sphinx_new_config

#
# Minimal Sphinx configuration for Bitrix
#

index bitrix
{
    #main settings
        type = rt
        path = /var/lib/sphinxsearch/data/bitrix
        docinfo = inline
	#ondisc_attrs=1
    #choose appropriate type of morphology to use
        #morphology = lemmatize_ru_all, lemmatize_en_all, lemmatize_de_all, stem_enru
        morphology = stem_enru, soundex
    #these settings are used by bitrix:search.title component
        dict = keywords
        prefix_fields = title
        infix_fields=
        min_prefix_len = 2
        enable_star = 1
    #all fields must be defined exactly as followed
        rt_field = title
        rt_field = body
        rt_attr_uint = module_id
        rt_attr_string = module
        rt_attr_uint = item_id
        rt_attr_string = item
        rt_attr_uint = param1_id
        rt_attr_string = param1
        rt_attr_uint = param2_id
        rt_attr_string = param2
        rt_attr_timestamp = date_change
        rt_attr_timestamp = date_to
        rt_attr_timestamp = date_from
        rt_attr_uint = custom_rank
        rt_attr_multi = tags
        rt_attr_multi = right
        rt_attr_multi = site
        rt_attr_multi = param
    #depends on settings of your site
        # uncomment for single byte character set
        charset_type = sbcs
        # uncomment for UTF character set
        #charset_type = utf-8
}

source bitrix2
{
	type                    = mysql
	sql_host                = localhost
	sql_user                = avselectro
	sql_pass                = MDJlNjBjZT
	sql_db                  = avselectro
	sql_port                = 3306

	sql_query_pre           = SET NAMES utf8
#        sql_query_pre           = SET group_concat_max_len = 4096
#        sql_query_pre           = TRUNCATE TABLE `tmp_features`
#        sql_query_pre           = \
#		INSERT INTO `tmp_features` (`raec_id`, `features`)\
#		SELECT `PRODUCTID`,\
#			CONCAT('{', GROUP_CONCAT(CONCAT('"', `product_values`.`FEATUREID`, '":', `product_values`.`VAL`, '')), '}') AS `features`\
#		FROM (\
#			SELECT `PRODUCTID`, `FEATUREID`, CONCAT('[', GROUP_CONCAT(CONCAT('"', IFNULL(`VALUE`, `IBLOCK_ELEMENT_ID`), '"')), ']') AS `VAL`\
#			FROM `tmp_product_feature_value_map`\
#			GROUP BY `PRODUCTID`, `FEATUREID`\
#		) AS `product_values`\
#		GROUP BY `PRODUCTID`;

	sql_query               = \
		SELECT 	`product`.`ID` AS `id`,\
			`product`.`XML_ID` AS `xml_id`,\
			`product`.`SHOW_COUNTER` AS `rating`,\
			`brands`.`ID` AS `brand_id`,\
			`prop`.`PROPERTY_20` AS `article`,\
			`prop`.`PROPERTY_51`>0 AS `is_sale`,\
			`prop`.`PROPERTY_52`>0 AS `is_new`,\
			`prop`.`PROPERTY_67`>0 AS `is_special`,\
			`brands`.`NAME` AS `brand`,\
			`product`.`NAME` AS `title`,\
			`product`.`DETAIL_TEXT` AS `text`,\
			`store`.`AMOUNT`>0 AS `remains`,\
			`price`.`PRICE` AS `price`,\
			`etimclasses`.`CODE` AS `etimclass_id`,\
			`tmp_features`.`features` AS `features`,\
			`tmp_features`.`values` AS `values`\
		FROM `b_iblock_element` AS `product`\
		LEFT JOIN `b_catalog_store_product` AS `store` ON `store`.`STORE_ID` = 32 AND `store`.`PRODUCT_ID` = `product`.`ID`\
		LEFT JOIN `b_catalog_price` AS `price` ON `price`.`CATALOG_GROUP_ID` = 6 AND `price`.`PRODUCT_ID` = `product`.`ID`\
		LEFT JOIN `b_iblock_element_prop_s6` AS `prop` ON `prop`.`IBLOCK_ELEMENT_ID` = `product`.`ID`\
		LEFT JOIN `b_iblock_element` AS `etimclasses` ON `etimclasses`.`IBLOCK_ID` = 4 AND `etimclasses`.`ACTIVE` = 'Y' AND `prop`.`PROPERTY_17` = `etimclasses`.`ID`\
		LEFT JOIN `b_iblock_element` AS `brands` ON `brands`.`IBLOCK_ID` = 7 AND `brands`.`ACTIVE` = 'Y' AND `prop`.`PROPERTY_19` = `brands`.`ID`\
		LEFT JOIN `tmp_features` ON `tmp_features`.`raec_id` = `prop`.`PROPERTY_27`\
		WHERE `product`.`IBLOCK_ID` = 6;

