Install Sphinx and php .so in Ubuntu 12.04

sphinx.conf

#############################################################################
## data source definitions
#############################################################################

source users
{
	# data source type. mandatory, no default value
	# known types are mysql, pgsql, mssql, xmlpipe, xmlpipe2, odbc
	type			= mysql

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

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


	# 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

	sql_query		= \
		SELECT user_id+10*1 as source_id, user_id as item_id, 0 as type_id, user_first_name, user_last_name, user_name \
		FROM user


	# joined/payload field fetch query
	# joined fields let you avoid (slow) JOIN and GROUP_CONCAT
	# payload fields let you attach custom per-keyword values (eg. for ranking)
	#
	# syntax is FIELD-NAME 'from'  ( 'query' | 'payload-query' ); QUERY
	# joined field QUERY should return 2 columns (docid, text)
	# payload field QUERY should return 3 columns (docid, keyword, weight)
	#
	# REQUIRES that query results are in ascending document ID order!
	# multi-value, optional, default is empty list of queries
	#
	# sql_joined_field	= tags from query; SELECT docid, CONCAT('tag',tagid) FROM tags ORDER BY docid ASC
	# sql_joined_field	= wtags from payload-query; SELECT docid, tag, tagweight FROM tags ORDER BY docid ASC


	# 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		= item_id
	sql_attr_uint		= type_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


	# bigint attribute declaration
	# multi-value (an arbitrary number of attributes is allowed), optional
	# declares a signed (unlike uint!) 64-bit attribute
	#
	# sql_attr_bigint		= my_bigint_id


	# 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 docid, tagid FROM tags
	# sql_attr_multi		= uint tag from ranged-query; \
	#	SELECT docid, tagid FROM tags WHERE id>=$start AND id<=$end; \
	#	SELECT MIN(docid), MAX(docid) FROM tags


	# string attribute declaration
	# multi-value (an arbitrary number of these is allowed), optional
	# lets you store and retrieve strings
	#
	# sql_attr_string		= stitle


	# wordcount attribute declaration
	# multi-value (an arbitrary number of these is allowed), optional
	# lets you count the words at indexing time
	#
	# sql_attr_str2wordcount	= stitle


	# combined field plus attribute declaration (from a single column)
	# stores column as an attribute, but also indexes it as a full-text field
	#
	# sql_field_string	= author
	# sql_field_str2wordcount	= title


	# 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

	# kill-list query, fetches the document IDs for kill-list
	# k-list will suppress matches from preceding indexes in the same query
	# optional, default is empty
	#
	# sql_query_killlist	= SELECT id FROM documents WHERE edited>=@last_reindex


	# columns to unpack on indexer side when indexing
	# multi-value, optional, default is empty list
	#
	# unpack_zlib		= zlib_column
	# unpack_mysqlcompress	= compressed_column
	# unpack_mysqlcompress	= compressed_column_2


	# maximum unpacked length allowed in MySQL COMPRESS() unpacker
	# optional, default is 16M
	#
	# unpack_mysqlcompress_maxsize	= 16M
}

source posts
{
	# data source type. mandatory, no default value
	# known types are mysql, pgsql, mssql, xmlpipe, xmlpipe2, odbc
	type			= mysql

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

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


	# 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

	sql_query		= \
		SELECT post_id+10*2 as source_id, post_id as item_id, post_type_id as type_id, post_title, post_content, UNIX_TIMESTAMP(post_timestamp) as post_date \
		FROM cl_posts \
		WHERE post_deleted IS NULL


	# joined/payload field fetch query
	# joined fields let you avoid (slow) JOIN and GROUP_CONCAT
	# payload fields let you attach custom per-keyword values (eg. for ranking)
	#
	# syntax is FIELD-NAME 'from'  ( 'query' | 'payload-query' ); QUERY
	# joined field QUERY should return 2 columns (docid, text)
	# payload field QUERY should return 3 columns (docid, keyword, weight)
	#
	# REQUIRES that query results are in ascending document ID order!
	# multi-value, optional, default is empty list of queries
	#
	# sql_joined_field	= tags from query; SELECT docid, CONCAT('tag',tagid) FROM tags ORDER BY docid ASC
	# sql_joined_field	= wtags from payload-query; SELECT docid, tag, tagweight FROM tags ORDER BY docid ASC



