[KoCo-CVS] [Commit] KoreanCodecs/korean/python hangul.py

[Chang <pe...@us...>]

perky       02/04/23 22:00:03

  Modified:    korean/python hangul.py
  Log:
  - Simpilify join, split function implementation.
  
  Revision  Changes    Path
  1.2       +16 -16    KoreanCodecs/korean/python/hangul.py
  
  Index: hangul.py
  ===================================================================
  RCS file: /cvsroot/koco/KoreanCodecs/korean/python/hangul.py,v
  retrieving revision 1.1
  retrieving revision 1.2
  diff -u -r1.1 -r1.2
  --- hangul.py	24 Apr 2002 03:36:01 -0000	1.1
  +++ hangul.py	24 Apr 2002 05:00:03 -0000	1.2
  @@ -15,7 +15,7 @@
   # Conjoining Jamo Behavior:
   #  http://www.unicode.org/unicode/uni2book/ch03.pdf  (section 3.11)
   #
  -# $Id: hangul.py,v 1.1 2002/04/24 03:36:01 perky Exp $
  +# $Id: hangul.py,v 1.2 2002/04/24 05:00:03 perky Exp $
   #
   
   class UnicodeHangulError(Exception):
  @@ -90,9 +90,9 @@
   
   # Unicode Hangul Syllables Characteristics
   zone = (u'\uAC00', u'\uD7A3')
  -splitters = [ ( len(Jongsung)*len(Jungsung), Chosung  ),
  -              ( len(Jongsung),               Jungsung ),
  -              ( 1,                           Jongsung ) ]
  +NCHOSUNG  = len(Chosung)
  +NJUNGSUNG = len(Jungsung)
  +NJONGSUNG = len(Jongsung)
   
   ishangul = (
       lambda code:
  @@ -127,12 +127,12 @@
       if not codes[0] or not codes[1]: # single jamo
           return codes[0] or codes[1]
   
  -    r = ord(zone[0])
  -    codes = codes[:]  # simple copy :D
  -    for multiplier, codeset in splitters:
  -        r = r + multiplier*codeset.index(codes.pop(0))
  -
  -    return unichr(r)
  +    return unichr(
  +        0xac00 + (
  +            Chosung.index(codes[0])*NJUNGSUNG +
  +            Jungsung.index(codes[1])
  +        )*NJONGSUNG + Jongsung.index(codes[2])
  +    )
   
   def split(code):
       """ Split function which splits hangul syllable into jamos """
  @@ -143,12 +143,12 @@
       if code in Moeum.Codes:
           return [Null, code, Null]
   
  -    code = ord(code) - ord(zone[0])
  -    r = []
  -    for divider, codeset in splitters:
  -        value, code = code / divider, code % divider
  -        r.append(codeset[value])
  -    return r
  +    code = ord(code) - 0xac00
  +    return [
  +        Chosung[int(code / (NJUNGSUNG*NJONGSUNG))], # Python3000 safe
  +        Jungsung[int(code / NJONGSUNG) % NJUNGSUNG],
  +        Jongsung[code % NJONGSUNG]
  +    ]
   
   def dividestring(str, intoelements=0):
       if type(str) is not type(u''):