	sql_attr_multi		= uint section_id from query; SELECT `IBLOCK_ELEMENT_ID` AS `id`, `IBLOCK_SECTION_ID` AS `section_id` FROM `b_iblock_section_element`
	sql_attr_uint		= brand_id
	sql_attr_uint		= xml_id
	sql_attr_uint		= rating
	sql_attr_bool		= is_sale
	sql_attr_bool		= is_new
	sql_attr_bool		= is_special
	sql_attr_bool		= remains
	sql_attr_float		= price
	sql_attr_string		= etimclass_id
	sql_attr_string		= title
	sql_attr_json		= features
}

index bitrix2
{
        type                    = plain
        source                  = bitrix2
        path                    = /var/www/sphinx/data/bitrix2
        mlock                   = 0
        morphology              = stem_en, stem_ru, soundex
        min_word_len            = 2
        html_strip              = 1
        preopen                 = 1
}

source catalog
{
        # Параметры подключения к БД
        type = mysql
        sql_host = localhost
        sql_user = avselectro
        sql_pass = MDJlNjBjZT
        sql_db = avselectro
        sql_port = 3306

        # Установим кодировку для работы с БД
        sql_query_pre = SET NAMES utf8
        sql_query_pre = SET CHARACTER SET utf8

        # Запрос выборки данных для индексации
        #sql_query = SELECT ID as post_id, post_title, post_content FROM wp_posts WHERE post_type = 'post'
        #sql_query = SELECT IBLOCK_ELEMENT_ID, PROPERTY_35 FROM b_iblock_element_prop_s6
        sql_query = SELECT ID, NAME, PROPERTY_35, PROPERTY_81 FROM b_iblock_element LEFT OUTER JOIN b_iblock_element_prop_s6 ON ID = IBLOCK_ELEMENT_ID WHERE IBLOCK_ID=6

        #sql_query = SELECT ID, NAME FROM b_iblock_element

        # Запрос доп. информации для вывода результата (используется утилитой "search")
        #sql_query_info = SELECT * FROM b_iblock_elemnt_prop_s6 WHERE IBLOCK_ELEMENT_ID = $id

        # Время простоя (sleep) перед посылкой запросов серверу (предназначен для разгрузки сервера БД)
        # Если установите "= 1000", то засыпание будет длится 1 секунду
        sql_ranged_throttle = 0
}

index catalog
{
        # Использовать соответствующий source-блок настроек при индексации
        source = catalog

        # Путь до файлов индекса
        path = /var/www/sphinx/data/catalog

        # Использование английского и русского стемминга
        morphology = stem_enru

        # Минимальная длина индексируемого слова
        min_word_len = 2

        # Установка используемой кодировки
        #charset_type = utf-8
}

source ETIM_catalog
{
        # Параметры подключения к БД
        type = mysql
        sql_host = localhost
        sql_user = avselectro
        sql_pass = MDJlNjBjZT
        sql_db = avselectro
        sql_port = 3306

        # Установим кодировку для работы с БД
        sql_query_pre = SET NAMES utf8
        sql_query_pre = SET CHARACTER SET utf8

