def composeHangulJamoToSyllable(L0,V0,T0=None):
if not ((L0 == None or isUnicodeChar(L0)) and isUnicodeChar(V0) and (T0 == None or isUnicodeChar(T0))):
raise Exception('Jamo not unicode characters: %s %s %s' % (L0,V0,T0 if T0 != None else str(T0)))
if L0 == None:
L0 = emptyJamo_L
if isHangulCompatibilityJamo(L0):
L = hangulCompatibilityJamoToJamo_L(L0)
else:
L = L0
if isHangulCompatibilityJamo(V0):
V = hangulCompatibilityJamoToJamo_V(V0)
else:
V = V0
if T0 != None:
if isHangulCompatibilityJamo(T0):
T = hangulCompatibilityJamoToJamo_T(T0)
else:
T = T0
else:
T = None # or do we want empty T pseudo Jamo?
LIndex = _hangulJamoToIndex_L(L)
VIndex = _hangulJamoToIndex_V(V)
TIndex = _hangulJamoToIndex_T(T)
cpSyll = (LIndex * VCount + VIndex) * TCount + TIndex + SBase
if not isCombinedS(cpSyll):
raise Exception("Codepoint produced by composition not Hangul syllable: " + codePointToCodePointString(cpSyll))
return codePointToCharacter(cpSyll)
def main():
# Write data in py nested tuple format, which needs to be pasted into this file. Function returns None.
# The file UnicodeData.txt resides in the UCD directory of the Unicode data distribution. See http://unicode.org/reports/tr44/#UCD_Files
# Unicode 6 version was used to make data in this file
makeJamoDataFromUnicodeData('UnicodeData.txt',sys.stdout)
# Write templates for transLists - transliterations will be '' and will need to be filled in with actual values
printTransList_L(sys.stdout)
printTransList_V(sys.stdout)
printTransList_T(sys.stdout)
for syllIndex in xrange(0,SCount,256):
syllCP = SBase + syllIndex
syll = unichr(syllCP)
L,V,T = decomposeHangulSyllableToJamo(syll)
print codePointToCodePointString(syllCP),syll,hangulJamoToTrans(L),hangulJamoToTrans(V),hangulJamoToTrans(T)
def test_conversions(self):
for char,expected in ((u'a','U+0061'),('a','U+0061'),(u'ㄱ','U+3131'),(u'가','U+AC00'),(u'㐀','U+3400'),(u'𠀀','U+20000')):
cp = cu.characterToCodepoint(char) # ord(char)
self.assertTrue(cu.codePointExists(cp))
char2 = cu.codePointToCharacter(cp)
self.assertTrue(cu.isUnicodeChar(char2))
self.assertEquals(char,char2)
cpStr = cu.codePointToCodePointString(cp)
self.assertEquals(cpStr,expected)
cp2 = cu.codePointStringToCodePoint(cpStr)
self.assertEquals(cp,cp2)
char3 = cu.codePointStringToCharacter(cpStr)
self.assertEquals(char3,char)
def hangulJamoToTrans(jamo):
if jamo == None: # Assume empty T
return ''
if not isUnicodeChar(jamo):
raise Exception('Not a unicode char: ' + unicode(jamo))
cp = ord(jamo)
if isL(cp):
return jamoTransList_L[cp - LBase]
elif isV(cp):
return jamoTransList_V[cp - VBase]
elif isT(cp):
return jamoTransList_T[cp - TBase]
else:
raise Exception('Not a Hangul Jamo: ' + codePointToCodePointString(cp) + ' ' +unicode(jamo))
def printTransList_T(out):
print >> out, '\njamoTransList_T = ['
for i in xrange(TCount):
print >> out, '\'\', #',i,codePointToCodePointString(TBase + i),unichr(TBase + i)
print ']'