sphinx.conf.in

#
# Sphinx configuration file sample
#
# WARNING! While this sample file mentions all available options,
# it contains (very) short helper descriptions only. Please refer to
# doc/sphinx.html for details.
#

#############################################################################
## data source definition
#############################################################################

source src1
{
	# data source type. mandatory, no default value
	# known types are 'mysql', 'pgsql', 'xmlpipe', 'xmlpipe2'
	type					= mysql

	#####################################################################
	## SQL settings (for 'mysql' and 'pgsql' types)
	#####################################################################

	# some straightforward parameters for SQL source types
	sql_host				= localhost
	sql_user				= test
	sql_pass				=
	sql_db					= test
	sql_port				= 3306	# optional, default is 3306

	# UNIX socket name
	# optional, default is empty (reuse client library defaults)
	# usually '/var/lib/mysql/mysql.sock' on Linux
	# usually '/tmp/mysql.sock' on FreeBSD
	#
	# sql_sock				= /tmp/mysql.sock


	# MySQL specific client connection flags
	# optional, default is 0
	#
	# mysql_connect_flags	= 32 # enable compression


	# pre-query, executed before the main fetch query
	# multi-value, optional, default is empty list of queries
	#
	# sql_query_pre			= SET NAMES utf8
	# sql_query_pre			= SET SESSION query_cache_type=OFF


	# main document fetch query
	# mandatory, integer document ID field MUST be the first selected column
	sql_query				= \
		SELECT id, group_id, UNIX_TIMESTAMP(date_added) AS date_added, title, content \
		FROM documents

	# range query setup, query that must return min and max ID values
	# optional, default is empty
	#
	# sql_query will need to reference $start and $end boundaries
	# if using ranged query:
	#
	# sql_query				= \
	#	SELECT doc.id, doc.id AS group, doc.title, doc.data \
	#	FROM documents doc \
	#	WHERE id>=$start AND id<=$end
	#
	# sql_query_range		= SELECT MIN(id),MAX(id) FROM documents


	# range query step
	# optional, default is 1024
	#
	# sql_range_step		= 1000


	# unsigned integer attribute declaration
	# multi-value (an arbitrary number of attributes is allowed), optional
	# optional bit size can be specified, default is 32
	#
	# sql_attr_uint			= author_id
	# sql_attr_uint			= forum_id:9 # 9 bits for forum_id
	sql_attr_uint			= group_id

	# boolean attribute declaration
	# multi-value (an arbitrary number of attributes is allowed), optional
	# equivalent to sql_attr_uint with 1-bit size
	#
	# sql_attr_bool			= is_deleted

	
	# UNIX timestamp attribute declaration
	# multi-value (an arbitrary number of attributes is allowed), optional
	# similar to integer, but can also be used in date functions
	#
	# sql_attr_timestamp	= posted_ts
	# sql_attr_timestamp	= last_edited_ts
	sql_attr_timestamp		= date_added

	# string ordinal attribute declaration
	# multi-value (an arbitrary number of attributes is allowed), optional
	# sorts strings (bytewise), and stores their indexes in the sorted list
	# sorting by this attr is equivalent to sorting by the original strings
	#
	# sql_attr_str2ordinal	= author_name


	# floating point attribute declaration
	# multi-value (an arbitrary number of attributes is allowed), optional
	# values are stored in single precision, 32-bit IEEE 754 format
	#
	# sql_attr_float = lat_radians
	# sql_attr_float = long_radians


	# multi-valued attribute (MVA) attribute declaration
	# multi-value (an arbitrary number of attributes is allowed), optional
	# MVA values are variable length lists of unsigned 32-bit integers
	#
	# syntax is ATTR-TYPE ATTR-NAME 'from' SOURCE-TYPE [;QUERY] [;RANGE-QUERY]
	# ATTR-TYPE is 'uint' or 'timestamp'
	# SOURCE-TYPE is 'field', 'query', or 'ranged-query'
	# QUERY is SQL query used to fetch all ( docid, attrvalue ) pairs
	# RANGE-QUERY is SQL query used to fetch min and max ID values, similar to 'sql_query_range'
	#
	# sql_attr_multi	= uint tag from query; SELECT id, tag FROM tags
	# sql_attr_multi	= uint tag from ranged-query; \
	#	SELECT id, tag FROM tags WHERE id>=$start AND id<=$end; \
	#	SELECT MIN(id), MAX(id) FROM tags


