From 4bb10495d685c2870399bb4393bab216797e2f22 Mon Sep 17 00:00:00 2001 From: Scott Chacon Date: Fri, 10 Oct 2008 19:41:41 -0700 Subject: [PATCH] added an example sphinx configuration file that uses gitsphinx --- sphinx.conf.example | 125 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 125 insertions(+) create mode 100644 sphinx.conf.example diff --git a/sphinx.conf.example b/sphinx.conf.example new file mode 100644 index 0000000..2dc4351 --- /dev/null +++ b/sphinx.conf.example @@ -0,0 +1,125 @@ + +source main +{ + type = xmlpipe2 + xmlpipe_command = /opt/gitsphinx/index.rb --main +} + +source delta : main +{ + xmlpipe_command = /opt/gitsphinx/index.rb --new +} + +############################################################################# +## index definition +############################################################################# + +index main +{ + source = main + + # index files path and file name, without extension + # mandatory, path must be writable, extensions will be auto-appended + path = /opt/data/main + + # document attribute values (docinfo) storage mode + # optional, default is 'extern' + # known values are 'none', 'extern' and 'inline' + docinfo = extern + mlock = 0 + + # a list of morphology preprocessors to apply + # builtin preprocessors are 'none', 'stem_en', 'stem_ru', 'stem_enru', + # 'soundex', and 'metaphone'; additional preprocessors available from + # morphology = stem_en, stem_ru, soundex + # morphology = libstemmer_german + # morphology = libstemmer_sv + morphology = none + + # stopword files list (space separated) + # contents are plain text, charset_table and stemming are both applied + # stopwords = /var/data/stopwords.txt + + # wordforms file, in "mapfrom > mapto" plain text format + # wordforms = /var/data/wordforms.txt + + # tokenizing exceptions file + # exceptions = /var/data/exceptions.txt + + # minimum indexed word length + min_word_len = 4 + + # charset encoding type + # known types are 'sbcs' (Single Byte CharSet) and 'utf-8' + charset_type = utf-8 + + # charset definition and case folding rules "table" + # 'utf-8' default value is + # charset_table = 0..9, A..Z->a..z, _, a..z, U+410..U+42F->U+430..U+44F, U+430..U+44F + + # ignored characters list + # ignore_chars = U+00AD + + # minimum word prefix length to index + # min_prefix_len = 0 + + # minimum word infix length to index + # min_infix_len = 0 + + # list of fields to limit prefix/infix indexing to + # prefix_fields = filename + # infix_fields = url, domain + + # enable star-syntax (wildcards) when searching prefix/infix indexes + # enable_star = 1 + + # phrase boundary characters list + # phrase_boundary = ., ?, !, U+2026 # horizontal ellipsis + + # phrase boundary word position increment + # phrase_boundary_step = 100 +} + + +index delta : main +{ + source = delta + path = /opt/data/delta +} + +############################################################################# +## indexer settings +############################################################################# + +indexer +{ + # memory limit, in bytes, kiloytes (16384K) or megabytes (256M) + # optional, default is 32M, max is 2047M, recommended is 256M to 1024M + mem_limit = 256M + + # maximum IO calls per second (for I/O throttling) + # max_iops = 40 + # maximum IO call size, bytes (for I/O throttling) + # max_iosize = 1048576 +} + +############################################################################# +## searchd settings +############################################################################# + +searchd +{ + # address = 192.168.0.1 + port = 3312 + log = /var/log/searchd.log + query_log = /var/log/query.log + read_timeout = 5 + max_children = 30 + pid_file = /var/log/searchd.pid + max_matches = 1000 + seamless_rotate = 1 + preopen_indexes = 0 + unlink_old = 1 +} + +# --eof--