indexer.conf

完美的在线教育系统

#!/usr/sbin/indexer -d

###########################################################################
# This is a sample indexer config file.
# To start using it please edit and rename to indexer.conf.
# You can also make this file executable and run it directly.
# You may want to keep the original indexer.conf-dist for future references.
# Use '#' to comment out lines.
# All command names are case insensitive (DBAddr=DBADDR=dbaddr).
# You may use '\' character to prolong current command to next line
# when it is required.
#
# You may include another configuration file in any place of the indexer.conf
# using "Include <filename>" command.
# Absolute path if <filename> starts with "/":
#Include /etc/mnogosearch/inc1.conf
# Relative path else:
#Include inc1.conf
###########################################################################



###########################################################################
#  Section 1.
#  Global parameters.


###########################################################################
# DBAddr <URL-style database description>
# Options (type, host, database name, port, user and password) 
# to connect to SQL database.
# Should be used before any other commands.
# Has global effect for whole config file.
# Format:
#DBAddr <DBType>:[//[DBUser[:DBPass]@]DBHost[:DBPort]]/DBName/[?dbmode=mode]
#
# ODBC notes:
#	Use DBName to specify ODBC data source name (DSN)
#	DBHost does not matter, use "localhost".
#
# Currently supported DBType values are 
# mysql, pgsql, mssql, oracle, ibase, db2, mimer, sqlite.
# 
# MySQL users can specify path to Unix socket when connecting to localhost:
# mysql://foo:bar@localhost/mnogosearch/?socket=/tmp/mysql.sock
#
# If you are using PostgreSQL and do not specify hostname,
#	e.g. pgsql://user:password@/dbname/
# then PostgreSQL will not work via TCP, but will use Unix socket.
#
# You may also select database mode of word storage.
# When "single" is specified, all words are stored in the same table.
# If "multi" is selected, words will be located in different tables.
# "multi" mode is usually faster but requires more tables.
# Default mode is "single".

DBAddr  mysql://db_user:db_password@db_host/db_name/?dbmode=single

######################################################################
# VarDir /var/lib/mnogosearch
# You may choose alternative working directory for 
# search results cache:
#
#VarDir /var/lib/mnogosearch



######################################################################
# NewsExtensions yes/no
# Whether to enable news extensions.
# Default value is no.
#NewsExtensions no


#######################################################################
#SyslogFacility <facility>
# This is used if indexer was compiled with syslog support and if you
# don't like the default value. Argument is the same as used in syslog.conf
# file. For list of possible facilities see syslog.conf(5)
#SyslogFacility local7


#######################################################################
# LocalCharset <charset>
# Defines the charset which will be used to store data in the database.
# All other character sets will be converted into the given charset.
# Take a look into mnoGoSearch documentation for detailed explanation 
# how to choose a LocalCharset depending on languages used on your site(s).
# This command should be used once and takes global effect for the config file.
# Only most popular charsets used in Internet are written here.
# Take a look into the documentation to check the whole list of
# supported charsets.
# Default LocalCharset is iso-8859-1 (latin1).
#
# Western Europe: German, Finnish, French, Swedish
LocalCharset iso-8859-1
#LocalCharset windows-1252

# Central Europe: Czech, Slovenian, Slovak, Hungarian, Polish
#LocalCharset iso-8859-2
#LocalCharset windows-1250

# Baltic: Lithuanian, Estonian, Latvian
#LocalCharset iso-8859-4
#LocalCharset iso-8859-13
#LocalCharset windows-1257

# Cyrillic: Russian, Serbian, Ukrainian, Belarussian, Macedonian, Bulgarian
#LocalCharset koi8-r
#LocalCharset iso-8859-5
#LocalCharset x-mac-cyrillic
#LocalCharset windows-1251

