indexer.conf

完美的在线教育系统

########################################################################
#NetErrorDelayTime <time>
# Specify document processing delay time if network error has occurred.
# For <time> format see description of Period above.
# Default value is one day
#NetErrorDelayTime 1d


#######################################################################
#Robots yes/no
# Allows/disallows using robots.txt and <META NAME="robots">
# exclusions. Use "no", for example for link validation of your server(s).
# Command may be used several times before "Server" command and
# takes effect till the end of config file or till next Robots command.
# Default value is "yes".
#Robots yes


#######################################################################
#DetectClones yes/no
# Allow/disallow clone detection and eliminating. If allowed, indexer will 
# detect the same documents under different location, such as
# mirrors, and will index only one document from the group of
# such equal documents. "DetectClones yes" also allows to reduce space usage.
# Default value is "yes".
DetectClones yes


#######################################################################
# Document sections.
#
# Format is:
#
#   Section <string> <number> <maxlen> [clone] [sep] [{expr} {repl}]
#
# where <string> is a section name and <number> is section ID
# between 0 and 255. Use 0 if you don't want to index some of 
# these sections. It is better to use different sections IDs
# for different documents parts. In this case during search 
# time you'll be able to give different weight to each part
# or even disallow some sections at a search time.
# <maxlen> argument contains a maximum length of section
# which will be stored in database.
# "clone" is an optional parameter describing whether this
# section should affect clone detection. It can 
# be "DetectClone" or "cdon", or "NoDetectClone" or "cdoff".
# By default, url.* section values are not taken in account
# for clone detection, while any other sections take part
# in clone detection.
# "sep" is an optional argument to specify a separator between
# parts of the same section. It is a space character by default.
# "expr" and "repl" can be used to extract user defined sections,
# for example pieces of text between the given tags. "expr" is
# a regular expression, "repl" is a replacement with $1, $2, etc
# meta-characters designating matches "expr" matches.

# Standard HTML sections: body, title

Section	body			1	256
Section title			2	128

# META tags
# For example <META NAME="KEYWORDS" CONTENT="xxxx">
#

Section meta.keywords		3	128
Section	meta.description	4	128

# HTTP headers example, let's store "Server" HTTP header
#
#
#Section header.server		5	64


# Document's URL parts

Section url.file		6	0
Section url.path		7	0
Section	url.host		8	0
Section url.proto		9	0

# CrossWords

Section crosswords		10	0

#
# If you use CachedCopy for smart excerpts (see below), 
# please keep Charset section active.
#
Section Charset 		11 	32

Section Content-Type		12	64
Section Content-Language	13	16

# Uncomment the following lines if you want tag attributes
# to be indexed

#Section attribute.alt		14	128
#Section attribute.label	15	128
#Section attribute.summary	16	128
#Section attribute.title	17	128
#Section attribute.face		27	0

# Uncomment the following lines if you want use NewsExtensions
# You may add any Newsgroups header to be indexed and stored in urlinfo table

#Section References		18	0
#Section Message-ID		19	0
#Section Parent-ID		20	0

# Uncomment the following lines if you want index MP3 tags.
#Section MP3.Song           	21    128
#Section MP3.Album          	22    128
#Section MP3.Artist         	23    128
#Section MP3.Year           	24    128

# Comment this line out if you don't want to store "cached copies"
# to generate smart excerpts at search time.
# Don't forget to keep "Charset" section active if you use cached copies.
# NOTE: 3.2.18 has limits for CachedCopy size, 32000 for Ibase and
# 15000 for Mimer. Other databases do not have limits.
# If indexer fails with 'string too long' error message then reduce
# this number. This will be fixed in the future versions.
#
Section CachedCopy		25 64000

# A user defined section example.
# Extract text between <h1> and </h1> tags:
#Section h1			26 128 "<h1>(.*)</h1>" $1

##########################################################################
#<IndexIf|NoIndexIf> [Match|NoMatch] [NoCase|Case] [String|Regex] <Section> <arg> [<arg> ... ]
# Use this to allow documents, which sections match given argument,
# to be indexed (IndexIf) or not indexed (NoIndexIf).
# First three optional parameters describe the type of comparison.
# Default values are Match, NoCase, String.
# See also Allow/Disallow.
# You may use several arguments for one 'IndexIf/NoIndexIf' commands.
# You may use this command any times.
# Takes global effect for config file.
# Example1: Don't index a document if its Body section contains "porno"
#NoIndexIf Body *porno*
#
# Example2: Index only those documents with Title section containing "reference"
#IndexIf Title *reference*
#NoIndexIf Title *

#######################################################################
#Index yes/no
# Prevent indexer from storing words into database.
# Useful for example for link validation.
# Can be set multiple times before "Server" command and
# takes effect till the end of config file or till next Index command.
# Default value is "yes".
#Index yes


########################################################################
#RemoteCharset <charset>
#<RemoteCharset> is default character set for the server in next "Server" 
# command(s).
# This is required only for "bad" servers that do not send information
# about charset in header: "Content-type: text/html; charset=some_charset"
# and do not have <META NAME="Content" Content="text/html; charset="some_charset">
# Can be set before every "Server" command and
# takes effect till the end of config file or till next RemoteCharset command.
# Default value is iso-8859-1 (latin1).
RemoteCharset iso-8859-1


#########################################################################
#ProxyAuthBasic login:passwd
# Use HTTP proxy basic authorization 
# Can be used before every "Server" command and
# takes effect only for next one "Server" command!
# It should be also before "Proxy" command.
# Examples:
#ProxyAuthBasic somebody:something  


