csft.conf 配置为
#
# 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', 'mssql', 'xmlpipe', 'xmlpipe2'
type = mysql
#####################################################################
## SQL settings (for 'mysql' and 'pgsql' types)
#####################################################################
# some straightforward parameters for SQL source types
sql_host = localhost
sql_user = root
sql_pass = 123456
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
# 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
# MS SQL specific Unicode indexing flag
# optional, default is 0 (request SBCS data)
#
# mssql_unicode = 1 # request Unicode data from server
# 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
# 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 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
# 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
#####################################################################
## 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 = D:/csft/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
# 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 = @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 = zh_cn.utf-8
charset_dictpath = D:\csft3.1\bin\uni.lib
# 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 i |
