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 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_number = u"０１２３４５６７８９"
  14 h_number = u"0123456789"
  15 z_alphabet = u"ＡＢＣＤＥＦＧＨＩＪＫＬＭＮＯＰＱＲＳＴＵＶＷＸＹＺａｂｃｄｅｆｇｈｉｊｋｌｍｎｏｐｑｒｓｔｕｖｗｘｙｚ　＃"
  16 h_alphabet = u"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz #"
  17 def toHankaku(str):
  18     retstr = u""
  19     for s in str:
  20         i = z_ascii.find(s)
  21         if (i != -1):
  22             s = h_ascii[i]
  23         i = z_number.find(s)
  24         if (i != -1):
  25             s = h_number[i]
  26         retstr = retstr + s
  27     return retstr
  28 def toHankaku_ABC123(str):
  29     retstr = u""
  30     for s in str:
  31         i = z_alphabet.find(s)
  32         if (i != -1):
  33             s = h_alphabet[i]
  34         i = z_number.find(s)
  35         if (i != -1):
  36             s = h_number[i]
  37         retstr = retstr + s
  38     return retstr
  39 def check_Character_Type(character):
  40     """
  41     return code is 1:Alphabet 2:Hiragana 3:Katakana 4:Kanji
  42     """
  43     #recdblist.printutf8(character)
  44     #recdblist.printutf8(type(character))
  45     #character=character.encode('UTF-8')
  46     #recdblist.printutf8(character)
  47     #recdblist.printutf8(type(character))
  48     chcode=ord(character)
  49     #recdblist.printutf8(ord(chcode))
  50     if chcode>=0x0000 and chcode<=0x007F:
  51         return 1
  52     elif chcode>=0x3040 and chcode<=0x309F:
  53         return 2
  54     elif chcode>=0x30A0 and chcode<=0x30FF:
  55         return 3
  56     elif chcode>=0x4E00 and chcode<=0x9FFF:
  57         return 4