSPAGEBOXRIGHTTOP -- eventual global
## HTML right top box:
CFG_WEBSTYLE_CDSPAGEBOXRIGHTTOP =
## (deprecated) CFG_WEBSTYLE_CDSPAGEBOXRIGHTBOTTOM -- eventual global
## HTML right bottom box:
CFG_WEBSTYLE_CDSPAGEBOXRIGHTBOTTOM =
## CFG_WEBSTYLE_HTTP_STATUS_ALERT_LIST -- when certain HTTP status
## codes are raised to the WSGI handler, the corresponding exceptions
## and error messages can be sent to the system administrator for
## inspecting. This is useful to detect and correct errors. The
## variable represents a comma-separated list of HTTP statuses that
## should alert admin. Wildcards are possible. If the status is
## followed by an "r", it means that a referer is required to exist
## (useful to distinguish broken known links from URL typos when 404
## errors are raised).
CFG_WEBSTYLE_HTTP_STATUS_ALERT_LIST = 404r,400,5*,41*
## CFG_WEBSTYLE_HTTP_USE_COMPRESSION -- whether to enable deflate
## compression of your HTTP/HTTPS connections. This will affect the Apache
## configuration snippets created by inveniocfg --create-apache-conf and
## the OAI-PMH Identify response.
CFG_WEBSTYLE_HTTP_USE_COMPRESSION = 0
## CFG_WEBSTYLE_REVERSE_PROXY_IPS -- if you are setting a multinode
## environment where an HTTP proxy such as mod_proxy is sitting in
## front of the Invenio web application and is forwarding requests to
## worker nodes, set here the the list of IP addresses of the allowed
## HTTP proxies. This is needed in order to avoid IP address spoofing
## when worker nodes are also available on the public Internet and
## might receive forged HTTP requests. Only HTTP requests coming from
## the specified IP addresses will be considered as forwarded from a
## reverse proxy. E.g. set this to '123.123.123.123'.
CFG_WEBSTYLE_REVERSE_PROXY_IPS =
##################################
## Part 3: WebSearch parameters ##
##################################
## This section contains some configuration parameters for WebSearch
## module. Please note that WebSearch is mostly configured on
## run-time via its WebSearch Admin web interface. The parameters
## below are the ones that you do not probably want to modify very
## often during the runtime. (Note that you may modify them
## afterwards too, though.)
## CFG_WEBSEARCH_SEARCH_CACHE_SIZE -- how many queries we want to
## cache in memory per one Apache httpd process? This cache is used
## mainly for "next/previous page" functionality, but it caches also
## "popular" user queries if more than one user happen to search for
## the same thing. Note that large numbers may lead to great memory
## consumption. We recommend a value not greater than 100.
CFG_WEBSEARCH_SEARCH_CACHE_SIZE = 0
## CFG_WEBSEARCH_FIELDS_CONVERT -- if you migrate from an older
## system, you may want to map field codes of your old system (such as
## 'ti') to Invenio/MySQL ("title"). Use Python dictionary syntax
## for the translation table, e.g. {'wau':'author', 'wti':'title'}.
## Usually you don't want to do that, and you would use empty dict {}.
CFG_WEBSEARCH_FIELDS_CONVERT = {}
## CFG_WEBSEARCH_LIGHTSEARCH_PATTERN_BOX_WIDTH -- width of the
## search pattern window in the light search interface, in
## characters. CFG_WEBSEARCH_LIGHTSEARCH_PATTERN_BOX_WIDTH = 60
CFG_WEBSEARCH_LIGHTSEARCH_PATTERN_BOX_WIDTH = 60
## CFG_WEBSEARCH_SIMPLESEARCH_PATTERN_BOX_WIDTH -- width of the search
## pattern window in the simple search interface, in characters.
CFG_WEBSEARCH_SIMPLESEARCH_PATTERN_BOX_WIDTH = 40
## CFG_WEBSEARCH_ADVANCEDSEARCH_PATTERN_BOX_WIDTH -- width of the
## search pattern window in the advanced search interface, in
## characters.
CFG_WEBSEARCH_ADVANCEDSEARCH_PATTERN_BOX_WIDTH = 30
## CFG_WEBSEARCH_NB_RECORDS_TO_SORT -- how many records do we still
## want to sort? For higher numbers we print only a warning and won't
## perform any sorting other than default 'latest records first', as
## sorting would be very time consuming then. We recommend a value of
## not more than a couple of thousands.
CFG_WEBSEARCH_NB_RECORDS_TO_SORT = 1000
## CFG_WEBSEARCH_CALL_BIBFORMAT -- if a record is being displayed but
## it was not preformatted in the "HTML brief" format, do we want to
## call BibFormatting on the fly? Put "1" for "yes" and "0" for "no".
## Note that "1" will display the record exactly as if it were fully
## preformatted, but it may be slow due to on-the-fly processing; "0"
## will display a default format very fast, but it may not have all
## the fields as in the fully preformatted HTML brief format. Note
## also that this option is active only for old (PHP) formats; the new
## (Python) formats are called on the fly by default anyway, since
## they are much faster. When usure, please set "0" here.
CFG_WEBSEARCH_CALL_BIBFORMAT = 0
