rec10/trunk/src/zenhan.py

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