	# post-query, executed on sql_query completion
	# optional, default is empty
	#
	# sql_query_post		=

	
	# post-index-query, executed on successful indexing completion
	# optional, default is empty
	# $maxid expands to max document ID actually fetched from DB
	#
	# sql_query_post_index = REPLACE INTO counters ( id, val ) \
	#	VALUES ( 'max_indexed_id', $maxid )


	# ranged query throttling, in milliseconds
	# optional, default is 0 which means no delay
	# enforces given delay before each query step
	sql_ranged_throttle	= 0

	
	# document info query, ONLY for CLI search (ie. testing and debugging)
	# optional, default is empty
	# must contain $id macro and must fetch the document by that id
	sql_query_info		= SELECT * FROM documents WHERE id=$id

	#####################################################################
	## xmlpipe settings
	#####################################################################

	# type				= xmlpipe

	# shell command to invoke xmlpipe stream producer
	# mandatory
	#
	# xmlpipe_command	= cat @CONFDIR@/test.xml

	#####################################################################
	## xmlpipe2 settings
	#####################################################################

	# type				= xmlpipe2
	# xmlpipe_command	= cat @CONFDIR@/test2.xml


	# xmlpipe2 field declaration
	# multi-value, optional, default is empty
	#
	# xmlpipe_field				= subject
	# xmlpipe_field				= content


	# xmlpipe2 attribute declaration
	# multi-value, optional, default is empty
	# all xmlpipe_attr_XXX options are fully similar to sql_attr_XXX
	#
	# xmlpipe_attr_timestamp	= published
	# xmlpipe_attr_uint			= author_id
}


# inherited source example
#
# all the parameters are copied from the parent source,
# and may then be overridden in this source definition
source src1throttled : src1
{
	sql_ranged_throttle			= 100
}

#############################################################################
## index definition
#############################################################################

# local index example
#
# this is an index which is stored locally in the filesystem
#
# all indexing-time options (such as morphology and charsets)
# are configured per local index
index test1
{
	# document source(s) to index
	# multi-value, mandatory
	# document IDs must be globally unique across all sources
	source			= src1

	# index files path and file name, without extension
	# mandatory, path must be writable, extensions will be auto-appended
	path			= @CONFDIR@/data/test1

	# document attribute values (docinfo) storage mode
	# optional, default is 'extern'
	# known values are 'none', 'extern' and 'inline'
	docinfo			= extern

	# memory locking for cached data (.spa and .spi), to prevent swapping
	# optional, default is 0 (do not mlock)
	# requires searchd to be run from root
	mlock			= 0

	# a list of morphology preprocessors to apply
	# optional, default is empty
	#
	# builtin preprocessors are 'none', 'stem_en', 'stem_ru', 'stem_enru',
	# 'soundex', and 'metaphone'; additional preprocessors available from
	# libstemmer are 'libstemmer_XXX', where XXX is algorithm code
	# (see libstemmer_c/libstemmer/modules.txt)
	#
	# morphology 	= stem_en, stem_ru, soundex
	# morphology	= libstemmer_german
	# morphology	= libstemmer_sv
	morphology		= none

	# stopword files list (space separated)
	# optional, default is empty
	# contents are plain text, charset_table and stemming are both applied
	#
	# stopwords			= @CONFDIR@/data/stopwords.txt


	# wordforms file, in "mapfrom > mapto" plain text format
	# optional, default is empty
	#
	# wordforms			= @CONFDIR@/data/wordforms.txt


	# tokenizing exceptions file
	# optional, default is empty
	#
	# plain text, case sensitive, space insensitive in map-from part
	# one "Map Several Words => ToASingleOne" entry per line
	#
	# exceptions		= @CONFDIR@/data/exceptions.txt


	# minimum indexed word length
	# default is 1 (index everything)
	min_word_len		= 1

	# charset encoding type
	# optional, default is 'sbcs'
	# known types are 'sbcs' (Single Byte CharSet) and 'utf-8'
	charset_type		= sbcs

	# charset definition and case folding rules "table"
	# optional, default value depends on charset_type
	#
	# defaults are configured to include English and Russian characters only
	# you need to change the table to include additional ones
	# this behavior MAY change in future versions
	#
	# 'sbcs' default value is
	# charset_table		= 0..9, A..Z->a..z, _, a..z, U+A8->U+B8, U+B8, U+C0..U+DF->U+E0..U+FF, U+E0..U+FF
	#
	# '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
	# optional, default value is empty
	#
	# ignore_chars		= U+00AD