## CFG_WEBSEARCH_USE_ALEPH_SYSNOS -- do we want to make old SYSNOs
## visible rather than MySQL's record IDs? You may use this if you
## migrate from a different e-doc system, and you store your old
## system numbers into 970__a. Put "1" for "yes" and "0" for
## "no". Usually you don't want to do that, though.
CFG_WEBSEARCH_USE_ALEPH_SYSNOS = 0
## CFG_WEBSEARCH_I18N_LATEST_ADDITIONS -- Put "1" if you want the
## "Latest Additions" in the web collection pages to show
## internationalized records. Useful only if your brief BibFormat
## templates contains internationalized strings. Otherwise put "0" in
## order not to slow down the creation of latest additions by WebColl.
CFG_WEBSEARCH_I18N_LATEST_ADDITIONS = 0
## CFG_WEBSEARCH_INSTANT_BROWSE -- the number of records to display
## under 'Latest Additions' in the web collection pages.
CFG_WEBSEARCH_INSTANT_BROWSE = 10
## CFG_WEBSEARCH_INSTANT_BROWSE_RSS -- the number of records to
## display in the RSS feed.
CFG_WEBSEARCH_INSTANT_BROWSE_RSS = 25
## CFG_WEBSEARCH_RSS_I18N_COLLECTIONS -- comma-separated list of
## collections that feature an internationalized RSS feed on their
## main seach interface page created by webcoll. Other collections
## will have RSS feed using CFG_SITE_LANG.
CFG_WEBSEARCH_RSS_I18N_COLLECTIONS =
## CFG_WEBSEARCH_RSS_TTL -- number of minutes that indicates how long
## a feed cache is valid.
CFG_WEBSEARCH_RSS_TTL = 360
## CFG_WEBSEARCH_RSS_MAX_CACHED_REQUESTS -- maximum number of request kept
## in cache. If the cache is filled, following request are not cached.
CFG_WEBSEARCH_RSS_MAX_CACHED_REQUESTS = 1000
## CFG_WEBSEARCH_AUTHOR_ET_AL_THRESHOLD -- up to how many author names
## to print explicitely; for more print "et al". Note that this is
## used in default formatting that is seldomly used, as usually
## BibFormat defines all the format. The value below is only used
## when BibFormat fails, for example.
CFG_WEBSEARCH_AUTHOR_ET_AL_THRESHOLD = 3
## CFG_WEBSEARCH_NARROW_SEARCH_SHOW_GRANDSONS -- whether to show or
## not collection grandsons in Narrow Search boxes (sons are shown by
## default, grandsons are configurable here). Use 0 for no and 1 for
## yes.
CFG_WEBSEARCH_NARROW_SEARCH_SHOW_GRANDSONS = 1
## CFG_WEBSEARCH_CREATE_SIMILARLY_NAMED_AUTHORS_LINK_BOX -- shall we
## create help links for Ellis, Nick or Ellis, Nicholas and friends
## when Ellis, N was searched for? Useful if you have one author
## stored in the database under several name formats, namely surname
## comma firstname and surname comma initial cataloging policy. Use 0
## for no and 1 for yes.
CFG_WEBSEARCH_CREATE_SIMILARLY_NAMED_AUTHORS_LINK_BOX = 1
## CFG_WEBSEARCH_USE_MATHJAX_FOR_FORMATS -- MathJax is a JavaScript
## library that renders (La)TeX mathematical formulas in the client
## browser. This parameter must contain a comma-separated list of
## output formats for which to apply the MathJax rendering, for example
## "hb,hd". If the list is empty, MathJax is disabled.
CFG_WEBSEARCH_USE_MATHJAX_FOR_FORMATS =
## CFG_WEBSEARCH_EXTERNAL_COLLECTION_SEARCH_TIMEOUT -- when searching
## external collections (e.g. SPIRES, CiteSeer, etc), how many seconds
## do we wait for reply before abandonning?
CFG_WEBSEARCH_EXTERNAL_COLLECTION_SEARCH_TIMEOUT = 5
## CFG_WEBSEARCH_EXTERNAL_COLLECTION_SEARCH_MAXRESULTS -- how many
## results do we fetch?
CFG_WEBSEARCH_EXTERNAL_COLLECTION_SEARCH_MAXRESULTS = 10
## CFG_WEBSEARCH_SPLIT_BY_COLLECTION -- do we want to split the search
## results by collection or not? Use 0 for not, 1 for yes.
CFG_WEBSEARCH_SPLIT_BY_COLLECTION = 1
## CFG_WEBSEARCH_DEF_RECORDS_IN_GROUPS -- the default number of
## records to display per page in the search results pages.
CFG_WEBSEARCH_DEF_RECORDS_IN_GROUPS = 10
## CFG_WEBSEARCH_MAX_RECORDS_IN_GROUPS -- in order to limit denial of
## service attacks the total number of records per group displayed as a
## result of a search query will be limited to this number. Only the superuser
## queries will not be affected by this limit.
CFG_WEBSEARCH_MAX_RECORDS_IN_GROUPS = 200
## CFG_WEBSEARCH_SHOW_COMMENT_COUNT -- do we want to show the 'N comments'
## links on the search engine pages? (useful only when you have allowed
## commenting)
CFG_WEBSEARCH_SHOW_COMMENT_COUNT = 1
