# This is a Namazu configuration file for namazu or namazu.cgi.
#
#  Originally, this file is named 'namazurc-sample'.  so you should
#  copy this to 'namazurc' to make the file effective.
#  
#  Each item is must be separated by one or more SPACE or TAB characters. 
#  You can use a double-quoted string for represanting a string which 
#  contains SPACE or TAB characters like "foo bar baz".


##
## Index: Specify the default directory.
## 
Index         /var/lib/apache/htdocs/


##
## Template: Set the template directory containing
## NMZ.{head,foot,body,tips,result} files.
##
Template      /var/lib/apache/htdocs/


##
## Replace: Replace TARGET with REPLACEMENT in URIs in search
## results.  
##
## TARGET is specified by Ruby's perl-like regular expressions.  
## You can caputure sub-strings in TARGET by surrounding them 
## with `(' and `)'and use them later as backreferences by
## \1, \2, \3,... \9.
##  
## To use meta characters literally such as `*', `+', `?', `|', 
## `[', `]', `{', `}', `(', `)', escape them with `\'.
##  
## e.g.,
##  
##    Replace  /home/foo/public_html/   http://www.foobar.jp/~foo/
##    Replace  /home/(.*)/public_html/  http://www.foobar.jp/\1/
##    Replace  /[Cc]\|/foo/             http://www.foobar.jp/
##  
## If you do not want to do the processing on command line use, 
## run namazu with -U option.
##
## You can specify more than one Replace rules but the only 
## first-matched rule are applied. 
##
Replace       /var/lib/apache/htdocs/  http://www.ドメイン名/


##
## Logging: Set OFF to turn off keyword logging to NMZ.slog. 
## Default is ON.
##
Logging       ON


##
## Lang: Set the locale code such as `ja_JP.eucJP', `ja_JP.SJIS', 
## `de', etc.  This directive works only if the environment 
## variable LANG is not set because the directive is mainly 
## intended for CGI use.  On the shell, You can set 
## environemtnt variable LANG instead of using the directive.
## 
## If you set `de' to it, namazu.cgi use 
## NMZ.(head|foot|body|tips|results).de for displaying results 
## and use a proper message catalog for `de'.
##
Lang          ja


##
## Scoring: Set the scoring method "tfidf" or "simple".
##
Scoring       tfidf


##
## EmphasisTags: Set the pair of html elements which is used in
## keyword emphasizing for search results.
##
EmphasisTags  ""   ""

##
## MaxHit: Set the maximum number of documents which can be
## handled in query operation.  If documents matching a
## query exceed the value, they will be ignored.
##
MaxHit	10000

##
## MaxMatch: Set the maximum number of words which can be
## handled in regex/prefix/inside/suffix query. If documents
## matching a query exceed the value, they will be ignored.
##
MaxMatch	1000

##
## ContentType: Set "Content-Type" header output. If you want to
## use non-HTML template files, set it suitably.
##
#ContentType	"text/x-hdml"

##
## Suicide_Time: namazu.cgi stops the process in 60 seconds by
## default.
## (Only UNIX)
##
#Suicide_Time	60

##
## Regex_Search: Set OFF to turn off regex_search.
## Default is ON.
##
#Regex_Search	off

#
# This is a Namazu configuration file for mknmz.
#
package conf;  # Don't remove this line!

#===================================================================
#
# Administrator's email address
#
 $ADDRESS = 'hirosima@ドメイン名';


#===================================================================
#
# Regular Expression Patterns
#

#
# This pattern specifies HTML suffixes.
#
 $HTML_SUFFIX = "html?|[ps]html|html\\.[a-z]{2}";

#
# This pattern specifies file names which will be targeted.
# NOTE: It can be specified by --allow=regex option.
#       Do NOT use `$' or `^' anchors.
#       Case-insensitive.
#
 $ALLOW_FILE =	".*\\.(?:$HTML_SUFFIX)|.*\\.txt" . # HTML, plain text
 		"|.*\\.gz|.*\\.Z|.*\\.bz2" .       # Compressed files
 		"|.*\\.pdf|.*\\.ps" . 		   # PDF, PostScript
 		"|.*\\.tex|.*\\.dvi" .   	   # TeX, DVI
 		"|.*\\.rpm|.*\\.deb" .   	   # RPM, DEB
 		"|.*\\.doc|.*\\.xls|.*\\.pp[st]" . # Word, Excel, PowerPoint
 		"|.*\\.docx|.*\\.xlsx|.*\\.pp[st]x" . # MS-OfficeOpenXML Word, Excel, PowerPoint
 		"|.*\\.vs[dst]|.*\\.v[dst]x" .     # Visio
 		"|.*\\.j[sabf]w|.*\\.jtd" .        # Ichitaro 4, 5, 6, 7, 8
 		"|.*\\.sx[widc]" .                 # OpenOffice Writer,Calc,Impress,Draw
 		"|.*\\.od[tspg]" .                 # OpenOffice2.0
 		"|.*\\.rtf" .                      # Rich Text Format
 		"|.*\\.hdml|.*\\.mht" .		   # HDML MHTML
 		"|.*\\.mp3" .			   # MP3 
 		"|.*\\.gnumeric" .                 # Gnumeric
 		"|.*\\.kwd|.*\\.ksp" .             # KWord, KSpread
 		"|.*\\.kpr|.*\\.flw" .             # KPresenter, Kivio
 		"|.*\\.eml|\\d+|[-\\w]+\\.[1-9n]"; # Mail/News, man

