############   PubCrawler configuration file   ############
    ############   (for PubCrawler Version 0.9x)   ############

    ############################################################
    #                                                          #
    #   lines beginning with hash marks (#) are ignored.       #
    #                                                          #
    #   PubCrawler home page:                                  #
    #            http://pubcrawler.gen.tcd.ie/pubcrawler              #
    #                                                          #
    #   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 7 mandatory fields.   #
    #                                                          #
    ############################################################

    ############################################################
    ################# MANDATORY SETTINGS #######################
    ############################################################
html_file pubcrawler_output.html   
              # 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 10   
              # viewdays is the number of days each document will be shown.

relpubdate 90
              # relpubdate (relative publication date) 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 relpubdate.
              # Therefore relpubdate needs to be high enough to find these
              # records.  A relpubdate of 90 days is suggested (if you make 
              # relpubdate too huge the searches will be very slow.)
	      # other valid entries are: 
	      # '1 year', '2 years', '5 years', '10 years', and 'no limit'

getmax 200    # getmax is the maximum number of documents to be retrieved
	      # for each search carried out.

fullmax 20    # 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 no  
              # include_config (yes/no) specifies whether or not to append this 
              # config-file to the end of the output file

search_URL http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi
	      # URL from which documents are being requested

#-------------------------------------------------------------------#
    ############################################################
    ################## OPTIONAL SETTINGS #######################
    ############################################################
work_dir                            
	# specify a directory in which databases, output and log file 
	# will be located
	# if no value given, the current working directory will be used

check 0
	# if set to '1' program will just check all settings
	# without performing the actual search
	# RECOMMENDED FOR THE FIRST RUN!

prompt 1
	# 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 0                                                    
	#verbose 0 runs silently and makes log file                 
	#verbose 1 writes log output on screen                      

mute 0
        # mute 0 writes some messages to STDERR
        # mute 1 stops ALL messages going to STDERR
        # unless an error was encountered  
        # if verbose is set to '0' PubCrawler will run
        # completely quiet     

log_file ''
	# name of file for log-output
	# (verbose has to be set to '0')             

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 ''
	# location of a header (in HTML-style) that will be used
	# for the output file

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 ''
	# 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')

proxy_port ''    
	# port of the proxy server,defaults to '80'

proxy_auth ''
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 180 
	# 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 http://www.ncbi.nlm.nih.gov/ 
	      # test-URL for proxy-test

no_test 0
	# 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

#--------------------------------------------------------------------------------#
	    ############################################################
	    ################# 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, and VOL = volume.                #
    ###############################################################################

##### Each search-specification has to be written on one line.
##### The first word must specify the database (genbank or pubmed).
##### 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.)


	# The next query searches PubMed for all articles about 'candida', 
	# skipping those that contain the phrase 'candida albicans':
pubmed 'Candida' candida[ALL] BUTNOT "candida albicans"[ALL]

	# The next three queries search PubMed for articles  
	# by three different authors:
pubmed 'Rivals' Dujon B[AUTH]
pubmed 'Rivals' Oliver SG[AUTH]
pubmed 'Rivals' Philippsen P[AUTH]

	# The next two queries search PubMed for yeast-specific
	# information with particular emphasis on two journals:
pubmed 'Yeast' yeast[ALL] AND (DNA[ALL] OR gene[ALL])
pubmed 'Yeast' (Mol Cell Biol[JOUR] OR Curr Genet[JOUR]) AND yeast[ALL]

	# The next query searches GenBank for all human sequences  
	# with length between 50000 and 350000 bases, 
	# where JC Venter appears as author:
	# (This search has no alias.)
genbank 50000:350000[SLEN] AND Venter JC[AUTH] AND human[ORGN]

	# Example for query matching a wild-card:
	# This will match words such as 'synthesis', 'synthase', etc.
	# ESTs have been excluded.
genbank 'Acyl-CoA synth*' acyl-coa synth*[ALL] BUTNOT est[PROP]