# Arabic
#LocalCharset iso-8859-6
#LocalCharset windows-1256

# Greek
#LocalCharset iso-8859-7
#LocalCharset windows-1253

# Hebrew
#LocalCharset iso-8859-8
#LocalCharset windows-1255

# Turkish
#LocalCharset iso-8859-9
#LocalCharset windows-1254

# Vietnamese
#LocalCharset viscii
#LocalCharset windows-1258

# Chinese
#LocalCharset gb2312
#LocalCharset BIG5

# Korean
#LocalCharset EUC-KR

# Japanese
#LocalCharset Shift-JIS

# Full UNICODE
#LocalCharset UTF-8
#LocalCharset iso-8859-1
#LocalCharset windows-1252

#######################################################################
#ForceIISCharset1251 yes/no
#This option is useful for users which deals with Cyrillic content and broken
#(or misconfigured?) Microsoft IIS web servers, which tends to not report
#charset correctly. This is really dirty hack, but if this option is turned on
#it is assumed that all servers which reports as 'Microsoft' or 'IIS' have
#content in Windows-1251 charset.
#This command should be used only once in configuration file and takes global
#effect.
#Default: no
#ForceIISCharset1251 no


###########################################################################
#CrossWords yes/no
# Whether to build CrossWords index
# Default value is no
#CrossWords no
CrossWords yes


###########################################################################
# StopwordFile <filename>
# Load stop words from the given text file. You may specify either absolute 
# file name or a name relative to mnoGoSearch /etc directory. You may use
# several StopwordFile commands.
#
#StopwordFile stopwords/en.sl

Include stopwords.conf


###########################################################################
# LangMapFile <filename>
# Load language map for charset and language guesser from the given file. 
# You may specify either an absolute file name or a name relative 
# to mnoGoSearch /etc directory. You may use several LangMapFile commands.
#
#LangMapFile langmap/en.ascii.lm

Include langmap.conf


#######################################################################
# Word lengths. You may change default length range of words
# stored in the database. By default, words with the length in the
# range from 1 to 32 are stored.
#
#MinWordLength 1
#MaxWordLength 32

#######################################################################
# MaxDocSize bytes
# Default value 1048576 (1 Mb)
# Takes global effect for whole config file
MaxDocSize 10485760

#######################################################################
# URLSelectCacheSize num
# Default value 128
# Select <num> targets to index at once. 
#URLSelectCacheSize 1024

#######################################################################
# WordCacheSize bytes
# Default value 8388608 (8 Mb)
# Defines maximal in-memory words cache size.
# Note: cache is allocated for every DBAddr, so if you have 3 DBAddr
# commands and WordCacheSize is 10Mb, it can take up to 30Mb of memory.
#WordCacheSize 8388608

#######################################################################
# HTTPHeader <header>
# You may add your desired headers in indexer HTTP request.
# You should not use "If-Modified-Since","Accept-Charset" headers,
# these headers are composed by indexer itself.
# "User-Agent: mnoGoSearch/version" is sent too, but you may override it.
# Command has global effect for all configuration file.
#
#HTTPHeader "User-Agent: My_Own_Agent"
#HTTPHeader "Accept-Language: ru, en"
HTTPHeader "Accept-Language: fr, nl, en, de, es"
#HTTPHeader "From: [e-mail]"


# flush server.active to inactive for all server table records
# before loading new
#FlushServerTable

#######################################################################
# ServerTable <table_addr>
# Load servers with all their parameters from the table specified in argument.
# Check an example of tables server and srvinfo structure in
# create/(your_database)/create.txt
#
#ServerTable mysql://user:pass@host/dbname/tablename

##########################################################################
# LoadChineseList <charset> <dictionaryfilename>
# Load Chinese word frequency list. 
# By default GB2312 charset and mandarin.freq dictionary is used.
#LoadChineseList

########################################################################## 
# LoadThaiList <charset> <dictionaryfilename>
# Load Thai word frequency list
# By default tis-620 and thai.freq dictionary is used.
#LoadThaiList

##########################################################################
# Section 2.
# URL control configuration.