## CFG_WEBSEARCH_SHOW_REVIEW_COUNT -- do we want to show the 'N reviews'
## links on the search engine pages? (useful only when you have allowed
## reviewing)
CFG_WEBSEARCH_SHOW_REVIEW_COUNT = 1
## CFG_WEBSEARCH_FULLTEXT_SNIPPETS -- how many full-text snippets do
## we want to display for full-text searches? If you want to specify
## different values for different document status types, please add
## more items into this dictionary. (Unless specified, the empty
## value will be used as default.) This is useful if you have
## restricted files of different types with various restrictions on
## what we can show.
CFG_WEBSEARCH_FULLTEXT_SNIPPETS = {
'': 4,
}
## CFG_WEBSEARCH_FULLTEXT_SNIPPETS_CHARS -- what is the maximum size
## of a snippet to display around the pattern found in the full-text?
## If you want to specify different values for different document
## status types, please add more items into this dictionary. (Unless
## specified, the empty value will be used as default.) This is
## useful if you have restricted files of different types with various
## restrictions on what we can show.
CFG_WEBSEARCH_FULLTEXT_SNIPPETS_CHARS = {
'': 100,
}
## CFG_WEBSEARCH_WILDCARD_LIMIT -- some of the queries, wildcard
## queries in particular (ex: cern*, a*), but also regular expressions
## (ex: [a-z]+), may take a long time to respond due to the high
## number of hits. You can limit the number of terms matched by a
## wildcard by setting this variable. A negative value or zero means
## that none of the queries will be limited (which may be wanted by
## also prone to denial-of-service kind of attacks).
CFG_WEBSEARCH_WILDCARD_LIMIT = 50000
## CFG_WEBSEARCH_SYNONYM_KBRS -- defines which knowledge bases are to
## be used for which index in order to provide runtime synonym lookup
## of user-supplied terms, and what massaging function should be used
## upon search pattern before performing the KB lookup. (Can be one
## of `exact', 'leading_to_comma', `leading_to_number'.)
CFG_WEBSEARCH_SYNONYM_KBRS = {
'journal': ['SEARCH-SYNONYM-JOURNAL', 'leading_to_number'],
}
## CFG_SOLR_URL -- optionally, you may use Solr to serve full-text
## queries and ranking. If so, please specify the URL of your Solr instance.
## Example: http://localhost:8983/solr (default solr port)
CFG_SOLR_URL =
## CFG_XAPIAN_ENABLED -- optionally, you may use Xapian to serve full-text
## queries and ranking. If so, please enable it: 1 = enabled
CFG_XAPIAN_ENABLED =
## CFG_WEBSEARCH_PREV_NEXT_HIT_LIMIT -- specify the limit when
## the previous/next/back hit links are to be displayed on detailed record pages.
## In order to speeding up list manipulations, if a search returns lots of hits,
## more than this limit, then do not loose time calculating next/previous/back
## hits at all, but display page directly without these.
## Note also that Invenio installations that do not like
## to have the next/previous hit link functionality would be able to set this
## variable to zero and not see anything.
CFG_WEBSEARCH_PREV_NEXT_HIT_LIMIT = 1000
## CFG_WEBSEARCH_PREV_NEXT_HIT_FOR_GUESTS -- Set this to 0 if you want
## to disable the previous/next/back hit link functionality for guests
## users.
## Since the previous/next/back hit link functionality is causing the allocation
## of user session in the database even for guests users, it might be useful to
## be able to disable it e.g. when your site is bombarded by web request
## (a.k.a. Slashdot effect).
CFG_WEBSEARCH_PREV_NEXT_HIT_FOR_GUESTS = 1
## CFG_WEBSEARCH_VIEWRESTRCOLL_POLICY -- when a record belongs to more than one
## restricted collection, if the viewrestcoll policy is set to "ALL" (default)
## then the user must be authorized to all the restricted collections, in
## order to be granted access to the specific record. If the policy is set to
## "ANY", then the user need to be authorized to only one of the collections
## in order to be granted access to the specific record.
CFG_WEBSEARCH_VIEWRESTRCOLL_POLICY = ANY
## CFG_WEBSEARCH_SPIRES_SYNTAX -- variable to configure the use of the
## SPIRES query syntax in searches. Values: 0 = SPIRES syntax is
## switched off; 1 = leading 'find' is required; 9 = leading 'find' is
## not required (leading SPIRES operator, space-operator-space, etc
## are also accepted).
CFG_WEBSEARCH_SPIRES_SYNTAX = 1
