# DIRECTIVES COMMON to  HTTP and FILESYSTEM METHODS
###################################################
# WINDOWS USERS NOTE:
#	Specify ALL files and directory paths in the
#	the config file using the forward slash, as
#	in /thisdirectory.	
#
###################################################

IndexDir http://www.lib.berkeley.edu/~ghill/spider.html
# For the FileSystem Method:
# This is a space-separated list of files and
# directories you want indexed. You can specify
# more than one of these directives.
#
# For the HTTP Method:
# Use the URL's from which you want the spidering
# to begin.
# NOTE: use  hmtl files rather than  directories
# for this method.

IndexFile /home/ghill/swishRon/dir1/myindex1
# This is what the generated index file will be.

IndexName "Improvement index"
IndexDescription "This is an index to test bug fixes in swish." 
IndexPointer "http://sunsite/~ghill/swish/index.html"
IndexAdmin "Giulia Hill, (ghill@library.berkeley.edu)"
# Extra information you can include in the index file.

MetaNames first author
# List of all the meta names used in the file to index, must be on one line.
# If no metanames DO NOT deleted the line.

IndexReport 3
# This is how detailed you want reporting. You can specify numbers
# 0 to 3 - 0 is totally silent, 3 is the most verbose.

FollowSymLinks yes
# Put "yes" to follow symbolic links in indexing, else "no".

#UseStemming no
# Put yes to apply word stemming algorithm during indexing,
# else no. See the manual for info about stemming. Default is 
# no.

#PropertyNames author
# List of meta tags names that can be retrieved with the -p option.
# Index size increases as by the formula in the manual.
# Comment out if no PropertyNames. Case insensitive

IgnoreTotalWordCountWhenRanking yes
# Put yes to ignore the total number of words in the file
# when calculating ranking. Often better with merges and
# small files. Default is no.

ReplaceRules remove "ghill/"
ReplaceRules replace "[a-z_0-9]*_m.*\.html" "index.html"
#ReplaceRules replace "/ghill" "moreghillmore"
# ReplaceRules allow you to make changes to file pathnames
# before they're indexed. This directive uses C library
# regex.h regular expressions.
# NOTE: do not use replace  "" to remove a string,
# use remove  instead - you might get a core dump otherwise.

#MinWordLimit 5
# Set the minimum length of an indexable word. Every shorter word
# will not be indexed.
# Commenting out the line will give the defaults

#MaxWordLimit 5
# Set the maximum length of an indexable word. Every longer word
# will not be indexed.
# Commenting out the line will give the defaults

#WordCharacters abcdefghijklmnopqrstuvwxyz\&#;0123456789.@|,-'"[](~!@$%^{}_+?
# WORDCHARS is a string of characters which SWISH permits to
# be in words. Any strings which do not include these characters
# will not be indexed. You can choose from any character in
# the following string:
#
# abcdefghijklmnopqrstuvwxyz0123456789_\|/-+=?!@$%^'"`~,.[]{}()
#
# Note that if you omit "0123456789&#;" you will not be able to
# index HTML entities. DO NOT use the asterisk (*), lesser than
# and greater than signs (<), (>), or colon (:).
#
# Including any of these four characters may cause funny things to happen.
# NOTE: Do not escape \ nor " and they cannot be the first letter in the string
# Commenting out the line will give the defaults

#BeginCharacters m"
# Of the characters that you decide can go into words, this is
# a list of characters that words can begin with. It should be
# a subset of (or equal to) WordCharacters
# Same rule of syntax as for WordCharacters

#EndCharacters \"\
# Of the characters that you decide can go into words, this is
# a list of characters that words can begin with. It should be
# a subset of (or equal to) WordCharacters
# Same rule of syntax as for WordCharacters

IgnoreLastChar 
# Array that contains the char that, if considered valid in the middle of 
# a word need to be disreguarded when at the end. It is important to also
# set the given char's in the ENDCHARS array, otherwise the word will not
# be indexed because considered invalid.
# Commenting out the line will give the defaults
# NOTE: if " is the first char in the string it needs to be escaped with \
# Do not escape otherwise

IgnoreFirstChar 
# Array that contains the char that, if considered valid in the middle of
# a word need to be disreguarded when at the beginning. This was to solve
# the problem of parenthesis when there is no space between ( and the
# beginning of the word.
# Remember to add the char's to the BEGINCHARS list also.
# Commenting out the line will give the defaults
# NOTE: if " is the first char in the string it needs to be escaped with \
# Do not escape otherwise

IgnoreLimit 50 1000
# This automatically omits words that appear too often in the files
# (these words are called stopwords). Specify a whole percentage
# and a number, such as "80 256". This omits words that occur in
# over 80% of the files and appear in over 256 files. Comment out
# to turn of auto-stopwording.

#IgnoreWords SwishDefault
# The IgnoreWords option allows you to specify words to ignore.
# Comment out for no stopwords; the word "SwishDefault" will
# include a list of default stopwords. Words should be separated by spaces
# and may span multiple directives.

IndexComments 0
# This option allows the user decide if to index the comments in the files
# default is 1. Set to 0 if comment indexing is not required.

##################################
# DIRECTIVES for FILESYSTEMS ONLY 
# Comment out if using HTTP
###################################

#IndexOnly .html .q
# Only files with these suffixes will be indexed.

#NoContents .gif .xbm .au .mov .mpg .pdf .ps
# Files with these suffixes will not have their contents indexed -
# only their file names will be indexed.

#FileRules pathname contains .*dir1
#FileRules filename contains # % ~ .bak .orig .old old.
#FileRules title contains construction example pointers
#FileRules directory contains .htaccess
#FileRules filename is index
# Files matching the above criteria will *not* be indexed.
# The patter matching uses the C library regex.h 

################################
# DIRECTIVES for HTTP METHOD ONLY
# Comment out if using FILESYSTEM
##################################

MaxDepth 5
#(default 5)  This defines how many links the spider should
#follow before stopping.  A value of 0 configures the spider to
#traverse all links

Delay 60
#(default 60)  The number of seconds to wait between issuing
#requests to a server.

TmpDir /home/ghill/swishRon/
#(default /var/tmp)  The location of a writeable temp directory
#on your system.  The HTTP access method tells the Perl helper to place
#its files there.

SpiderDirectory /home/ghill/swishRon/src/
#(default ./)  The location of the Perl helper
#script.  Remember, if you use a relative directory, it is relative to
#your directory when you run SWISH-E, not to the directory that SWISH-E
#is in.

EquivalentServer http://library.berkeley.edu http://www.lib.berkeley.edu
EquivalentServer http://sunsite.berkeley.edu:2000 http://sunsite.berkeley.edu
#(default nothing)  This allows you to deal with
#servers that use respond to multiple DNS names.  Each line should have
#a list of all the method/names that should be considered equivalent. 
#If you have multiple directives, each one defines its own set of equivalent
#servers.