conf.pl

namazu. 虽然是日语的,也适用于文件中单词索引后全文检索.

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

#===================================================================
#
# Administrator's email address
#
$ADDRESS = '[e-mail]';


#===================================================================
#
# 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|.*\\.ppt" .	   # Word, Excel, PowerPoint
		"|.*\\.j[sabf]w|.*\\.jtd" .        # Ichitaro 4, 5, 6, 7, 8
		"|\\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 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';

#===================================================================
# 
# 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   = 5000000;

#
# 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 <meta name="keywords" content="foo bar">
     '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 
#       <h[1-6]> 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 v1.62 or later
#
$NKF = "module_nkf"; 

#
# KAKASI
#
$KAKASI = "module_kakasi -ieuc -oeuc -w";

#
# ChaSen 1.51 or later (simple wakatigaki)
#
$CHASEN = "chasen -j -F '\%m '";

#
# ChaSen 1.51 or later (with noun words extraction)
#
$CHASEN_NOUN = "chasen -j -F '\%m %H\\n'";

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


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

1;