rec10/zenhan.py

   1 #!/usr/bin/python
   2 # coding: UTF-8
   3 # Rec10 TS Recording Tools
   4 # Copyright (C) 2009-2011 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_sp = unichr(0x2212)+unichr(0xff0e)
  14 h_ascii_sp = unichr(0x002d)+unichr(0x002e)
  15 z_number = u"０１２３４５６７８９"
  16 h_number = u"0123456789"
  17 z_alphabet = u"ＡＢＣＤＥＦＧＨＩＪＫＬＭＮＯＰＱＲＳＴＵＶＷＸＹＺａｂｃｄｅｆｇｈｉｊｋｌｍｎｏｐｑｒｓｔｕｖｗｘｙｚ　＃"
  18 h_alphabet = u"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz #"
  19 def toHankaku(str):
  20     retstr = u""
  21     for s in str:
  22         i = z_ascii.find(s)
  23         if (i != -1):
  24             s = h_ascii[i]
  25         i = z_ascii_sp.find(s)
  26         if (i != -1):
  27             s = h_ascii_sp[i]
  28         i = z_number.find(s)
  29         if (i != -1):
  30             s = h_number[i]
  31         retstr = retstr + s
  32     return retstr
  33 def toHankaku_ABC123(str):
  34     retstr = u""
  35     for s in str:
  36         i = z_alphabet.find(s)
  37         if (i != -1):
  38             s = h_alphabet[i]
  39         i = z_ascii_sp.find(s)
  40         if (i != -1):
  41             s = h_ascii_sp[i]
  42         i = z_number.find(s)
  43         if (i != -1):
  44             s = h_number[i]
  45         retstr = retstr + s
  46     return retstr
  47 def checkCharacterType(character):
  48     """
  49     return code is 1:Alphabet 2:Hiragana 3:Katakana 4:Kanji
  50     """
  51     chcode=ord(character)
  52     if chcode>=0x0000 and chcode<=0x007F:
  53         return 1
  54     elif chcode>=0x3040 and chcode<=0x309F:
  55         return 2
  56     elif chcode>=0x30A0 and chcode<=0x30FF:
  57         return 3
  58     elif chcode>=0x4E00 and chcode<=0x9FFF:
  59         return 4