	# minimum word prefix length to index
	# optional, default is 0 (do not index prefixes)
	#
	# min_prefix_len	= 0


	# minimum word infix length to index
	# optional, default is 0 (do not index infixes)
	#
	# min_infix_len		= 0


	# list of fields to limit prefix/infix indexing to
	# optional, default value is empty (index all fields in prefix/infix mode)
	#
	# prefix_fields		= filename
	# infix_fields		= url, domain


	# enable star-syntax (wildcards) when searching prefix/infix indexes
	# known values are 0 and 1
	# optional, default is 0 (do not use wildcard syntax)
	#
	# enable_star		= 1


	# n-gram length to index, for CJK indexing
	# only supports 0 and 1 for now, other lengths to be implemented
	# optional, default is 0 (disable n-grams)
	#
	# ngram_len				= 1


	# n-gram characters list, for CJK indexing
	# optional, default is empty
	#
	# ngram_chars			= U+3000..U+2FA1F


	# phrase boundary characters list
	# optional, default is empty
	#
	# phrase_boundary		= ., ?, !, U+2026 # horizontal ellipsis


	# phrase boundary word position increment
	# optional, default is 0
	#
	# phrase_boundary_step	= 100


	# whether to strip HTML tags from incoming documents
	# known values are 0 (do not strip) and 1 (do strip)
	# optional, default is 0
	html_strip				= 0

	# what HTML attributes to index if stripping HTML
	# optional, default is empty (do not index anything)
	#
	# html_index_attrs		= img=alt,title; a=title;


	# what HTML elements contents to strip
	# optional, default is empty (do not strip element contents)
	#
	# html_remove_elements	= style, script


	# whether to preopen index data files on startup
	# optional, default is 0 (do not preopen)
	#
	# preopen				= 1
}


# inherited index example
#
# all the parameters are copied from the parent index,
# and may then be overridden in this index definition
index test1stemmed : test1
{
	path			= @CONFDIR@/data/test1stemmed
	morphology		= stem_en
}


# distributed index example
#
# this is a virtual index which can NOT be directly indexed,
# and only contains references to other local and/or remote indexes
index dist1
{
	# 'distributed' index type MUST be specified
	type				= distributed

	# local index to be searched
	# there can be many local indexes configured
	local				= test1
	local				= test1stemmed

	# remote agent
	# multiple remote agents may be specified
	# syntax is 'hostname:port:index1,[index2[,...]]
	agent				= localhost:3313:remote1
	agent				= localhost:3314:remote2,remote3

	# remote agent connection timeout, milliseconds
	# optional, default is 1000 ms, ie. 1 sec
	agent_connect_timeout	= 1000

	# remote agent query timeout, milliseconds
	# optional, default is 3000 ms, ie. 3 sec
	agent_query_timeout		= 3000
}

#############################################################################
## 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			= 32M

	# maximum IO calls per second (for I/O throttling)
	# optional, default is 0 (unlimited)
	#
	# max_iops			= 40


	# maximum IO call size, bytes (for I/O throttling)
	# optional, default is 0 (unlimited)
	#
	# max_iosize		= 1048576
}

#############################################################################
## searchd settings
#############################################################################

searchd
{
	# IP address to bind on
	# optional, default is 0.0.0.0 (ie. listen on all interfaces)
	#
	# address				= 127.0.0.1
	# address				= 192.168.0.1


	# searchd TCP port number
	# mandatory, default is 3312
	port				= 3312

	# log file, searchd run info is logged here
	# optional, default is 'searchd.log'
	log					= @CONFDIR@/log/searchd.log

	# query log file, all search queries are logged here
	# optional, default is empty (do not log queries)
	query_log			= @CONFDIR@/log/query.log

	# client read timeout, seconds
	# optional, default is 5
	read_timeout		= 5

	# maximum amount of children to fork (concurrent searches to run)
	# optional, default is 0 (unlimited)
	max_children		= 30

	# PID file, searchd process ID file name
	# mandatory
	pid_file			= @CONFDIR@/log/searchd.pid

	# max amount of matches the daemon ever keeps in RAM, per-index
	# WARNING, THERE'S ALSO PER-QUERY LIMIT, SEE SetLimits() API CALL
	# default is 1000 (just like Google)
	max_matches			= 1000

	# seamless rotate, prevents rotate stalls if precaching huge datasets
	# optional, default is 1
	seamless_rotate		= 1

	# whether to forcibly preopen all indexes on startup
	# optional, default is 0 (do not preopen)
	preopen_indexes		= 0

	# whether to unlink .old index copies on succesful rotation.
	# optional, default is 1 (do unlink)
	unlink_old			= 1
}

# --eof--