mave_base.rb

   1 require 'kconv'
   2
   3 #===============================================================================
   4 #
   5 #       Integer
   6 #
   7 class Integer
   8
   9         #-----------------------------------------------------------
  10         #
  11         #       数値を人間に読みやすい表現形式で返す
  12         #
  13         def to_h(dot = false)
  14                 unless((full = self.to_s).length > 3)
  15                         full
  16                 else
  17                         case full.length % 3
  18                                 when 1 then top = full[0, 1] + (dot ? '.' + full[1, 1] : '')
  19                                 when 2 then top = full[0, 2]
  20                                 when 0 then top = full[0, 3]
  21                         end
  22                         top + '....KKKMMMGGGTTTPPP'[full.length].chr
  23                 end
  24         end
  25 end
  26
  27 #===============================================================================
  28 #
  29 #       String
  30 #
  31 class String
  32
  33         #-----------------------------------------------------------
  34         #
  35         #       キャラクタセットの定義
  36         #
  37         #               http://www.iana.org/assignments/character-sets
  38         #
  39         @@charsets = {
  40                 'ISO-2022-JP'   => Kconv::JIS,
  41                 'SHIFT_JIS'             => Kconv::SJIS,
  42                 'EUC-JP'                => Kconv::EUC,
  43                 'UTF-8'                 => Kconv::UTF8,
  44         }
  45
  46         def self.charset(charset)
  47                 @@charsets[charset]
  48         end
  49
  50         #-----------------------------------------------------------
  51         #
  52         #       メッセージヘッダのデコーダ
  53         #
  54         #               http://tools.ietf.org/html/rfc2047
  55         #
  56         @@decoders = {}
  57
  58         def self.bind_decoder(code)
  59                 @@decoders[code.upcase] = Proc.new
  60         end
  61
  62         def decode_mh                                                                                           # decode message header
  63                 gsub(/=\?([^?]+)\?(B|Q)\?([^?]+)\?=/i) {
  64                         $3.decode_ec($2).decode_cs('UTF-8', $1)                         #### now fixed utf-8
  65                 }
  66         end
  67
  68         def decode_ec(code)                                                                                     # decode encodings
  69                 (it = @@decoders[code.upcase]) ? it.call(self) : self
  70         end
  71
  72         def decode_cs(out_code, in_code)                                                        # decode character sets
  73                 (it = @@decoders[in_code.upcase]) ? it.call(self, out_code) : self
  74         end
  75
  76         #-----------------------------------------------------------
  77         #
  78         #       文字列を指定の長さに切り詰める
  79         #
  80         @@snippers = {}
  81         @@each_snippers = {}
  82         @@current_snip_charset = 'UTF-8'
  83
  84         def self.bind_snipper(charset)
  85                 @@snippers[charset] = Proc.new
  86         end
  87
  88         def self.bind_each_snipper(charset)
  89                 @@each_snippers[charset] = Proc.new
  90         end
  91
  92         def self.set_snip_charset(charset)
  93                 @@current_snip_charset = charset
  94         end
  95
  96         def snip(n)
  97                 @@snippers[@@current_snip_charset].call(self, n)
  98         end
  99
 100         def each_snip(n, max = 9999)
 101                 @@each_snippers[@@current_snip_charset].call(self, n, max, Proc.new)
 102         end
 103
 104         #-----------------------------------------------------------
 105         #
 106         #       端末の UTF-8 対応の不備を補う
 107         #
 108         #               http://ja.wikipedia.org/wiki/UTF-8
 109         #
 110         def enspc
 111                 self.gsub(/[\xC0-\xE2][\x80-\xBF]+/) {|c|                               #### いーかげん
 112                         c + '_'
 113                 }
 114         end
 115 end
 116
 117 #===============================================================================
 118 #
 119 #       多言語対応クラス
 120 #
 121 #               http://www.gnu.org/software/gettext/gettext.html
 122 #
 123 class Intl
 124
 125         @@domains = {}
 126         @@domains[@@current_domain = 'default'] = {}
 127
 128         def self.bind_text_domain(domain, dirname = '')
 129                 load "#{dirname}#{domain}.pmo"
 130                 @@domains[domain] = @@catalog
 131         end
 132
 133         def self.set_text_domain(domain)
 134                 @@current_domain = domain
 135         end
 136
 137         def self.get_text(msgid)
 138                 @@domains[@@current_domain][msgid] or msgid
 139         end
 140 end
 141
 142 #===============================================================================
 143 #
 144 #       多言語対応
 145 #
 146 def _(msgid)
 147         Intl.get_text(msgid)
 148 end
 149
 150 #===============================================================================
 151 #
 152 #       その他
 153 #
 154 def yap(arg = 'done.')
 155         @yap = 0 unless(@yap)
 156         print "#{@yap += 1}: #{arg.inspect}\n"
 157 end
 158
 159 def debug(log = 'log.', obj = self)
 160         @debug = File.new('debug.log', 'a') and @debug.write('-' * 76 + "\n") unless(@debug)
 161         @debug.write(obj.to_s + ': ' + log.to_s + "\n")
 162 end
 163
 164 #===============================================================================
 165 #
 166 #       各種デコーダを登録
 167 #
 168 String.bind_decoder('7BIT') {|str|                                                              # 7bit decoder
 169         str
 170 }
 171 String.bind_decoder('8BIT') {|str|                                                              # 8bit decoder
 172         str
 173 }
 174 String.bind_decoder('BINARY') {|str|                                                    # binary decoder?
 175         '-- binary --'
 176 }
 177 String.bind_decoder('BASE64') {|str|                                                    # Base64 decoder
 178         str.unpack('m')[0]
 179 }
 180 String.bind_decoder('QUOTED-PRINTABLE') {|str|                                  # Quoted Printable decoder
 181         str.unpack('M')[0]
 182 }
 183 String.bind_decoder('B') {|str|                                                                 # Base64 decoder
 184         str.unpack('m')[0]
 185 }
 186 String.bind_decoder('Q') {|str|                                                                 # Quoted Printable decoder
 187         str.unpack('M')[0]
 188 }
 189 String.bind_decoder('US-ASCII') {|str, out_code|                                # us-ascii(auto) decoder
 190         str.kconv(String.charset(out_code))
 191 }
 192 String.bind_decoder('ISO-2022-JP') {|str, out_code|                             # iso-2022-jp decoder
 193         str.kconv(String.charset(out_code), Kconv::JIS)
 194 }
 195 String.bind_decoder('SHIFT_JIS') {|str, out_code|                               # shift_jis decoder
 196         str.kconv(String.charset(out_code), Kconv::SJIS)
 197 }
 198 String.bind_decoder('EUC-JP') {|str, out_code|                                  # euc-jp decoder
 199         str.kconv(String.charset(out_code), Kconv::EUC)
 200 }
 201 String.bind_decoder('UTF-8') {|str, out_code|                                   # utf-8 decoder
 202         str.kconv(String.charset(out_code), Kconv::UTF8)
 203 }
 204 #       http://tools.ietf.org/html/rfc2152
 205 String.bind_decoder('UTF-7') {|str, out_code|                                   # utf-7 decoder
 206         str.gsub(%r|\+([A-Za-z0-9+/]+)-?|) {|p|
 207                 ($1 + '==').unpack('m')[0].kconv(Kconv::UTF8, Kconv::UTF16)
 208         }.gsub(/\+-/, '+').kconv(String.charset(out_code), Kconv::UTF8)
 209 }
 210
 211 #### String.wsize                                                                                               # 表示幅を得る
 212
 213 #### String.center                                                                                              # センタリングする
 214
 215 String.bind_snipper('UTF-8') {|str, n|                                                  # 指定の長さに切り詰める
 216         ws = str[0, n * 2].gsub(/[\xC0-\xFD][\x80-\xBF]+/, "\xFF\xFF")[0, n]
 217         wc = ws.count("\xFF")
 218         str.slice(0, n + wc / 2 - wc % 2).enspc + ' ' * (n - ws.length + wc % 2)
 219 }
 220
 221 String.bind_each_snipper('UTF-8') {|str, n, max, proc|                  # 指定の長さに切り詰め、順に行を渡す
 222         p = 0; while(p <= str.length)                                                           # '<': 改行文字のみの行は省略
 223                 break if((max -= 1) < 0)
 224                 ws = str[p, n * 2].gsub(/[\xC0-\xFD][\x80-\xBF]+/, "\xFF\xFF")[0, n]
 225                 wc = ws.count("\xFF")
 226                 proc.call(str.slice(p, nn = n + wc / 2 - wc % 2).enspc + ' ' * (n - ws.length + wc % 2))
 227                 p += nn
 228         end
 229 }
 230
 231 #### TAB 対応
 232
 233 __END__
 234