kris/puppet-pubcrawler
1
0
Fork 0
mirror of https://github.com/krislamo/puppet-pubcrawler synced 2025-10-08 23:59:28 +00:00
Code Issues Releases Wiki Activity

move to github

Browse Source
This commit is contained in:
drew
2018-04-06 14:00:35 -04:00
commit b0b69367c8
7 changed files with 849 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
templates/cron.erb Normal file
View File

@@ -0,0 +1 @@
20 4 * * * nobody /usr/share/pubcrawler/bin/pubcrawler-runall

7
templates/http.pubcrawler.conf.erb Normal file
View File

@@ -0,0 +1,7 @@
Alias /pubcrawler /usr/share/pubcrawler/html
<Directory /usr/share/pubcrawler/html>
Options FollowSymLinks Includes
AllowOverride None
Order allow,deny
Allow from all
</Directory>

255
templates/product.config.erb Normal file
View File

@@ -0,0 +1,255 @@
############ PubCrawler configuration file ############
####### (for PubCrawler Version higher than 0.53) ######
############################################################
# #
# lines beginning with hash marks (#) are ignored. #
# #
# PubCrawler home page: #
# http://www.pubcrawler.ie #
# #
# Specify your file locations and search options here. #
# Each line is in the format FIELD space VALUE. #
# Any leading or trailing quotes will be chopped off. #
# Hash marks separate comments from data. #
# You must specify a value for all 6 mandatory fields. #
# #
############################################################
############################################################
################# MANDATORY SETTINGS #######################
############################################################
project <%= @name %>
# Identifier for a project. This value is displayed in the header
# of the results page.
background_color <%= @bgcolor %>
# background color for sectional headers of the result page.
header_icon <%= @header_icon %>
# relative or absolute URL for icon to display in results page
# header.
<%- if @html_file -%>
html_file <%= @html_file %>
<%- else -%>
html_file /usr/share/pubcrawler/html/<%= @name %>/index.html
<%- end -%>
# html_file is the name of the output HTML file for results
# it will be written to the specified working directory
# unless an absolute pathname is given
viewdays <%= @viewdays %>
# viewdays is the number of days each document will be shown.
relentrezdate <%= @relentrezdate %>
# relentrezdate (relative date of insertion into Entrez)
# is the maximum age (in days) of database entries to be reported.
# NOTE: sometimes records first appear in the databases several
# days or even weeks later than indicated by their database
# date-stamp, i.e. with non-zero values of relentrezdate.
# Therefore relentrezdate needs to be high enough to find these
# records. A relentrezdate of 90 days is suggested (if you make
# relentrezdate too huge the searches will be very slow.)
# other valid entries are:
# '1 year', '2 years', '5 years', '10 years', and 'no limit'
getmax <%= @getmax %>
# getmax is the maximum number of documents to be retrieved
# for each search carried out.
fullmax <%= @fullmax %>
# fullmax is the maximum number of documents for which a full
# report is being presented
# if more documents were retrieved, these can be accessed
# through a hyperlink (in groups of up to fullmax articles)
include_config <%= @include_config %>
# include_config (yes/no) specifies whether or not to append
# this config-file to the end of the output file
#-------------------------------------------------------------------#
############################################################
################## OPTIONAL SETTINGS #######################
############################################################
search_URL <%= @search_URL %>
# URL where searches are being sent to
# defaults to
# https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi
neighbour_URL <%= @neighbour_URL %>
# URL where neighbourhood searches are being sent to
# defaults to
# https://www.ncbi.nlm.nih.gov/entrez/utils/pmneighbor.fcgi
retrieve_URL <%= @retrieve_URL %>
# URL where documents are retrieved from
# defaults to
# https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi
<%- if @work_dir -%>
work_dir <%= @work_dir %>
<%- else -%>
work_dir /var/lib/pubcrawler/<%= @name %>
<%- end -%>
# specify a directory in which databases, output and log file
# will be located
# if no value given, the current working directory will be used
extra_range <%= @extra_range %>
# specifies the number of documents combined in a link
# minimum value is 1, defaults to 'fullmax'
check <%= @check %>
# if set to '1' program will just check all settings
# without performing the actual search
# RECOMMENDED FOR THE FIRST RUN!
prompt <%= @prompt %>
# for Mac-users only:
# if this option is set to '1' the program will ask you
# explicitly for command line options
# NOTE: THIS IS NOT SUITABLE FOR AUTOMATED USE!
verbose <%= @verbose %>
# verbose 0 runs silently and makes log file
# verbose 1 writes log output on screen
mute <%= @mute %>
# mute 0 writes some messages to STDERR
# mute 1 stops ALL messages going to STDERR
# unless an error was encountered
log_file <%= @log_file %>
# name of file for log-output
# (verbose has to be set to '0')
#base_URL 'http://www.gen.tcd.ie/pubcrawler/pubcrawler_output.html'
base_URL <%= @base_URL %>
# specify a URL, that will be used for
# the 'Back to Top' link in the output page
# 'local_file' makes links relative to results file
# mail joe@hotmail.earth.com
# if the hash mark ('#') at the beginning of the above line
# is removed, PubCrawler will send the results file to
# the given address at the end of each run. You can specify
# multiple addresses using commas (no spaces!).
# notify jfk@hotmail.earth.com#joe
# if the hash mark ('#') at the beginning of the above line
# is removed, PubCrawler will send a notification to
# the given address (minus '#joe') at the end of each run
# The recipient will be addressed with joe (optional).
# You can specify multiple addresses using commas (no spaces!).
mail_features <%= @mail_features %>
# comma-separated list of extra features for the mail
# to be sent (without them it will be plain text). These are:
# css,javascript,entrez_links,pubcrawler_links,images,html,description
# or simply 'all' for everything
lynx <%= @lynx %>
# for Unix-users only:
# if you don't want to use the libwww-Perl module and
# have an alternative browser installed, that works from the
# command line, like 'Lynx', you can use it by entering the
# command that evokes it (e.g. lynx '/usr/bin/lynx')
# NOTE: THIS OVERRIDES ANY PROXY SETTINGS!
#header 'head.html'
# specify a location of a header (in HTML-style) that will be used
# for the output file (disabled unless hash mark is removed)
prefix <%= @prefix %>
# if you would like a different prefix to be used
# for standard files (configuration, database, log)
# insert it here (default is program name up to first dot):
system <%= @system %>
# name of operating system
# might need the explicit assignment of an adequate value
# ('MacOS','Win','Unix', or 'Linux')
# if Perl is not configured properly
#### PROXY SETTING (if desired and/or necessary) ####
#proxy www.tcd.ie/proxy.cgi
# insert either a proxy server (eg. 'proxy.domain.com')
# or the address of a proxy configuration file
# if known (eg. 'www.domain.com/proxy.cgi')
# and uncomment
proxy_port <%= @proxy_port %>
# port of the proxy server,defaults to '80'
proxy_auth <%= @proxy_auth %>
proxy_pass <%= @proxy_pass %>
# in case you need to submit a username and a password
# for accessing your proxy, you can fill it in here:
# CAUTION! Having passwords stored in a file means a
# possible security risk! Please delete after usage
# or use the according command line option!
# !!! Please make sure that the module MIME::Base64 is
# installed for the proxy authorization to work!!!
time_out <%= @time_out %>
# specify how many SECONDS to give remote servers
# in creating responses before the library disconnects
# (defaults to 180 seconds if no value is given)
test_URL <%= @test_URL %>
# test-URL for proxy-test
no_test <%= @no_test %>
# if a proxy is given, the internet connection is tested
# at the start of the program by default; this can be
# suppressed if a value of '1' is given here
indent <%= @indent %>
# amount of pixels that output is being shifted to the right
no_decap <%= @no_decap %>
# put 1 inbetween single quotes if you want to disable
# processing of the entrez documents (chopping of head and tail
# and collecting UIs)
spacer <%= @spacer %>
# specify a gif that will be inserted in the output to shift
# text past the left, blue column
# (defaults to: http://www.gen.tcd.ie/pubcrawler/pics/spacer.gif)
#-----------------------------------------------------------------------------#
############################################################
################# SEARCH SPECIFICATION #####################
############################################################
###########################################################################
###### Entrez abbreviations for fields #
###### (see http://www4.ncbi.nlm.nih.gov/PubMed/linking.html). #
###### combine fields with AND, OR, BUTNOT and parentheses. #
# #
# for PubMed : one of AFFL, ALL, AUTH, ECNO, JOUR, MESH, MAJR, PAGE, #
# PDAT, PTYP, KYWD, WORD, TITLE, or VOL. #
# for Nucleotide : one of ACCN, AUTH, PDAT, ECNO, FKEY, GENE, JOUR, KYWD, #
# MDAT, ORGN, PROP, PROT, SQID, SLEN, SUBS, or #
# WORD. #
# #
# where ACCN = Accession Number, AFFL = Afilliation, ALL = all fields, #
# AUTH = Author Name, ECNO = E. C. Number, FKEY = Feature Key, #
# GENE = gene name, JOUR =journal name, KYWD = Keywords, #
# MAJR = MeSH major topic, MDAT = modification date, #
# MESH = mesh term,ORGN = organism, PACC = Primary Accesion Number, #
# PAGE = first page, PDAT = publication/creation date, #
# PROP = Properties, PROT = protein name, PTYP = Publication Type, #
# SUBS = Substance, TITL = title word, WORD = text word, #
# VOL = volume. #
###########################################################################
##### Each search-specification has to be written on one line.
##### The first word must specify the database:
##### pubmed, pm_neighbour, genbank, or gb_neighbour
##### Any following words enclosed in single quotes (') will be used
##### as an alias for this query, otherwise they will be considered
##### Entrez-search-terms, as will the rest of the line.
##### You can have as many different searches as you wish. The results of all
##### searches will be combined according to their aliases.
##### You CAN NOT use the same alias for searches at different databases!
##### Write your search descriptions below this line.
##### (Upper/lower case does not matter.)
<%- if @searches and @searches.kind_of?(Array) -%>
<%- @searches.each do |search| -%>
<%= search['database'] %> '<%= search['alias'] %>' <%= search['term'] %>
<%- end -%>
<%- end -%>