	# 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		= item_id
	sql_attr_uint		= type_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


	# bigint attribute declaration
	# multi-value (an arbitrary number of attributes is allowed), optional
	# declares a signed (unlike uint!) 64-bit attribute
	#
	# sql_attr_bigint		= my_bigint_id


	# 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	= post_date

	# 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 docid, tagid FROM tags
	# sql_attr_multi		= uint tag from ranged-query; \
	#	SELECT docid, tagid FROM tags WHERE id>=$start AND id<=$end; \
	#	SELECT MIN(docid), MAX(docid) FROM tags
	sql_attr_multi		= uint categories from query; SELECT post_id, category_id FROM cl_post_categories


	# string attribute declaration
	# multi-value (an arbitrary number of these is allowed), optional
	# lets you store and retrieve strings
	#
	# sql_attr_string		= stitle


	# wordcount attribute declaration
	# multi-value (an arbitrary number of these is allowed), optional
	# lets you count the words at indexing time
	#
	# sql_attr_str2wordcount	= stitle


	# combined field plus attribute declaration (from a single column)
	# stores column as an attribute, but also indexes it as a full-text field
	#
	# sql_field_string	= author
	# sql_field_str2wordcount	= title


	# 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
}


#############################################################################
## index definitions
#############################################################################

# 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 userindex
{
	# index type
	# optional, default is 'plain'
	# known values are 'plain', 'distributed', and 'rt' (see samples below)
	# type			= plain

	# document source(s) to index
	# multi-value, mandatory
	# document IDs must be globally unique across all sources
	source			= users

	# index files path and file name, without extension
	# mandatory, path must be writable, extensions will be auto-appended
	path			= /var/lib/sphinxsearch/data/userindex

	# 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

	# minimum word length at which to enable stemming
	# optional, default is 1 (stem everything)
	#
	# min_stemming_len	= 1


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


	# wordforms file, in "mapfrom > mapto" plain text format
	# optional, default is empty
	#
	# wordforms		= /var/lib/sphinxsearch/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		= /var/lib/sphinxsearch/data/exceptions.txt


	# minimum indexed word length
	# default is 1 (index everything)
	min_word_len		= 3

	# 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		= 3


	# minimum word infix length to index
	# optional, default is 0 (do not index infixes)
	#
	min_infix_len		= 3


	# 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
	# search-time only, does not affect indexing, can be 0 or 1
	# optional, default is 0 (do not use wildcard syntax)
	#
	enable_star		= 1


	# expand keywords with exact forms and/or stars when searching fit indexes
	# search-time only, does not affect indexing, can be 0 or 1
	# optional, default is 0 (do not expand keywords)
	#
	# expand_keywords		= 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


	# blended characters list
	# blended chars are indexed both as separators and valid characters
	# for instance, AT&T will results in 3 tokens ("at", "t", and "at&t")
	# optional, default is empty
	#
	# blend_chars		= +, &, U+23


	# blended token indexing mode
	# a comma separated list of blended token indexing variants
	# known variants are trim_none, trim_head, trim_tail, trim_both, skip_pure
	# optional, default is trim_none
	#
	# blend_mode		= trim_tail, skip_pure


	# 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), searchd-only
	#
	# preopen			= 1


	# whether to keep dictionary (.spi) on disk, or cache it in RAM
	# optional, default is 0 (cache in RAM), searchd-only
	#
	# ondisk_dict		= 1


	# whether to enable in-place inversion (2x less disk, 90-95% speed)
	# optional, default is 0 (use separate temporary files), indexer-only
	#
	# inplace_enable		= 1


	# in-place fine-tuning options
	# optional, defaults are listed below
	#
	# inplace_hit_gap		= 0 # preallocated hitlist gap size
	# inplace_docinfo_gap	= 0 # preallocated docinfo gap size
	# inplace_reloc_factor	= 0.1 # relocation buffer size within arena
	# inplace_write_factor	= 0.1 # write buffer size within arena