## CFG_WEBSEARCH_DISPLAY_NEAREST_TERMS -- when user search does not
## return any direct result, what do we want to display? Set to 0 in
## order to display a generic message about search returning no hits.
## Set to 1 in order to display list of nearest terms from the indexes
## that may match user query. Note: this functionality may be slow,
## so you may want to disable it on bigger sites.
CFG_WEBSEARCH_DISPLAY_NEAREST_TERMS = 1
## CFG_WEBSEARCH_DETAILED_META_FORMAT -- the output format to use for
## detailed meta tags containing metadata as configured in the tag
## table. Default output format should be 'hdm', included. This
## format will be included in the header of /record/ pages. For
## efficiency this format should be pre-cached with BibReformat. See
## also CFG_WEBSEARCH_ENABLE_GOOGLESCHOLAR and
## CFG_WEBSEARCH_ENABLE_GOOGLESCHOLAR.
CFG_WEBSEARCH_DETAILED_META_FORMAT = hdm
## CFG_WEBSEARCH_ENABLE_GOOGLESCHOLAR -- decides if meta tags for
## Google Scholar shall be included in the detailed record page
## header, when using the standard formatting templates/elements. See
## also CFG_WEBSEARCH_DETAILED_META_FORMAT and
## CFG_WEBSEARCH_ENABLE_OPENGRAPH. When this variable is changed and
## output format defined in CFG_WEBSEARCH_DETAILED_META_FORMAT is
## cached, a bibreformat must be run for the cached records.
CFG_WEBSEARCH_ENABLE_GOOGLESCHOLAR = True
## CFG_WEBSEARCH_ENABLE_OPENGRAPH -- decides if meta tags for the Open
## Graph protocol shall be included in the detailed record page
## header, when using the standard formatting templates/elements. See
## also CFG_WEBSEARCH_DETAILED_META_FORMAT and
## CFG_WEBSEARCH_ENABLE_GOOGLESCHOLAR. When this variable is changed
## and output format defined in CFG_WEBSEARCH_DETAILED_META_FORMAT is
## cached, a bibreformat must be run for the cached records. Note that
## enabling Open Graph produces invalid XHTML/HTML5 markup.
CFG_WEBSEARCH_ENABLE_OPENGRAPH = False
## CFG_WEBSEARCH_CITESUMMARY_SELFCITES_THRESHOLD -- switches off
## self-citations computation if the number records in the citesummary
## is above the threshold
CFG_WEBSEARCH_CITESUMMARY_SELFCITES_THRESHOLD = 2000
#######################################
## Part 4: BibHarvest OAI parameters ##
#######################################
## This part defines parameters for the Invenio OAI gateway.
## Useful if you are running Invenio as OAI data provider.
## CFG_OAI_ID_FIELD -- OAI identifier MARC field:
CFG_OAI_ID_FIELD = 909COo
## CFG_OAI_SET_FIELD -- OAI set MARC field:
CFG_OAI_SET_FIELD = 909COp
## CFG_OAI_SET_FIELD -- previous OAI set MARC field:
CFG_OAI_PREVIOUS_SET_FIELD = 909COq
## CFG_OAI_DELETED_POLICY -- OAI deletedrecordspolicy
## (no/transient/persistent):
CFG_OAI_DELETED_POLICY = persistent
## CFG_OAI_ID_PREFIX -- OAI identifier prefix:
CFG_OAI_ID_PREFIX = atlantis.cern.ch
## CFG_OAI_SAMPLE_IDENTIFIER -- OAI sample identifier:
CFG_OAI_SAMPLE_IDENTIFIER = oai:atlantis.cern.ch:123
## CFG_OAI_IDENTIFY_DESCRIPTION -- description for the OAI Identify verb:
CFG_OAI_IDENTIFY_DESCRIPTION = This HOWTO guide intends to give you ideas on how to run your CDS Invenio installation and how to take care of its normal day-to-day operation.
Many tasks that manipulate the bibliographic record database can be set to run in a periodical mode. For example, we want to have the indexing engine to scan periodically for newly arrived documents to index them as soon as they enter into the system. It is the role of the BibSched system to take care of the task scheduling and the task execution.
Periodical tasks (such as regular metadata indexing) as well as one-time tasks (such as a batch upload of newly acquired metadata file) are not executed straight away but are stored in the BibSched task queue. BibSched daemon looks periodically in the queue and launches the tasks according to their order or the date of programmed runtime. You can consider BibSched to be a kind of cron daemon for bibliographic tasks.
This means that after having installed Invenio you will want to have the BibSched daemon running permanently. To launch BibSched daemon, do:
$ bibsched start
To setup indexing, ranking, sorting, formatting, and collection cache updating daemons to run periodically with a sleeping period of, say, 5 minutes:
$ bibindex -f50000 -s5m $ bibreformat -oHB -s5m $ webcoll -v0 -s5m $ bibrank -f50000 -s5m $ bibsort -s5m
It is imperative to have the above five tasks permanently in your BibSched queue so that newly submitted documents will be processed automatically.
You may also want to set up some periodical housekeeping tasks:
$ bibrank -f50000 -R -wwrd -s14d -LSunday $ bibsort -R -s7d -L 'Sunday 01:00-05:00' $ inveniogc -a -s7d -L 'Sunday 01:00-05:00' $ dbdump -s20h -L '22:00-06:00' -o/opt2/mysql-backups -n10
Please consult the sections below for more details about these housekeeping tasks.
There is also the possibility to setup the batch uploader daemon to run periodically, looking for new documents or metadata files to upload:
$ batchuploader --documents -s20m $ batchuploader --metadata -s20m
Additionally you might want to automatically generate sitemap.xml files for your installation. For this just schedule:
You will then need to add a line such as:$ bibexport -w sitemap -s1d
to your robots.txt file. -Sitemap:/sitemap-index.xml.gz
If you are using the WebLinkback module, you should run the following tasklets: +
If you are using the WebLinkback module, you may want to run some of the following tasklets:
+# Delete rejected, broken and pending linkbacks whose URLs is on blacklist
sudo -u www-data /opt/invenio/bin/bibtasklet \
-N weblinkbackupdaterdeleteurlsonblacklist \
-T bst_weblinkback_updater \
-a "mode=1" \
-u admin -s1d -L '22:00-05:00'
+# Update page titles of new linkbacks
sudo -u www-data /opt/invenio/bin/bibtasklet \
-N weblinkbackupdaternewpages \
-T bst_weblinkback_updater \
-a "mode=2" \
-u admin -s1d -L '22:00-05:00'
+# Update page titles of old linkbacks
sudo -u www-data /opt/invenio/bin/bibtasklet \
-N weblinkbackupdateroldpages \
-T bst_weblinkback_updater \
-a "mode=3" \
-u admin -s7d -L '22:00-05:00'
+# Update manually set page titles
sudo -u www-data /opt/invenio/bin/bibtasklet \
-N weblinkbackupdatermanuallysettitles \
-T bst_weblinkback_updater \
-a "mode=4" \
-u admin -s7d -L '22:00-05:00'
+# Detect and disable broken linkbacks
sudo -u www-data /opt/invenio/bin/bibtasklet \
-N weblinkbackupdaterdetectbrokenlinkbacks \
-T bst_weblinkback_updater \
-a "mode=5" \
-u admin -s7d -L 'Sunday 01:00-05:00'
+
+# Send notification email for all pending linkbacks
+sudo -u www-data /opt/invenio/bin/bibtasklet \
+ -N weblinkbacknotifications \
+ -T bst_weblinkback_updater \
+ -a "mode=6" \
+ -u admin -s1d
Note that the BibSched automated daemon stops as soon as some of its tasks end with an error. You will be informed by email about this incident. Nevertheless, it is a good idea to inspect the BibSched queue from time to time anyway, say several times per day, to see what is going on. This can be done by running the BibSched command-line monitor:
$ bibsched
The monitor will permit you to stop/start the automated mode, to
delete the tasks that were wrongly submitted, to run some of the tasks
manually, etc. Note also that the BibSched daemon writes its log and
error files about its own operation, as well as on the operation of
its tasks, to the /opt/invenio/var/log directory.
Invenio users may set up an automatic notification email alerts so that they are automatically alerted about documents of their interest by email, either daily, weekly, or monthly. It is the job of the alert engine to do this. The alert engine has to be run every day:
$ alertengine
You may want to set up an external cron job to call
alertengine each day, for example:
$ crontab -l # invenio: periodically restart Apache: 59 23 * * * /usr/sbin/apachectl restart # invenio: run alert engine: 30 14 * * * /usr/bin/sudo -u apache /opt/invenio/bin/alertengine
When you are adding new records to the system, the word frequency ranking weights for old records aren't recalculated by default in order to speed up the insertion of new records. This may influence a bit the precision of word similarity searches. It is therefore advised to expressely run bibrank in the recalculating mode once in a while during a relatively quiet site operation day, by doing:
You may want to do this either (i) periodically, say once per month (see the previous section), or (ii) depending on the frequency of new additions to the record database, say when the size grows by 2-3 percent.$ bibrank -R -w wrd -s 14d -L Sunday
It is advised to run from time to time the rebalancing of the sorting buckets. In order to speed up the process of insertion of new records, the sorting buckets are not being recalculated, but new records are being added at the end of the corresponding bucket. This might create differences in the size of each bucket which might have a small impact on the speed of sorting.
The rebalancing might be run weekly or even daily.$ bibsort -R -s 7d -L 'Sunday 01:00-05:00'
The tool inveniogc provides a garbage collector for
the database, temporary files, and the like.