#
# This pattern specifies file names which will NOT be targeted.
# NOTE: It can be specified by --deny=regex option.
#       Do NOT use `$' or `^' anchors.
#       Case-insensitive.
#
 $DENY_FILE = ".*\\.(gif|png|jpg|jpeg)|.*\\.tar\\.gz|core|.*\\.bak|.*~|\\..*|\x23.*";

#
# This pattern specifies DDN(DOS Device Name) which will NOT be targeted.
# NOTE: Only for Windows.
#       Do NOT use `$' or `^' anchors.
#       Case-insensitive.
#
 $DENY_DDN = "con|aux|nul|prn|lpt[1-9]|com[1-9]|clock\$|xmsxxxx0";

#
# This pattern specifies PATHNAMEs which will NOT be targeted.
# NOTE: Usually specified by --exclude=regex option.
#
 $EXCLUDE_PATH = undef;

#
# This pattern specifies file names which can be omitted 
# in URI.  e.g., 'index.html|index.htm|Default.html'
#
# NOTE: This is similar to Apache's "DirectoryIndex" directive.
#
 $DIRECTORY_INDEX = "";

#
# This pattern specifies Mail/News's fields in its header which 
# should be searchable.  NOTE: case-insensitive
#
 $REMAIN_HEADER = "From|Date|Message-ID";

#
# This pattern specifies fields which used for field-specified 
# searching.  NOTE: case-insensitive
# 
 $SEARCH_FIELD = "message-id|subject|from|date|uri|newsgroups|to|summary|size";

#
# This pattern specifies meta tags which used for field-specified 
# searching.  NOTE: case-insensitive
#
 $META_TAGS = "keywords|description";

#
# This pattern specifies aliases for NMZ.field.* files.
# NOTE: Editing NOT recommended.
#
 %FIELD_ALIASES = ('title' => 'subject', 'author' => 'from');

#
# This pattern specifies HTML elements which should be replaced with 
# null string when removing them. Normally, the elements are replaced 
# with a single space character.
#
 $NON_SEPARATION_ELEMENTS = 'A|TT|CODE|SAMP|KBD|VAR|B|STRONG|I|EM|CITE|FONT|U|'.
                        'STRIKE|BIG|SMALL|DFN|ABBR|ACRONYM|Q|SUB|SUP|SPAN|BDO';

#
# This pattern specifies attribute of a HTML tag which should be 
# searchable.
#
# $HTML_ATTRIBUTES = 'ALT|SUMMARY|TITLE';


#===================================================================
# 
# Critical Numbers
# 

# 
# The max size of files which can be loaded in memory at once.
# If you have much memory, you can increase the value.
# If you have less memory, you can decrease the value.
#
 $ON_MEMORY_MAX   = 512000000; ←検索INDEX作成時に500MBのメモリを与えています。

#
# The max file size for indexing. Files larger than this 
# will be ignored.
# NOTE: This value is usually larger than TEXT_SIZE_MAX because 
#       binary-formated files such as PDF, Word are larger.
#
 $FILE_SIZE_MAX   = 2000000;

#
# The max text size for indexing. Files larger than this 
# will be ignored.
#
 $TEXT_SIZE_MAX   =  600000;

#
# The max length of a word. the word longer than this will be ignored.
#
 $WORD_LENG_MAX   = 128;


#
# Weights for HTML elements which are used for term weightning.
#
 %Weight = 
     (
      'html' => {
          'title'  => 16,
          'h1'     => 8,
          'h2'     => 7,
          'h3'     => 6,
          'h4'     => 5,
          'h5'     => 4,
          'h6'     => 3,
          'a'      => 4,
          'strong' => 2,
          'em'     => 2,
          'kbd'    => 2,
          'samp'   => 2,
          'var'    => 2,
          'code'   => 2,
          'cite'   => 2,
          'abbr'   => 2,
          'acronym'=> 2,
          'dfn'    => 2,
      },
      'metakey' => 32, # for 
      'headers' => 8,  # for Mail/News' headers
 );

#
# The max length of a HTML-tagged string which can be processed for
# term weighting. 
# NOTE: There are not a few people has a bad manner using 
#        for changing a font size.
#
 $INVALID_LENG = 128; 

#
# The max length of a field.
# This MUST be smaller than libnamazu.h's BUFSIZE (usually 1024).
#
 $MAX_FIELD_LENGTH = 200;


#===================================================================
#
# Softwares for handling a Japanese text
#

#
# Network Kanji Filter nkf v1.71 or later
#
 $NKF = "/usr/local/bin/nkf"; 

#
# KAKASI 2.x or later
# Text::Kakasi 1.05 or later
#
 $KAKASI = "/usr/local/bin/kakasi -ieuc -oeuc -w";

#
# ChaSen 2.02 or later (simple wakatigaki)
# Text::ChaSen 1.03
#
# $CHASEN = "no";

#
# ChaSen 2.02 or later (with noun words extraction)
#
# $CHASEN_NOUN = "no";

#
# MeCab
#
# $MECAB = "no";

#
# Default Japanese processer: KAKASI or ChaSen.
#
 $WAKATI  = $KAKASI;


#===================================================================
#
# Directories
#
# $LIBDIR = "@PERLLIBDIR@";
# $FILTERDIR = "@FILTERDIR@";
# $TEMPLATEDIR = "@TEMPLATEDIR@";

# 1;