##########################################################################
#Allow [Match|NoMatch] [NoCase|Case] [String|Regex] <arg> [<arg> ... ]
# Use this to allow URLs that match (doesn't match) the given argument.
# First three optional parameters describe the type of comparison.
# Default values are Match, NoCase, String.
# Use "NoCase" or "Case" values to choose case insensitive or case sensitive
# comparison.
# Use "Regex" to choose regular expression comparison. 
# Use "String" to choose string with wildcards comparison.
# Wildcards are '*' for any number of characters and '?' for one character.
# Note that '?' and '*' have special meaning in "String" match type. Please use
# "Regex" to describe documents with '?' and '*' signs in URL.
# "String" match is much faster than "Regex". Use "String" where it 
# is possible.
# You may use several arguments for one 'Allow' command.
# You may use this command any times.
# Takes global effect for config file.
# Note that mnoGoSearch automatically adds one "Allow regex .*"
# command after reading config file. It means that allowed everything
# that is not disallowed.
# Examples
#  Allow everything:
#Allow *
#  Allow everything but .php .cgi .pl extensions case insensitively using regex:
#Allow NoMatch Regex \.php$|\.cgi$|\.pl$
#  Allow .HTM extension case sensitively:
#Allow Case *.HTM


##########################################################################
#Disallow [Match|NoMatch] [NoCase|Case] [String|Regex] <arg> [<arg> ... ]
# Use this to disallow URLs that match (doesn't match) given argument.
# The meaning of first three optional parameters is exactly the same 
# with "Allow" command.
# You can use several arguments for one 'Disallow' command.
# Takes global effect for config file.
#
# Examples:
# Disallow URLs that are not in udm.net domains using "string" match:
#Disallow NoMatch *.udm.net/*
# Disallow any except known extensions and directory index using "regex" match:
#Disallow NoMatch Regex \/$|\.htm$|\.html$|\.shtml$|\.phtml$|\.php$|\.txt$
# Exclude cgi-bin and non-parsed-headers using "string" match:
#Disallow */cgi-bin/* *.cgi */nph-*
# Exclude anything with '?' sign in URL. Note that '?' sign has a 
# special meaning in "string" match, so we have to use "regex" match here:
#Disallow Regex  \?

Disallow Match *whoisonline*
Disallow Match *myagenda*
Disallow Match *&rand=*
Disallow Match */chat/*
Disallow Match */auth/*
Disallow Match */online/*
Disallow Match */user/*
Disallow Match */admin/*
Disallow Match */group/*
Disallow Match *delete*
Disallow Match *del*
Disallow Match *remove*
Disallow Match *example_document.html*


# Exclude some known extensions using fast "String" match:
Disallow *.b    *.sh   *.md5  *.rpm
Disallow *.arj  *.tar  *.zip  *.tgz  *.gz   *.z     *.bz2 
Disallow *.lha  *.lzh  *.rar  *.zoo  *.ha   *.tar.Z
Disallow *.gif  *.jpg  *.jpeg *.bmp  *.tiff *.tif   *.xpm  *.xbm *.pcx
Disallow *.vdo  *.mpeg *.mpe  *.mpg  *.avi  *.movie *.mov  *.wmv
Disallow *.mid  *.mp3  *.rm   *.ram  *.wav  *.aiff  *.ra
Disallow *.vrml *.wrl  *.png  *.ico  *.psd  *.dat
Disallow *.exe  *.com  *.cab  *.dll  *.bin  *.class *.ex_
#Disallow *.xls *.doc
Disallow *.tex  *.texi *.texinfo
# Disallow *.rtf  *.pdf  *.ps *.eps
Disallow *.cdf
Disallow *.ai   *.ppt  *.hqx
Disallow *.cpt  *.bms  *.oda  *.tcl
Disallow *.o    *.a    *.la   *.so 
Disallow *.pat  *.pm   *.m4   *.am   *.css
Disallow *.map  *.aif  *.sit  *.sea
Disallow *.m3u  *.qt

# Exclude Apache directory list in different sort order using "string" match:
Disallow *D=A *D=D *M=A *M=D *N=A *N=D *S=A *S=D

# More complicated case. RAR .r00-.r99, ARJ a00-a99 files 
# and UNIX shared libraries. We use "Regex" match type here: