[KoCo-CVS] [Commit] KoreanCodecs-Pure/korean cp949.py euc_kr.py johab.py
Brought to you by:
perky
Menu
▾
▴
[KoCo-CVS] [Commit] KoreanCodecs-Pure/korean cp949.py euc_kr.py johab.py
|
From: Hye-Shik C. <pe...@us...> - 2003-07-23 20:31:44
|
perky 03/07/23 13:31:43
Modified: korean cp949.py euc_kr.py johab.py
Log:
Fix for new mappings
Revision Changes Path
1.2 +4 -4 KoreanCodecs-Pure/korean/cp949.py
Index: cp949.py
===================================================================
RCS file: /cvsroot/koco/KoreanCodecs-Pure/korean/cp949.py,v
retrieving revision 1.1
retrieving revision 1.2
diff -u -r1.1 -r1.2
--- cp949.py 23 Jul 2003 19:09:50 -0000 1.1
+++ cp949.py 23 Jul 2003 20:31:43 -0000 1.2
@@ -24,15 +24,15 @@
# IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
#
-# $Id: cp949.py,v 1.1 2003/07/23 19:09:50 perky Exp $
+# $Id: cp949.py,v 1.2 2003/07/23 20:31:43 perky Exp $
#
from korean import euc_kr
-from korean.mappings import uhc
+from korean.mappings import cp949ext
class Codec(euc_kr.Codec):
- uhc_encmap = uhc.encoding_map
- uhc_decmap = uhc.decoding_map
+ uhc_encmap = cp949ext.cp949extencmap
+ uhc_decmap = cp949ext.cp949extdecmap
class StreamWriter(Codec, euc_kr.StreamWriter):
pass
1.2 +10 -44 KoreanCodecs-Pure/korean/euc_kr.py
Index: euc_kr.py
===================================================================
RCS file: /cvsroot/koco/KoreanCodecs-Pure/korean/euc_kr.py,v
retrieving revision 1.1
retrieving revision 1.2
diff -u -r1.1 -r1.2
--- euc_kr.py 23 Jul 2003 19:09:50 -0000 1.1
+++ euc_kr.py 23 Jul 2003 20:31:43 -0000 1.2
@@ -24,16 +24,11 @@
# IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
#
-# $Id: euc_kr.py,v 1.1 2003/07/23 19:09:50 perky Exp $
+# $Id: euc_kr.py,v 1.2 2003/07/23 20:31:43 perky Exp $
#
import codecs
-
-from korean.mappings import ksc5601_hangul
-encmap_hangul = ksc5601_hangul.encoding_map
-decmap_hangul = ksc5601_hangul.decoding_map
-encmap_ideo, decmap_ideo = {}, {}
-encmap_misc, decmap_misc = {}, {}
+from korean.mappings.ksx1001 import *
class Codec(codecs.Codec):
@@ -51,29 +46,14 @@
for c in data:
if c < u'\u0080':
buffer.append(c.encode("ascii", errors))
- elif encmap_hangul.has_key(c):
- buffer.append(encmap_hangul[c])
+ elif ksx1001encmap.has_key(c):
+ buffer.append(ksx1001encmap[c])
elif self.uhc_encmap.has_key(c):
buffer.append(self.uhc_encmap[c])
- else:
- if not encmap_misc:
- from korean.mappings import ksc5601_misc
- encmap_misc = ksc5601_misc.encoding_map
- if encmap_misc.has_key(c):
- buffer.append(encmap_misc[c])
- continue
-
- if not encmap_ideo:
- from korean.mappings import ksc5601_ideograph
- encmap_ideo = ksc5601_ideograph.encoding_map
- if encmap_ideo.has_key(c):
- buffer.append(encmap_ideo[c])
- continue
-
- if errors == 'replace':
- buffer.append('\xa1\xa1')
- elif errors == 'strict':
- raise UnicodeError, "cannot map \\u%04x to EUC-KR" % ord(c)
+ elif errors == 'replace':
+ buffer.append('?')
+ elif errors == 'strict':
+ raise UnicodeError, "cannot map \\u%04x to EUC-KR" % ord(c)
return (''.join(buffer), len(data))
@@ -96,25 +76,11 @@
c = data[p:p+2]
p += 2
if len(c) == 2:
- if decmap_hangul.has_key(c):
- buffer.append(decmap_hangul[c])
+ if ksx1001decmap.has_key(c):
+ buffer.append(ksx1001decmap[c])
continue
elif self.uhc_decmap.has_key(c):
buffer.append(self.uhc_decmap[c])
- continue
-
- if not decmap_misc:
- from korean.mappings import ksc5601_misc
- decmap_misc = ksc5601_misc.decoding_map
- if decmap_misc.has_key(c):
- buffer.append(decmap_misc[c])
- continue
-
- if not decmap_ideo:
- from korean.mappings import ksc5601_ideograph
- decmap_ideo = ksc5601_ideograph.decoding_map
- if decmap_ideo.has_key(c):
- buffer.append(decmap_ideo[c])
continue
if errors == 'replace':
1.2 +43 -20 KoreanCodecs-Pure/korean/johab.py
Index: johab.py
===================================================================
RCS file: /cvsroot/koco/KoreanCodecs-Pure/korean/johab.py,v
retrieving revision 1.1
retrieving revision 1.2
diff -u -r1.1 -r1.2
--- johab.py 23 Jul 2003 19:09:52 -0000 1.1
+++ johab.py 23 Jul 2003 20:31:43 -0000 1.2
@@ -24,11 +24,11 @@
# IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
#
-# $Id: johab.py,v 1.1 2003/07/23 19:09:52 perky Exp $
+# $Id: johab.py,v 1.2 2003/07/23 20:31:43 perky Exp $
#
import codecs
-
+from korean.mappings.ksx1001 import *
from korean.hangul import Jaeum, Moeum, ishangul, split, join
encmap, decmap = {}, {}
@@ -89,17 +89,26 @@
)
code = 0x8000 | (cho<<10) | (jung<<5) | jong
buffer.append(chr(code>>8) + chr(code&0xFF))
- else:
- if not encmap:
- from korean.mappings import johab_ideograph
- encmap = johab_ideograph.encoding_map
-
- if encmap.has_key(c):
- buffer.append(encmap[c])
- elif errors == 'replace':
- buffer.append('\x84\x41')
- elif errors == 'strict':
- raise UnicodeError, "cannot map \\u%04x to JOHAB" % ord(c)
+ elif ksx1001encmap.has_key(c):
+ c1, c2 = map(ord, ksx1001encmap[c])
+ if c1 < 0xca:
+ c1 = c1 + 0x111
+ else:
+ c1 = c1 + 0xf6
+ if c1 & 1:
+ c2 = c2 - 0x43
+ else:
+ c2 = c2 - 0xa1
+ c1 = c1 >> 1
+ if c2 < 0x4e:
+ c2 += 0x31
+ else:
+ c2 += 0x43
+ buffer.append(chr(c1) + chr(c2))
+ elif errors == 'replace':
+ buffer.append('\x84\x41')
+ elif errors == 'strict':
+ raise UnicodeError, "cannot map \\u%04x to JOHAB" % ord(c)
return (''.join(buffer), len(data))
@@ -135,14 +144,26 @@
johab2uni_jongsung[jong]
]) )
continue
-
- if not decmap:
- from korean.mappings import johab_ideograph
- decmap = johab_ideograph.decoding_map
- if decmap.has_key(c):
- buffer.append(decmap[c])
- continue
+ c1, c2 = ord(c[0]), ord(c[1])
+ if ((0x31 <= c2 <= 0x7e or 0x91 <= c2 <= 0xfe)
+ and not (c1 == 0xda and (0xa1 <= c2 <= 0xd3))):
+ if c1 < 0xe0:
+ t1 = 2 * (c1 - 0xd9)
+ else:
+ t1 = 2 * c1 - 0x197
+ if c2 < 0x91:
+ t2 = c2 - 0x31
+ else:
+ t2 = c2 - 0x43
+ if t2 < 0x5e:
+ ch = chr(t1 + 0xa1) + chr(t2 + 0xa1)
+ else:
+ ch = chr(t1 + 0xa2) + chr(t2 + 0x43)
+
+ if ksx1001decmap.has_key(ch):
+ buffer.append(ksx1001decmap[ch])
+ continue
if errors == 'replace':
buffer.append(u'\uFFFD') # REPLACEMENT CHARACTER
@@ -208,3 +229,5 @@
def getregentry():
return (Codec().encode,Codec().decode,StreamReader,StreamWriter)
+
+# ex: ts=8 sts=4 et sw=4
|
