rec10/trunk/src/zenhan.py

   1 #!/usr/bin/python
   2 # coding: UTF-8
   3 # Rec10 TS Recording Tools
   4 # Copyright (C) 2009-2010 Yukikaze
   5
   6 import recdblist
   7 global z_ascii
   8 global h_ascii
   9 global z_number
  10 global h_number
  11 z_ascii = u"ＡＢＣＤＥＦＧＨＩＪＫＬＭＮＯＰＱＲＳＴＵＶＷＸＹＺａｂｃｄｅｆｇｈｉｊｋｌｍｎｏｐｑｒｓｔｕｖｗｘｙｚ　！”＃＄％＆’（）＊＋，−．／：；＜＝＞？＠［￥］＾＿‘｛｜｝〜　〜"
  12 h_ascii = u"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz !\"#$%&'()*+,-./:;<=>?@[\]^_`{|}~ -"
  13 #z_ascii = z_ascii+Ur"\Ue28892\Uefbc8e"
  14 #h_ascii = h_ascii+Ur"\Uefbc8d."
  15 z_ascii_sp = unichr(0x2212)+unichr(0xff0e)
  16 h_ascii_sp = unichr(0x002d)+unichr(0x002e)
  17 z_number = u"０１２３４５６７８９"
  18 h_number = u"0123456789"
  19 z_alphabet = u"ＡＢＣＤＥＦＧＨＩＪＫＬＭＮＯＰＱＲＳＴＵＶＷＸＹＺａｂｃｄｅｆｇｈｉｊｋｌｍｎｏｐｑｒｓｔｕｖｗｘｙｚ　＃"
  20 h_alphabet = u"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz #"
  21 def toHankaku(str):
  22     retstr = u""
  23     for s in str:
  24         i = z_ascii.find(s)
  25         if (i != -1):
  26             s = h_ascii[i]
  27         i = z_ascii_sp.find(s)
  28         if (i != -1):
  29             s = h_ascii_sp[i]
  30         i = z_number.find(s)
  31         if (i != -1):
  32             s = h_number[i]
  33         retstr = retstr + s
  34     return retstr
  35 def toHankaku_ABC123(str):
  36     retstr = u""
  37     for s in str:
  38         i = z_alphabet.find(s)
  39         if (i != -1):
  40             s = h_alphabet[i]
  41         i = z_ascii_sp.find(s)
  42         if (i != -1):
  43             s = h_ascii_sp[i]
  44         i = z_number.find(s)
  45         if (i != -1):
  46             s = h_number[i]
  47         retstr = retstr + s
  48     return retstr
  49 def check_Character_Type(character):
  50     """
  51     return code is 1:Alphabet 2:Hiragana 3:Katakana 4:Kanji
  52     """
  53     #recdblist.printutf8(character)
  54     #recdblist.printutf8(type(character))
  55     #character=character.encode('UTF-8')
  56     #recdblist.printutf8(character)
  57     #recdblist.printutf8(type(character))
  58     chcode=ord(character)
  59     #recdblist.printutf8(ord(chcode))
  60     if chcode>=0x0000 and chcode<=0x007F:
  61         return 1
  62     elif chcode>=0x3040 and chcode<=0x309F:
  63         return 2
  64     elif chcode>=0x30A0 and chcode<=0x30FF:
  65         return 3
  66     elif chcode>=0x4E00 and chcode<=0x9FFF:
  67         return 4