If you choose to differentiate between guest users
(see CFG_WEBSESSION_DIFFERENTIATE_BETWEEN_GUESTS
in invenio.conf), then guest users can create a lot of
entries in Invenio tables that are related to their web sessions,
their search history, personal baskets, etc. This data has to be
garbage-collected periodically. You can run this, say every Sunday
between 01:00 and 05:00, via:
$ inveniogc -s 7d -L 'Sunday 01:00-05:00'
Different temporary log and err files are created
in /opt/invenio/var/log
and /opt/invenio/var/tmp directory that is good to
clean up from time to time. The previous command could be used to
clean those files, too, via:
$ inveniogc -s 7d -d -L 'Sunday 01:00-05:00'
The inveniogc tool can run other cleaning actions;
please refer to its help (inveniogc --help) for more
details.
Note that in the above section "Setting up periodical daemon
tasks", we have set up inveniogc with
argument -a in that example, meaning that it would run
all possible cleaning actions. Please modify this if it is not what
you want.
You can launch a bibsched task called dbdump in order
to take regular snapshot of your database content into SQL dump files.
For example, to back up the database content
into /opt2/mysql-backups directory every night, keeping
at most 10 latest copies of the backup file, you would launch:
$ dbdump -s 20h -L '22:00-06:00' -o /opt2/mysql-backups -n 10
This will create files named
like invenio-dbdump-2009-03-10_22:10:28.sql in this
folder.
Note that you may use Invenio-independent MySQL backuping tools
like mysqldump, but these might generally lock all tables
during backup for consistency, hence it could happen that your site
might not be accessible during backuping time due to the user session
table being locked as well. The dbdump tool does not
lock all tables, therefore the site remains accessible to users while
the dump files are being created. Note that the dump files are kept
consistent with respect to the data, since dbdump runs
via bibsched, hence not allowing any other important
bibliographic task to run during the backup.
To load a dump file produced by dbdump into a running
Invenio instance later, you can use:
diff --git a/modules/webjournal/lib/elements/bfe_webjournal_trackback_auto_discovery.py b/modules/webjournal/lib/elements/bfe_webjournal_trackback_auto_discovery.py index 5c1ecf35b..579c328b0 100644 --- a/modules/webjournal/lib/elements/bfe_webjournal_trackback_auto_discovery.py +++ b/modules/webjournal/lib/elements/bfe_webjournal_trackback_auto_discovery.py @@ -1,46 +1,48 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- ## This file is part of Invenio. ## Copyright (C) 2009, 2010, 2011 CERN. ## ## Invenio is free software; you can redistribute it and/or ## modify it under the terms of the GNU General Public License as ## published by the Free Software Foundation; either version 2 of the ## License, or (at your option) any later version. ## ## Invenio is distributed in the hope that it will be useful, but ## WITHOUT ANY WARRANTY; without even the implied warranty of ## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU ## General Public License for more details. ## ## You should have received a copy of the GNU General Public License ## along with Invenio; if not, write to the Free Software Foundation, Inc., ## 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA. """ WebJournal Element - return trackback auto discovery tag """ import cgi from invenio.webjournal_utils import parse_url_string from invenio.weblinkback_templates import get_trackback_auto_discovery_tag +from invenio.config import CFG_WEBLINKBACK_TRACKBACK_ENABLED def format_element(bfo): """ Return trackback auto discovery tag if recid != -1, will return "" for recid == -1 like index pages """ - # Retrieve context (journal, issue and category) from URI - args = parse_url_string(bfo.user_info['uri']) - recid = args["recid"] - html = "" - if recid != -1: - html = get_trackback_auto_discovery_tag(recid) + if CFG_WEBLINKBACK_TRACKBACK_ENABLED: + # Retrieve context (journal, issue and category) from URI + args = parse_url_string(bfo.user_info['uri']) + recid = args["recid"] + + if recid != -1: + html = get_trackback_auto_discovery_tag(recid) return html def escape_values(bfo): """ Called by BibFormat in order to check if output of this element should be escaped. """ return 0 diff --git a/modules/weblinkback/lib/weblinkback.py b/modules/weblinkback/lib/weblinkback.py index dfa107230..d8b3d6f64 100644 --- a/modules/weblinkback/lib/weblinkback.py +++ b/modules/weblinkback/lib/weblinkback.py @@ -1,313 +1,334 @@ # -*- coding: utf-8 -*- ## This file is part of Invenio. ## Copyright (C) 2011 CERN. ## ## Invenio is free software; you can redistribute it and/or ## modify it under the terms of the GNU General Public