swish-e/conf/example4.config

# ----- Example 4 - Site-wide settings -------
#
#  Please see the swish-e documentation for
#  information on configuration directives.
#  Documentation is included with the swish-e
#  distribution, and also can be found on-line
#  at http://swish-e.org
#
#
#  This example demonstrates how to define
#  settings that change the way swish indexes.
#  Since you will probably want consistent
#  settings for all your indexes, you can
#  create one file, and include it in other
#  config files.
#
#  Once you define a common configuration file you
#  can include it in other configuration files.  For
#  example, if this file was saved as "common.config"
#  you can include it in other configuration files
#  with the following directive:
#
#       ...
#       IncludeConfig  /home/swish/common.config
#       ...
#
#---------------------------------------------------

# These settings tell swish what defines a word.

# We only index words that include letters, numbers, a dash,
# or a period.  (Not very realistic)

# These are the characters that are allowed in a "word".
# i.e. words are split on any character NOT found in WordCharacters

WordCharacters abcdefghijklmnopqrstuvwxyz0123456789.-


# We allow a period and a dash within words, but strip them
# from the beginning or end of a word.  This is done after
# WordCharacters above is used to split words.

IgnoreFirstChar .-
IgnoreLastChar  .-

# Finally, resulting words must begin/end with one
# of the characters listed here

BeginCharacters abcdefghijklmnopqrstuvwxyz0123456789
EndCharacters   abcdefghijklmnopqrstuvwxyz0123456789


# Turn this on for a slight performance improvement
#FollowSymLinks yes


# This is how detailed you want reporting. You can specify numbers
# 0 to 3 - 0 is totally silent, 3 is the most verbose.
# 4 is debugging.  Can be overridden with -v on the command line

IndexReport 2


# Set the stopwords (words to ignore when searching and when indexing)
# Carefully think about this feature before using a list of stopwords
# You can list the words here:
#  IgnoreWords of or and the a to
# Or you can use the compiled in defaults:
#  IgnoreWords SwishDefault
# Or you can use a file that includes your own words:

IgnoreWords file: stopwords/my_stopwords.txt

# Another option is to use the IgnoreLimit directive, and
# swish will determine what stopwords to use.  But please
# read the documentation before using the IgnoreLimit directive.
# It can be slow, and may not work with other options.


# Since we are using such a restrictive WordCharacters settings, we
# want to map eight-bit characters to ascii.
# For example, "resum�" will be indexed and searched as "resume".
# See docs for more info.

TranslateCharacters :ascii7:


# We don't want pharse searches to work across sentenses, plus
# we use the pipe "|" to force a break in phrases when indexing.

BumpPositionCounterCharacters |.

# end of example
1	adcroft	1.1	# ----- Example 4 - Site-wide settings -------
2			#
3			# Please see the swish-e documentation for
4			# information on configuration directives.
5			# Documentation is included with the swish-e
6			# distribution, and also can be found on-line
7			# at http://swish-e.org
8			#
9			#
10			# This example demonstrates how to define
11			# settings that change the way swish indexes.
12			# Since you will probably want consistent
13			# settings for all your indexes, you can
14			# create one file, and include it in other
15			# config files.
16			#
17			# Once you define a common configuration file you
18			# can include it in other configuration files. For
19			# example, if this file was saved as "common.config"
20			# you can include it in other configuration files
21			# with the following directive:
22			#
23			# ...
24			# IncludeConfig /home/swish/common.config
25			# ...
26			#
27			#---------------------------------------------------
28
29			# These settings tell swish what defines a word.
30
31			# We only index words that include letters, numbers, a dash,
32			# or a period. (Not very realistic)
33
34			# These are the characters that are allowed in a "word".
35			# i.e. words are split on any character NOT found in WordCharacters
36
37			WordCharacters abcdefghijklmnopqrstuvwxyz0123456789.-
38
39
40			# We allow a period and a dash within words, but strip them
41			# from the beginning or end of a word. This is done after
42			# WordCharacters above is used to split words.
43
44			IgnoreFirstChar .-
45			IgnoreLastChar .-
46
47			# Finally, resulting words must begin/end with one
48			# of the characters listed here
49
50			BeginCharacters abcdefghijklmnopqrstuvwxyz0123456789
51			EndCharacters abcdefghijklmnopqrstuvwxyz0123456789
52
53
54			# Turn this on for a slight performance improvement
55			#FollowSymLinks yes
56
57
58			# This is how detailed you want reporting. You can specify numbers
59			# 0 to 3 - 0 is totally silent, 3 is the most verbose.
60			# 4 is debugging. Can be overridden with -v on the command line
61
62			IndexReport 2
63
64
65			# Set the stopwords (words to ignore when searching and when indexing)
66			# Carefully think about this feature before using a list of stopwords
67			# You can list the words here:
68			# IgnoreWords of or and the a to
69			# Or you can use the compiled in defaults:
70			# IgnoreWords SwishDefault
71			# Or you can use a file that includes your own words:
72
73			IgnoreWords file: stopwords/my_stopwords.txt
74
75			# Another option is to use the IgnoreLimit directive, and
76			# swish will determine what stopwords to use. But please
77			# read the documentation before using the IgnoreLimit directive.
78			# It can be slow, and may not work with other options.
79
80
81			# Since we are using such a restrictive WordCharacters settings, we
82			# want to map eight-bit characters to ascii.
83			# For example, "resum�" will be indexed and searched as "resume".
84			# See docs for more info.
85
86			TranslateCharacters :ascii7:
87
88
89			# We don't want pharse searches to work across sentenses, plus
90			# we use the pipe "\|" to force a break in phrases when indexing.
91
92			BumpPositionCounterCharacters \|.
93
94			# end of example