#########################################################################
#Proxy your.proxy.host[:port]
# Use proxy rather then connect directly
#One can index ftp servers when using proxy
#Default port value if not specified is 3128 (Squid)
#If proxy host is not specified direct connect will be used.
#Can be set before every "Server" command and
# takes effect till the end of config file or till next Proxy command.
#If no one "Proxy" command specified indexer will use direct connect.
#
#           Examples:
#           Proxy on atoll.anywhere.com, port 3128:
#Proxy atoll.anywhere.com
#
#           Proxy on lota.anywhere.com, port 8090:
#Proxy lota.anywhere.com:8090
#
#           Disable proxy (direct connect):
#Proxy


#########################################################################
#AuthBasic login:passwd
# Use basic HTTP authorization 
# Can be set before every "Server" command and
# takes effect only for next one Server command!
# Examples:
#AuthBasic somebody:something  
#
# If you have password protected directory(ies), but whole server is open,use:
#AuthBasic login1:passwd1
#Server http://my.server.com/my/secure/directory1/
#AuthBasic login2:passwd2
#Server http://my.server.com/my/secure/directory2/
#Server http://my.server.com/


##############################################################
# Mirroring parameters commands.
#
# You may specify a path to root directory to enable sites mirroring
#MirrorRoot /path/to/mirror
#
# You may specify as well root directory of mirrored document's headers
# indexer will store HTTP headers to local disk too.
#MirrorHeadersRoot /path/to/headers
#
# MirrorPeriod <time>
# You may specify period during which earlier mirrored files 
# will be used while indexing instead of real downloading.
# It is very useful when you do some experiments with mnoGoSearch
# indexing the same hosts and do not want much traffic from/to Internet.
# If MirrorHeadersRoot is not specified and headers are not stored
# to local disk then default Content-Type's given in AddType commands
# will be used.
# Default value of the MirrorPeriod is -1, which means
# "do not use mirrored files".
#
# For <time> format see Period command description above.
#
# The command below will force using local copies for one day:
#MirrorPeriod 1d


#########################################################################
#ServerWeight <number>
# Server weight for Popularity Rank calculation.
# Default value is 1.
#ServerWeight 1


#########################################################################
#PopRankSkipSameSite yes|no
# Skip links from same site for Popularity Rank calculation.
# Default value is "no".
#PopRankSkipSameSite yes


#########################################################################
#PopRankFeedBack yes|no
# Calculate sites wights before Popularity Rank calculation.
# Default value is "no".
#PopRankSkipSameSite yes


#########################################################################
#Server [Method] [SubSection] <URL> [alias]
# This is the main command of the indexer.conf file. It's used 
# to describe web-space you want to index. It also inserts
# given URL into database to use it as a start point.
# You may use "Server" command as many times as a number of different
# servers or their parts you want to index.
#
# "Method" is an optional parameter which can take on of the following values:
# Allow, Disallow, CheckOnly, HrefOnly, CheckMP3, CheckMP3Only, Skip.
#
# "SubSection" is an optional parameter to specify server's subsection, 
# i.e. a part of Server command argument. 
# It can take the following values:
# "page" describes web space which consists of one page with address <URL>.
# "path" describes all documents which are under the same path with <URL>.
# "site" describes all documents from the same host with <URL>.
# "world" means "any document".
# Default value is "path".
#
# To index whole server "localhost":
#Server http://localhost/
#
# You can also specify some path to index subdirectory only:
#Server http://localhost/subdir/
#
# To specify the only one page:
#Server page http://localhost/path/main.html
#
# To index whole server but giving non-root page as a start point:
#Server site http://localhost/path/main.html
#
#
# You can also specify optional parameter "alias". This example will
# index server "http://www.mnogosearch.org/" directly from disk instead of
# fetching from HTTP server:
#Server http://www.mnogosearch.org/  file:///home/httpd/www.mnogosearch.org/
#
Server http://your.domain.com/indexer_login.php



#########################################################################
#Realm [Method] [CmpType] [Match|NoMatch] <arg> [alias]
# It works almost like "Server" command but takes a regular expression or 
# a string wildcards as it's argument and do not insert any URL into
# database for indexing. To insert URLs into database use URL command (see
# below).
#
# "Method" is an optional parameter which can take one of the following
# values: Allow, Disallow, CheckOnly, HrefOnly, CheckMP3, CheckMP3Only
# with Allow as a default value.
#
# "CmpType" is an optional parameter to specify comparison type and can
# take either String or RegExp value with String as a default value.
#
# For example, if you want to index all HTTP sites in ".ru" domain, use:
#Realm http://*.ru/*
# The same using "Regex" match:
#Realm Regex ^http://.*\.ru/
# Another example. Use this command to index everything without .com domain:
#Realm NoMatch http://*.com/*
#
# Optional "alias" argument allows to provide very complicated URL rewrite
# more powerful than other aliasing mechanism. Take a look into alias.txt
# for "alias" argument usage explanation.


#########################################################################
#URL http://localhost/path/to/page.html
# This command inserts given URL into database. This is useful to add
# several entry points to one server. Has no effect if an URL is already
# in the database. When inserting indexer does not executes any checks
# and this URL may be deleted at first indexing attempt if URL has no 
# correspondent Server command or is disallowed by rules given in 
# Allow/Disallow commands. 
#
#This command will add /main/index.html page:
#URL http://localhost/main/index.html

UseCookie yes