	# whether to index original keywords along with stemmed versions
	# enables "=exactform" operator to work
	# optional, default is 0
	#
	# index_exact_words	= 1


	# position increment on overshort (less that min_word_len) words
	# optional, allowed values are 0 and 1, default is 1
	#
	# overshort_step		= 1


	# position increment on stopword
	# optional, allowed values are 0 and 1, default is 1
	#
	# stopword_step		= 1


	# hitless words list
	# positions for these keywords will not be stored in the index
	# optional, allowed values are 'all', or a list file name
	#
	# hitless_words		= all
	# hitless_words		= hitless.txt


	# detect and index sentence and paragraph boundaries
	# required for the SENTENCE and PARAGRAPH operators to work
	# optional, allowed values are 0 and 1, default is 0
	#
	# index_sp			= 1


	# index zones, delimited by HTML/XML tags
	# a comma separated list of tags and wildcards
	# required for the ZONE operator to work
	# optional, default is empty string (do not index zones)
	#
	# index_zones		= title, h*, th
}

index postindex
{
	# index type
	# optional, default is 'plain'
	# known values are 'plain', 'distributed', and 'rt' (see samples below)
	# type			= plain

	# document source(s) to index
	# multi-value, mandatory
	# document IDs must be globally unique across all sources
	source			= posts

	# index files path and file name, without extension
	# mandatory, path must be writable, extensions will be auto-appended
	path			= /var/lib/sphinxsearch/data/postindex

	# 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

	# minimum word length at which to enable stemming
	# optional, default is 1 (stem everything)
	#
	# min_stemming_len	= 1


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


	# wordforms file, in "mapfrom > mapto" plain text format
	# optional, default is empty
	#
	# wordforms		= /var/lib/sphinxsearch/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		= /var/lib/sphinxsearch/data/exceptions.txt


	# minimum indexed word length
	# default is 1 (index everything)
	min_word_len		= 3

	# 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		= 3


	# minimum word infix length to index
	# optional, default is 0 (do not index infixes)
	#
	# min_infix_len		= 3


	# 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
	# search-time only, does not affect indexing, can be 0 or 1
	# optional, default is 0 (do not use wildcard syntax)
	#
	# enable_star		= 1


	# expand keywords with exact forms and/or stars when searching fit indexes
	# search-time only, does not affect indexing, can be 0 or 1
	# optional, default is 0 (do not expand keywords)
	#
	# expand_keywords		= 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


	# blended characters list
	# blended chars are indexed both as separators and valid characters
	# for instance, AT&T will results in 3 tokens ("at", "t", and "at&t")
	# optional, default is empty
	#
	# blend_chars		= +, &, U+23


	# blended token indexing mode
	# a comma separated list of blended token indexing variants
	# known variants are trim_none, trim_head, trim_tail, trim_both, skip_pure
	# optional, default is trim_none
	#
	# blend_mode		= trim_tail, skip_pure


	# 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), searchd-only
	#
	# preopen			= 1


	# whether to keep dictionary (.spi) on disk, or cache it in RAM
	# optional, default is 0 (cache in RAM), searchd-only
	#
	# ondisk_dict		= 1


	# whether to enable in-place inversion (2x less disk, 90-95% speed)
	# optional, default is 0 (use separate temporary files), indexer-only
	#
	# inplace_enable		= 1


	# in-place fine-tuning options
	# optional, defaults are listed below
	#
	# inplace_hit_gap		= 0 # preallocated hitlist gap size
	# inplace_docinfo_gap	= 0 # preallocated docinfo gap size
	# inplace_reloc_factor	= 0.1 # relocation buffer size within arena
	# inplace_write_factor	= 0.1 # write buffer size within arena


	# whether to index original keywords along with stemmed versions
	# enables "=exactform" operator to work
	# optional, default is 0
	#
	# index_exact_words	= 1


	# position increment on overshort (less that min_word_len) words
	# optional, allowed values are 0 and 1, default is 1
	#
	# overshort_step		= 1


	# position increment on stopword
	# optional, allowed values are 0 and 1, default is 1
	#
	# stopword_step		= 1


	# hitless words list
	# positions for these keywords will not be stored in the index
	# optional, allowed values are 'all', or a list file name
	#
	# hitless_words		= all
	# hitless_words		= hitless.txt


	# detect and index sentence and paragraph boundaries
	# required for the SENTENCE and PARAGRAPH operators to work
	# optional, allowed values are 0 and 1, default is 0
	#
	# index_sp			= 1


	# index zones, delimited by HTML/XML tags
	# a comma separated list of tags and wildcards
	# required for the ZONE operator to work
	# optional, default is empty string (do not index zones)
	#
	# index_zones		= title, h*, th
}

#############################################################################
## 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)
	# 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


	# maximum xmlpipe2 field length, bytes
	# optional, default is 2M
	#
	# max_xmlpipe2_field	= 4M


	# write buffer size, bytes
	# several (currently up to 4) buffers will be allocated
	# write buffers are allocated in addition to mem_limit
	# optional, default is 1M
	#
	# write_buffer		= 1M


	# maximum file field adaptive buffer size
	# optional, default is 8M, minimum is 1M
	#
	# max_file_field_buffer	= 32M
}

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

searchd
{
	# [hostname:]port[:protocol], or /unix/socket/path to listen on
	# known protocols are 'sphinx' (SphinxAPI) and 'mysql41' (SphinxQL)
	#
	# multi-value, multiple listen points are allowed
	# optional, defaults are 9312:sphinx and 9306:mysql41, as below
	#
	# listen			= 127.0.0.1
	# listen			= 192.168.0.1:9312
	# listen			= 9312
	# listen			= /var/run/searchd.sock
	listen			= 9312
	listen			= 9306:mysql41

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

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

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

	# request timeout, seconds
	# optional, default is 5 minutes
	client_timeout		= 300

	# maximum amount of children to fork (concurrent searches to run)
	# optional, default is 0 (unlimited)
	max_children		= 70

	# PID file, searchd process ID file name
	# mandatory
	pid_file		= /var/run/sphinxsearch/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 1 (preopen everything)
	preopen_indexes		= 1

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

	# attribute updates periodic flush timeout, seconds
	# updates will be automatically dumped to disk this frequently
	# optional, default is 0 (disable periodic flush)
	#
	# attr_flush_period	= 900


	# instance-wide ondisk_dict defaults (per-index value take precedence)
	# optional, default is 0 (precache all dictionaries in RAM)
	#
	# ondisk_dict_default	= 1


	# MVA updates pool size
	# shared between all instances of searchd, disables attr flushes!
	# optional, default size is 1M
	mva_updates_pool	= 5M

	# max allowed network packet size
	# limits both query packets from clients, and responses from agents
	# optional, default size is 8M
	max_packet_size		= 8M

	# crash log path
	# searchd will (try to) log crashed query to 'crash_log_path.PID' file
	# optional, default is empty (do not create crash logs)
	#
	# crash_log_path		= /var/log/sphinxsearch/crash


	# max allowed per-query filter count
	# optional, default is 256
	max_filters		= 256

	# max allowed per-filter values count
	# optional, default is 4096
	max_filter_values	= 4096


	# socket listen queue length
	# optional, default is 5
	#
	# listen_backlog		= 5


	# per-keyword read buffer size
	# optional, default is 256K
	#
	# read_buffer		= 256K


	# unhinted read size (currently used when reading hits)
	# optional, default is 32K
	#
	# read_unhinted		= 32K


	# max allowed per-batch query count (aka multi-query count)
	# optional, default is 32
	max_batch_queries	= 32


	# max common subtree document cache size, per-query
	# optional, default is 0 (disable subtree optimization)
	#
	# subtree_docs_cache	= 4M


	# max common subtree hit cache size, per-query
	# optional, default is 0 (disable subtree optimization)
	#
	# subtree_hits_cache	= 8M


	# multi-processing mode (MPM)
	# known values are none, fork, prefork, and threads
	# optional, default is fork
	#
	workers			= threads # for RT to work


	# max threads to create for searching local parts of a distributed index
	# optional, default is 0, which means disable multi-threaded searching
	# should work with all MPMs (ie. does NOT require workers=threads)
	#
	# dist_threads		= 4


	# binlog files path; use empty string to disable binlog
	# optional, default is build-time configured data directory
	#
	# binlog_path		= # disable logging
	# binlog_path		= /var/lib/sphinxsearch/data # binlog.001 etc will be created there


	# binlog flush/sync mode
	# 0 means flush and sync every second
	# 1 means flush and sync every transaction
	# 2 means flush every transaction, sync every second
	# optional, default is 2
	#
	# binlog_flush		= 2


	# binlog per-file size limit
	# optional, default is 128M, 0 means no limit
	#
	# binlog_max_log_size	= 256M


	# per-thread stack size, only affects workers=threads mode
	# optional, default is 64K
	#
	# thread_stack			= 128K


	# per-keyword expansion limit (for dict=keywords prefix searches)
	# optional, default is 0 (no limit)
	#
	# expansion_limit		= 1000


	# RT RAM chunks flush period
	# optional, default is 0 (no periodic flush)
	#
	# rt_flush_period		= 900


	# query log file format
	# optional, known values are plain and sphinxql, default is plain
	#
	# query_log_format		= sphinxql


	# version string returned to MySQL network protocol clients
	# optional, default is empty (use Sphinx version)
	#
	# mysql_version_string	= 5.0.37


	# trusted plugin directory
	# optional, default is empty (disable UDFs)
	#
	# plugin_dir			= /usr/local/sphinx/lib


	# default server-wide collation
	# optional, default is libc_ci
	#
	# collation_server		= utf8_general_ci


	# server-wide locale for libc based collations
	# optional, default is C
	#
	# collation_libc_locale	= ru_RU.UTF-8


	# threaded server watchdog (only used in workers=threads mode)
	# optional, values are 0 and 1, default is 1 (watchdog on)
	#
	# watchdog				= 1


	# SphinxQL compatibility mode (legacy columns and their names)
	# optional, default is 0 (SQL compliant syntax and result sets)
	#
	# compat_sphinxql_magics	= 1
}

sphinx.md

#Sphinx

This is Ubuntu and PHP-oriented

$ apt-get install sphinxsearch #Install the search index

# The PHP binaries aren't automagically installed, and we need to take care of
# some BS to get them tot work (need libsphinxclient available to us)
Download tar: sudo pear install pecl/sphinx, untar is (tar -xvf)
cd 'dir'/api/libsphinxclient

$ ./configure
$ make
$ sudo make install
$ sudo pecl install sphinx
$ echo "extension=sphinx.so" >> /etc/php5/conf.d/sphinx.ini
$ sudo service apache2 restart

# SET TONS OF OPTIONS, note: enable_start, min_prefix_len, min_infix_len

$ indexer --config /etc/sphinx/sphinx.conf --all --rotate #Rotate if searchd is running
$ searchd --config /etc/sphinx/sphinx.conf
$ search --config /etc/sphinx/sphinx.conf "term"

##Searchd options --stop --stopwait (use this one)

Note: Consider using default config /etc/sphinxsearch/sphinx.conf (Does ubuntu start searchd on startup? User issue?)

##GOTCHAS:

1. If you search multiple indexes, those index need to have identical attribute names
2. Items across multiple indexes all need unique ID's. Think primary keys in SQL, except every row across every table needs a unique Primary Key, instead of simply each row per table. This accounts for the document id having +10*1 and +10*2 per index - To ensure unique IDs across indeces.

sphinx.php

<?php

class Sphinx {

	private $_sphinx;
	private $_config;

	private $_ready = FALSE;

	const SPHINX_INDEX_USERS = 'user_index';
	const SPHINX_INDEX_POSTS = 'post_index';
	const SPHINX_INDEX_ALL = '*'; //all indeces

	const SPHINX_STAR_LEFT  = 1;
	const SPHINX_STAR_RIGHT = 2;
	const SPHINX_STAR_BOTH  = 3;

	//Results
	private $_index;
	private $_raw_results;
	private $_results;

	public function __construct() {

		parent::__construct();

		if( class_exists('SphinxClient') !== FALSE ) {

			//Sphinx configuration
			$this->_config = array(
				'host' => 'localhost',
				'port' => 9312,
				'max_results' => 100
			);

			/*
			* PHP Sphinx - PECL package
			* @link 	http://pecl.php.net/package/sphinx
			* @link 	https://gist.github.com/3824335
			* @link 	http://us3.php.net/sphinx
			*/
			$this->_sphinx = new SphinxClient();

			$this->_sphinx->setServer($this->_config['host'], $this->_config['port']);

			$this->_sphinx->setMatchMode(SPH_MATCH_ANY);
			$this->_sphinx->setMaxQueryTime(3);

			$this->_status = $this->_sphinx->status();

		}

	}

	/**
	* Search sphinx indeces
	*
	* @param string 	 The search query
	* @param string 	 The index to search. Use constants
	* @param string 	 Wild cards - '*$query' vs '$query*' vs '*$query*' - Similar to LIKE search in mysql. Use constants.
	* @param int 		 Limit of results. Max of max_results config
	* @param int 		 Offset, for pagination in conjunction with limit
	* @return array|bool Array of results, or FALSE
	*/
	public function search($query, $index='*', $star=FALSE, $limit=20, $offset=0, $filters=FALSE) {

		if( $this->isReady() === FALSE ) {

			return FALSE;

		}

		/*
		* Pagination, with required max_results from config
		* @link 	http://stage2.sphinxsearch.com/docs/2.0.4/api-func-setlimits.html
		* @link 	http://us2.php.net/manual/en/sphinxclient.setlimits.php
		*/
		$this->_sphinx->setLimits($offset, $limit, $this->_config['max_results']);

		/*
		* Filters 	(Note that $filter[values] should be an array)
		* @link 	http://sphinxsearch.com/docs/2.0.4/api-func-setfilter.html
		* @link 	http://us2.php.net/manual/en/sphinxclient.setfilter.php
		*/
		if( is_array($filters) ) {

			foreach( $filters as $filter ) {

				$exclude = isset($filter['exclude']) ? $filter['exclude'] : FALSE;

				$this->_sphinx->setFilter($filter['attribute'], $filter['values'], $exclude);

			}

		}

		//$this->_sphinx->SetSelect("post_id, post_type_id, user_identity_id");

		//Ensure proper index used
		switch( $index ) {

			case self::SPHINX_INDEX_USERS :
				$this->_index = self::SPHINX_INDEX_USERS;
				break;

			case self::SPHINX_INDEX_POSTS :
				$this->_index = self::SPHINX_INDEX_POSTS;
				break;

			default :
				$this->_index = '*';
				break;

		}

		//Add star to search as appropriate
		switch( $star ) {

			case self::SPHINX_STAR_LEFT :
				$query = '*'.$query;
				break;

			case self::SPHINX_STAR_RIGHT :
				$query = $query.'*';
				break;

			case self::SPHINX_STAR_BOTH :
				$query = '*'.$query.'*';
				break;

		}

		$this->_results = FALSE; //fallback
		$this->_raw_results = $this->_sphinx->query($query, $this->_index);

		if( $this->_raw_results ) {

			//Make a more sensible (for our data) return array
			$this->_results = $this->processResults($this->_raw_results);

		}

		return $this->_results;

	}

	/**
	* Create a more sensible return object
	*
	* @param array 	Results array from SphinxClient::query() call
	* @return array Result attr items for each result (aka the data we care about)
	*/
	public function processResults($results) {

		if( $results['error'] != '' || isset($results['matches']) !== TRUE ) {
			return FALSE;
		}

		$processed = array();

		//Only grab the important data
		foreach( $results['matches'] as $match ) {

			$processed[] = $match['attrs'];

		}

		return $processed;

	}

	/**
	* Test if Sphinx is connected
	*
	* @return bool If Sphinx status is OK
	*/
	public function isReady() {

		if( $this->_status === FALSE ) {

			return FALSE;

		} else {

			return TRUE;

		}

	}


}