# # This is a Namazu configuration file for mknmz. # #--------------------------------------------------------------- # # Administrator's email address #↓ここにメールアドレスを記入 $conf::ADDRESS = 'hoge@page.bar.ne.jp'; #--------------------------------------------------------------- # # Regular Expression Patterns # # # This pattern specifies HTML suffixes. # # $conf::HTML_SUFFIX = 'html?|[ps]html|html\.[a-z]{2}|asp|cgi'; # # This pattern specifies file names which will be targeted. # NOTE: It can be specified by --allow=regex option. # Do NOT use `$' or `^' anchors. # Case-insensitive. # $conf::ALLOW_FILE = '.*\.hnf'; # # This pattern specifies file names which will NOT be targeted. # NOTE: It can be specified by --deny=regex option. # Do NOT use `$' or `^' anchors. # Case-insensitive. # # $conf::DENY_FILE = '.*\.(gif|png|jpg|jpeg)|.*\.tar\.gz|core|.*\.bak|.*~|\..*|\x23.*|NMZ\..*'; # # This pattern specifies PATHNAMEs which will NOT be targeted. # NOTE: Usually specified by --exclude=regex option. # # $conf::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. # # $conf::DIRECTORY_INDEX = ""; # # This pattern specifies Mail/News's fields in its header which # should be searchable. NOTE: case-insensitive # # $conf::REMAIN_HEADER = "From|Date|Message-ID"; # # This pattern specifies fields which used for field-specified # searching. NOTE: case-insensitive # # $conf::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 # # $conf::META_TAGS = 'keywords|description'; # # This pattern specifies aliases for NMZ.field.* files. # NOTE: Editing NOT recommended. # # %conf::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. # # $conf::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. #↓ここは使用するメモリーのサイズ。このままでも可。 $conf::ON_MEMORY_MAX = 1000000; # # 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. # # $conf::FILE_SIZE_MAX = 2000000; # # The max text size for indexing. Files larger than this # will be ignored. # # $conf::TEXT_SIZE_MAX = 600000; # # The max length of a word. the word longer than this will be ignored. # # $conf::WORD_LENG_MAX = 128; # # Weights for HTML elements which are used for term weightning. # # %conf::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. # # $conf::INVALID_LENG = 128; # # The max length of a field. # This MUST be smaller than libnamazu.h's BUFSIZE (usually 1024). # # $conf::MAX_FIELD_LENGTH = 200; #--------------------------------------------------------------- # # Settings for robots.txt # FIXME: I don't know whether the settings works or not. # # $conf::HTDOCUMENT_ROOT = "/usr/local/apache/share/htdocs"; # $conf::HTDOCUMENT_ROOT_URI_PREFIX = "http://www.foo.domain.jp/"; # $conf::ROBOTS_TXT = "$HTDOCUMENT_ROOT/robots.txt"; # $conf::ROBOTS_EXCLUDE_URIS = ""; #--------------------------------------------------------------- # # Softwares for handling a Japanese text # # # Network Kanji Filter nkf v1.62 or later # #$conf::NKF = "/usr/bin/nkf"; # # KAKASI #↓モジュールkakasiを使用している場合。書き換え不要。 $conf::KAKASI = "module_kakasi -ieuc -oeuc -w"; # # ChaSen 1.51 or later (simple wakatigaki) # # $conf::CHASEN = "no -j -F '\%m '"; # # ChaSen 1.51 or later (with noun words extraction) # # $conf::CHASEN_NOUN = "no -j -F '\%m %H\\n'"; # # Default Japanese processer: KAKASI or ChaSen. # #$conf::WAKATI = $KAKASI; #--------------------------------------------------------------- # # HyperNikkiSystem (hns) #以下を追加。 $hnf::hns_version = 2; # hns major version, 2 or 1 ##↓下に日記のURIを記入 $hnf::diary_uri = "http://www.yomogi.sakura.ne.jp/~hiro/diary"; #↓にメールアドレスを記入 $hnf::author = 'foo@bar.ne.jp'; #↓にalias.txtの絶対パスを記入。aliasを使っていない人は不要。 $hnf::alias_file = " /home/hiro/diary/conf/alias.txt"; #↓はそのまま。 $hnf::grp_hide = 1; # 1 -> don't show GRP section # 0 -> show GRP section # 1;