sphinx学习（二）基本配置 data source definition

2019独角兽企业重金招聘Python工程师标准>>>

基本配置

sphinx.conf配置文件包含的部分有三种主要类型：

1. data source definition

source src1
{
	# 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		= 120.25.223.132
	sql_user		= wb
	sql_pass		= weibao2014
	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

	# MySQL specific SSL certificate settings
	# optional, defaults are empty
	#
	# mysql_ssl_cert		= /etc/ssl/client-cert.pem
	# mysql_ssl_key		= /etc/ssl/client-key.pem
	# mysql_ssl_ca		= /etc/ssl/cacert.pem

	# MS SQL specific Windows authentication mode flag
	# MUST be in sync with charset_type index-level setting
	# optional, default is 0
	#
	# mssql_winauth		= 1 # use currently logged on user credentials


	# ODBC specific DSN (data source name)
	# mandatory for odbc source type, no default value
	#
	# odbc_dsn		= DBQ=C:\data;DefaultDir=C:\data;Driver={Microsoft Text Driver (*.txt; *.csv)};
	# sql_query		= SELECT id, data FROM documents.csv


	# ODBC and MS SQL specific, per-column buffer sizes
	# optional, default is auto-detect
	#
	# sql_column_buffers	= content=12M, comments=1M


	# 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


	# 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


	# file based field declaration
	#
	# content of this field is treated as a file name
	# and the file gets loaded and indexed in place of a field
	#
	# max file size is limited by max_file_field_buffer indexer setting
	# file IO errors are non-fatal and get reported as warnings
	#
	# sql_file_field		= content_file_path


	# 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


	# 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


	# 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


	# JSON attribute declaration
	# multi-value (an arbitrary number of these is allowed), optional
	# lets you store a JSON document as an (in-memory) attribute for later use
	#
	# sql_attr_json		= properties


	# 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

	
	# 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


	# 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


	# hook command to run when SQL connection succeeds
	# optional, default value is empty (do nothing)
	#
	# hook_connect			= bash sql_connect.sh


	# hook command to run after (any) SQL range query
	# it may print out "minid maxid" (w/o quotes) to override the range
	# optional, default value is empty (do nothing)
	#
	# hook_query_range		= bash sql_query_range.sh


	# hook command to run on successful indexing completion
	# $maxid expands to max document ID actually fetched from DB
	# optional, default value is empty (do nothing)
	#
	# hook_post_index		= bash sql_post_index.sh $maxid

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

	# type			= xmlpipe

	# shell command to invoke xmlpipe stream producer
	# mandatory
	#
	# xmlpipe_command		= cat /usr/local/sphinx/var/test.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
	# examples:
	#
	# xmlpipe_attr_timestamp	= published
	# xmlpipe_attr_uint	= author_id
	# xmlpipe_attr_bool	= is_enabled
	# xmlpipe_attr_float	= latitude
	# xmlpipe_attr_bigint	= guid
	# xmlpipe_attr_multi	= tags
	# xmlpipe_attr_multi_64	= tags64
	# xmlpipe_attr_string	= title
	# xmlpipe_attr_json	= extra_data
	# xmlpipe_field_string	= content


	# perform UTF-8 validation, and filter out incorrect codes
	# avoids XML parser choking on non-UTF-8 documents
	# optional, default is 0
	#
	# xmlpipe_fixup_utf8	= 1
}

 

 

sql_host

 

转载于:https://my.oschina.net/yunjie/blog/774819