# This is a Namazu configuration file for mknmz.
#
package conf; # Don't remove this line!
# Administrator's email address
#
 $ADDRESS = 'tonkachi@servers.net';
#
# Regular Expression Patterns
#
# This pattern specifies HTML suffixes.
#
 $HTML_SUFFIX = "html?|[ps]html|html\\.[a-z]{2}";
#
 $ALLOW_FILE = ".*\\.(?:$HTML_SUFFIX)|.*\\.txt" .# HTML, plain text
#"|.*\\.gz|.*\\.Z|.*\\.bz2" .# Compressed files
#"|.*\\.pdf" .# PDF
"|.*\\.tex" .# TeX
#"|.*\\.doc|.*\\.xls" .# Word, Excel
#"|.*\\.j[sab]w" .# Ichitaro 4, 5, 6
#"|\\d+|[-\\w]+\\.[1-9n]";# Mail/News, man
#
 $DENY_FILE = ".*\\.(cgi|pl|log|dat|css)|.*\\.tar\\.gz|core|.*\\.bak|.*~|\\..*|\x23.*";
#
#
 $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';
#
 $ON_MEMORY_MAX = 5000000;
#
 $FILE_SIZE_MAX = 2000000;
#
 $TEXT_SIZE_MAX = 600000;
#
 $WORD_LENG_MAX = 128;
#
 $INVALID_LENG = 128;
#
 $MAX_FIELD_LENGTH = 200;
#
 $NKF = "module_nkf";
# $NKF = "/usr/bin/nkf";
#
 $KAKASI = "module_kakasi -ieuc -oeuc -w";
# $KAKASI = "/usr/bin/kakasi";
#
# Default Japanese processer: KAKASI or ChaSen.
#
 $WAKATI = $KAKASI;
#