License as ## published by the Free Software Foundation; either version 2 of the ## License, or (at your option) any later version. ## ## Invenio is distributed in the hope that it will be useful, but ## WITHOUT ANY WARRANTY; without even the implied warranty of ## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU ## General Public License for more details. ## ## You should have received a copy of the GNU General Public License ## along with Invenio; if not, write to the Free Software Foundation, Inc., ## 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA. """WebLinkback - Handling Linkbacks""" from invenio.config import CFG_SITE_URL, \ CFG_SITE_RECORD, \ - CFG_SITE_ADMIN_EMAIL + CFG_SITE_ADMIN_EMAIL, \ + CFG_SITE_LANG from invenio.weblinkback_config import CFG_WEBLINKBACK_TYPE, \ CFG_WEBLINKBACK_SUBSCRIPTION_DEFAULT_ARGUMENT_NAME, \ CFG_WEBLINKBACK_STATUS, \ CFG_WEBLINKBACK_ORDER_BY_INSERTION_TIME, \ CFG_WEBLINKBACK_LIST_TYPE, \ CFG_WEBLINKBACK_TRACKBACK_SUBSCRIPTION_ERROR_MESSAGE, \ CFG_WEBLINKBACK_PAGE_TITLE_STATUS, \ - CFG_WEBLINKBACK_BROKEN_COUNT + CFG_WEBLINKBACK_BROKEN_COUNT, \ + CFG_WEBLINKBACK_LATEST_FACTOR from invenio.weblinkback_dblayer import create_linkback, \ get_url_list, \ get_all_linkbacks, \ get_approved_latest_added_linkbacks, \ approve_linkback, \ get_urls_and_titles, \ update_url_title, \ set_url_broken, \ increment_broken_count, \ remove_linkback from invenio.search_engine import check_user_can_view_record, \ guess_primary_collection_of_a_record from invenio.access_control_engine import acc_authorize_action, \ acc_get_authorized_emails from invenio.webuser import collect_user_info from invenio.mailutils import send_email -from invenio.bibformat import format_record from invenio.urlutils import get_title_of_page def check_user_can_view_linkbacks(user_info, recid): """ Check if the user is authorized to view linkbacks for a given recid. Returns the same type as acc_authorize_action """ # check user cannot view the record itself (auth_code, auth_msg) = check_user_can_view_record(user_info, recid) if auth_code: return (auth_code, auth_msg) # check if user can view the linkbacks record_primary_collection = guess_primary_collection_of_a_record(recid) return acc_authorize_action(user_info, 'viewlinkbacks', authorized_if_no_roles=True, collection=record_primary_collection) -def generate_redirect_url(recid, ln, action = None): +def generate_redirect_url(recid, ln=CFG_SITE_LANG, action = None): """ Get redirect URL for an action @param action: the action, must be defined in weblinkback_webinterface.py @return "CFG_SITE_URL/CFG_SITE_RECORD/recid/linkbacks/action?ln=%s" if action != None, otherwise CFG_SITE_URL/CFG_SITE_RECORD/recid/linkbacks?ln=%s """ result = "%s/%s/%s/linkbacks" % (CFG_SITE_URL, CFG_SITE_RECORD, recid) if action != None: return result + "/%s?ln=%s" % (action, ln) else: return result + "?ln=%s" % ln def split_in_days(linkbacks): """ Split linkbacks in days @param linkbacks: a list of this format: [(linkback_id, origin_url, recid, additional_properties, type, status, insert_time)] in ascending or descending order by insert_time @return a list of lists of linkbacks """ result = [] same_day_list = [] previous_date = None current_date = None for i in range(len(linkbacks)): current_linkback = linkbacks[i] previous_date = None if i > 0: previous_date = current_date else: previous_date = current_linkback[6] current_date = current_linkback[6] # same day --> same group if (current_date.year == previous_date.year and current_date.month == previous_date.month and current_date.day == previous_date.day): same_day_list.append(current_linkback) else: result.append(same_day_list) same_day_list = [] same_day_list.append(current_linkback) # add last group if non-empty if same_day_list: result.append(same_day_list) return result def create_trackback(recid, url, title, excerpt, blog_name, blog_id, source, user_info): """ Create a trackback @param recid """ # copy optional arguments argument_copy = {} if title != CFG_WEBLINKBACK_SUBSCRIPTION_DEFAULT_ARGUMENT_NAME: argument_copy['title'] = title if excerpt != CFG_WEBLINKBACK_SUBSCRIPTION_DEFAULT_ARGUMENT_NAME: argument_copy['excerpt'] = excerpt if blog_name != CFG_WEBLINKBACK_SUBSCRIPTION_DEFAULT_ARGUMENT_NAME: argument_copy['blog_name'] = blog_name if blog_id != CFG_WEBLINKBACK_SUBSCRIPTION_DEFAULT_ARGUMENT_NAME: argument_copy['id'] = blog_id if source != CFG_WEBLINKBACK_SUBSCRIPTION_DEFAULT_ARGUMENT_NAME: argument_copy['source'] = source additional_properties = "" if len(argument_copy) > 0: additional_properties = argument_copy return create_linkback(url, recid, additional_properties, CFG_WEBLINKBACK_TYPE['TRACKBACK'], user_info) -def send_request_notification_to_all_linkback_moderators(recid, origin_url, linkback_type, ln): +def send_pending_linkbacks_notification(linkback_type): """ - Send notification emails to all linkback moderators for linkback request - @param recid - @param origin_url: URL of the requestor + Send notification emails to all linkback moderators for all pending linkbacks @param linkback_type: of CFG_WEBLINKBACK_LIST_TYPE """ - content = """There is a new %(linkback_type)s request for %(recordURL)s from %(origin_url)s which you should approve or reject. - """ % {'linkback_type': linkback_type, - 'recordURL': generate_redirect_url(recid, ln), - 'origin_url': origin_url} + pending_linkbacks = get_all_linkbacks(linkback_type=CFG_WEBLINKBACK_TYPE['TRACKBACK'], status=CFG_WEBLINKBACK_STATUS['PENDING']) + + if pending_linkbacks: + content = """There are %(count)s new %(linkback_type)s requests which you should approve or reject: + """ % {'count': len(pending_linkbacks), + 'linkback_type': linkback_type} - html_content = """There is a new %(linkback_type)s request for %(record)s (%(recordURL)s) from %(title)s (%(origin_url)s) which you should approve or reject. - """ % {'linkback_type': linkback_type, - 'record': format_record(recID=recid, of='hs', ln=ln), - 'recordURL': generate_redirect_url(recid, ln), - 'origin_url': origin_url, - 'title': origin_url} + for pending_linkback in pending_linkbacks: + content += """ + For %(recordURL)s from %(origin_url)s. + """ % {'recordURL': generate_redirect_url(pending_linkback[2]), + 'origin_url': pending_linkback[1]} - for email in acc_get_authorized_emails('moderatelinkbacks', collection = guess_primary_collection_of_a_record(recid)): - send_email(CFG_SITE_ADMIN_EMAIL, email, 'New ' + linkback_type + ' request', content, html_content) + for email in acc_get_authorized_emails('moderatelinkbacks'): + send_email(CFG_SITE_ADMIN_EMAIL, email, 'Pending ' + linkback_type + ' requests', content) def infix_exists_for_url_in_list(url, list_type): """ Check if an infix of a url exists in a list @param url @param list_type, of CFG_WEBLINKBACK_LIST_TYPE @return True, False """ urls = get_url_list(list_type) for current_url in urls: if current_url in url: return True return False +def get_latest_linkbacks_to_accessible_records(rg, linkbacks, user_info): + result = [] + for linkback in linkbacks: + (auth_code, auth_msg) = check_user_can_view_record(user_info, linkback[2]) # pylint: disable=W0612 + if not auth_code: + result.append(linkback) + if len(result) == rg: + break + return result + + def perform_request_display_record_linbacks(req, recid, show_admin, weblinkback_templates, ln): # pylint: disable=W0613 """ Display linkbacks of a record @param recid @param argd @param show_admin: True, False --> show admin parts to approve/reject linkbacks pending requests @param weblinkback_templates: template object reference """ out = weblinkback_templates.tmpl_linkbacks_general(recid=recid, ln=ln) if show_admin: pending_linkbacks = get_all_linkbacks(recid, CFG_WEBLINKBACK_STATUS['PENDING'], CFG_WEBLINKBACK_ORDER_BY_INSERTION_TIME['DESC']) out += weblinkback_templates.tmpl_linkbacks_admin(pending_linkbacks=pending_linkbacks, recid=recid, ln=ln) approved_linkbacks = get_all_linkbacks(recid, CFG_WEBLINKBACK_STATUS['APPROVED'], CFG_WEBLINKBACK_ORDER_BY_INSERTION_TIME['DESC']) out += weblinkback_templates.tmpl_linkbacks(approved_linkbacks=approved_linkbacks, ln=ln) return out -def perform_request_display_approved_latest_added_linkbacks(rg, ln, weblinkback_templates): +def perform_request_display_approved_latest_added_linkbacks_to_accessible_records(rg, ln, user_info, weblinkback_templates): """ - Display approved latest added linbacks + Display approved latest added linbacks to accessible records @param rg: count of linkbacks to display @param weblinkback_templates: template object reference """ - latest_linkbacks = get_approved_latest_added_linkbacks(rg) + latest_linkbacks = get_approved_latest_added_linkbacks(rg * CFG_WEBLINKBACK_LATEST_FACTOR) + latest_linkbacks = get_latest_linkbacks_to_accessible_records(rg, latest_linkbacks, user_info) latest_linkbacks_in_days = split_in_days(latest_linkbacks) out = weblinkback_templates.tmpl_get_latest_linkbacks_top(rg, ln) out += '$ bibsched stop $ cat /opt2/mysql-backups/invenio-dbdump-2009-03-10_22\:10\:28.sql | dbexec $ bibsched start
|
| (%(type)s) %(page_title)s %(submit_date)s |
' out += '''(%(type)s) %(page_title)s''' % { 'type': current_linkback[4], 'origin_url': cgi.escape(url), 'page_title': cgi.escape(get_url_title(url))} out += '' out += '
| CFG_WEBSTYLE_INSPECT_TEMPLATES debugging mode is enabled. Please hover your mouse pointer over any region on the page to see which template function generated it. |
|
%(userinfobox)s
|
|||||||||||
| %(msg_search)s | %(msg_submit)s | %(useractivities)s | %(msg_help)s | %(adminactivities)s||||||||
| %(navtrailbox)s |