        # Запрос выборки данных для индексации
        # sql_query = SELECT b_iblock_element.ID, b_iblock_element.NAME, b_iblock_element.CODE,b_iblock_element_prop_s4.PROPERTY_6,    b_iblock_element_prop_m4.VALUE FROM b_iblock_element LEFT OUTER JOIN b_iblock_element_prop_s4 ON b_iblock_element.ID = b_iblock_element_prop_s4.IBLOCK_ELEMENT_ID LEFT OUTER JOIN b_iblock_element_prop_m4 ON b_iblock_element.ID = b_iblock_element_prop_m4.IBLOCK_ELEMENT_ID WHERE IBLOCK_ID=4

        sql_query = SELECT b_iblock_element_prop_s6.IBLOCK_ELEMENT_ID, b_iblock_element.NAME, b_iblock_element.CODE, b_iblock_element_prop_s4.PROPERTY_6, b_iblock_element_prop_m4.VALUE FROM b_iblock_element LEFT OUTER JOIN b_iblock_element_prop_s4 ON b_iblock_element.ID = b_iblock_element_prop_s4.IBLOCK_ELEMENT_ID LEFT OUTER JOIN b_iblock_element_prop_m4 ON b_iblock_element.ID = b_iblock_element_prop_m4.IBLOCK_ELEMENT_ID LEFT OUTER JOIN b_iblock_element_prop_s6 ON b_iblock_element.ID = b_iblock_element_prop_s6.PROPERTY_17 WHERE IBLOCK_ID=4


        # Время простоя (sleep) перед посылкой запросов серверу (предназначен для разгрузки сервера БД)
        # Если установите "= 1000", то засыпание будет длится 1 секунду
        sql_ranged_throttle = 0
}

index ETIM_catalog
{
        # Использовать соответствующий source-блок настроек при индексации
        source = ETIM_catalog

        # Путь до файлов индекса
        path = /var/www/sphinx/data/ETIM_catalog

        # Использование английского и русского стемминга
        morphology = stem_enru

        # Минимальная длина индексируемого слова
        min_word_len = 2

        # Установка используемой кодировки
        #charset_type = utf-8

        #wordforms = /var/www/sphinx/dic.txt
}

source CODE_catalog
{
        # Параметры подключения к БД
        type = mysql
        sql_host = localhost
        sql_user = avselectro
        sql_pass = MDJlNjBjZT
        sql_db = avselectro
        sql_port = 3306

        # Установим кодировку для работы с БД
        sql_query_pre = SET NAMES utf8
        sql_query_pre = SET CHARACTER SET utf8

        # Запрос выборки данных для индексации
        sql_query = SELECT IBLOCK_ELEMENT_ID, PROPERTY_27, PROPERTY_20, PROPERTY_25, PROPERTY_24 FROM b_iblock_element_prop_s6

        # Время простоя (sleep) перед посылкой запросов серверу (предназначен для разгрузки сервера БД)
        # Если установите "= 1000", то засыпание будет длится 1 секунду
        sql_ranged_throttle = 0
}

index CODE_catalog
{
        # Использовать соответствующий source-блок настроек при индексации
        source = CODE_catalog

        # Путь до файлов индекса
        path = /var/www/sphinx/data/CODE_catalog

        # Использование английского и русского стемминга
        morphology = stem_enru

        # Минимальная длина индексируемого слова
        min_word_len = 2

        # Установка используемой кодировки
        #charset_type = utf-8

        #wordforms = /var/www/sphinx/dic.txt
}

#############################################################################
## 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
	    lemmatizer_cache	= 128M

}

#############################################################################
## 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:sphinx
        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            = 30

        # 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        = 1M

        # 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       = 200


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


        # max common subtree hit cache size, per-query
        # optional, default is 0 (disable subtree optimization)
        #
        subtree_hits_cache      = 16M

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


        # 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_path		= /var/lib/sphinxsearch/data/


       # 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   = 512M


        # 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               = 3600


        # 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
}

# common settings

common
{
        json_autoconv_numbers           = 1
        #json_autoconv_keynames         = lowercase
	lemmatizer_base = /etc/sphinxsearch/dicts/

}