[KoCo-CVS] [Commit] cjkcodecs/tools genmap_schinese.py genmap_tchinese.py genmap_zh_TW_codecs.py
Brought to you by:
perky
Menu
▾
▴
[KoCo-CVS] [Commit] cjkcodecs/tools genmap_schinese.py genmap_tchinese.py genmap_zh_TW_codecs.py
|
From: Hye-Shik C. <pe...@us...> - 2003-05-17 20:33:07
|
perky 03/05/17 13:33:06
Added: tools genmap_schinese.py genmap_tchinese.py
Removed: tools genmap_zh_TW_codecs.py
Log:
Add map generators for chinese.
Revision Changes Path
1.1 cjkcodecs/tools/genmap_schinese.py
Index: genmap_schinese.py
===================================================================
#
# genmap_schinese.py: Simplified Chinese Codecs Map Generator
#
# Copyright (C) 2003 Hye-Shik Chang <pe...@Fr...>.
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
# are met:
#
# 1. Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
#
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
# IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT,
# INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
# (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
# STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
# IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
#
# $Id: genmap_schinese.py,v 1.1 2003/05/17 20:33:06 perky Exp $
#
from genmap_support import *
GB2312_C1 = (0x21, 0x7e)
GB2312_C2 = (0x21, 0x7e)
GBKL1_C1 = (0x81, 0xa8)
GBKL1_C2 = (0x40, 0xfe)
GBKL2_C1 = (0xa9, 0xfe)
GBKL2_C2 = (0x40, 0xa0)
GB18030EXTP1_C1 = (0xa1, 0xa9)
GB18030EXTP1_C2 = (0x40, 0xfe)
GB18030EXTP2_C1 = (0xaa, 0xaf)
GB18030EXTP2_C2 = (0xa1, 0xfe)
GB18030EXTP3_C1 = (0xd7, 0xd7)
GB18030EXTP3_C2 = (0xfa, 0xfe)
GB18030EXTP4_C1 = (0xf8, 0xfd)
GB18030EXTP4_C2 = (0xa1, 0xfe)
GB18030EXTP5_C1 = (0xfe, 0xfe)
GB18030EXTP5_C2 = (0x50, 0xfe)
try:
gb2312map = open('GB2312.TXT')
except IOError:
print "=>> Please download mapping table from http://www.unicode." \
"org/Public/MAPPINGS/OBSOLETE/EASTASIA/GB/GB2312.TXT"
raise SystemExit
try:
cp936map = open('CP936.TXT')
except IOError:
print "=>> Please download mapping table from http://www.unicode." \
"org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP936.TXT"
raise SystemExit
try:
gb18030map = open('gb-18030-2000.xml')
except IOError:
print "=>> Please download mapping table from http://oss.software" \
".ibm.com/cvs/icu/~checkout~/charset/data/xml/gb-18030-2000.xml"
raise SystemExit
re_gb18030ass = re.compile('<a u="([A-F0-9]{4})" b="([0-9A-F ]+)"/>')
def parse_gb18030map(fo):
m, gbuni = {}, {}
for i in range(65536):
if i < 0xd800 or i > 0xdfff: # exclude unicode surrogate area
gbuni[i] = None
for uni, native in re_gb18030ass.findall(fo.read()):
uni = eval('0x'+uni)
native = [eval('0x'+u) for u in native.split()]
if len(native) <= 2:
del gbuni[uni]
if len(native) == 2: # we can decode algorithmically for 1 or 4 bytes
m.setdefault(native[0], {})
m[native[0]][native[1]] = uni
gbuni = gbuni.keys()
gbuni.sort()
return m, gbuni
print "Loading Mapping File..."
gb18030decmap, gb18030unilinear = parse_gb18030map(gb18030map)
datever, gbkdecmap = loadmap(cp936map)
gb2312_datever, gb2312decmap = loadmap(gb2312map)
difmap = {}
for c1, m in gbkdecmap.items():
for c2, code in m.items():
del gb18030decmap[c1][c2]
if not gb18030decmap[c1]:
del gb18030decmap[c1]
for c1, m in gb2312decmap.items():
for c2, code in m.items():
gbkc1, gbkc2 = c1 | 0x80, c2 | 0x80
if gbkdecmap[gbkc1][gbkc2] == code:
del gbkdecmap[gbkc1][gbkc2]
if not gbkdecmap[gbkc1]:
del gbkdecmap[gbkc1]
gb2312_gbkencmap, gb18030encmap = {}, {}
for c1, m in gbkdecmap.iteritems():
for c2, code in m.iteritems():
gb2312_gbkencmap.setdefault(code >> 8, {})
gb2312_gbkencmap[code >> 8][code & 0xff] = c1 << 8 | c2 # MSB set
for c1, m in gb2312decmap.iteritems():
for c2, code in m.iteritems():
gb2312_gbkencmap.setdefault(code >> 8, {})
gb2312_gbkencmap[code >> 8][code & 0xff] = c1 << 8 | c2 # MSB unset
for c1, m in gb18030decmap.iteritems():
for c2, code in m.iteritems():
gb18030encmap.setdefault(code >> 8, {})
gb18030encmap[code >> 8][code & 0xff] = c1 << 8 | c2
omap = open('map_gb2312.h', 'w')
printcopyright(omap)
print "Generating GB2312 decode map..."
codebunch = []
genmap_decode(codebunch, "gb2312", GB2312_C1, GB2312_C2, gb2312decmap)
print_decmap(omap, codebunch, "gb2312", gb2312decmap)
omap = open('map_gbkext.h', 'w')
printcopyright(omap)
print "Generating GBK decode map..."
codebunch = []
genmap_decode(codebunch, "gbkext", GBKL1_C1, GBKL1_C2, gbkdecmap)
genmap_decode(codebunch, "gbkext", GBKL2_C1, GBKL2_C2, gbkdecmap)
print_decmap(omap, codebunch, "gbkext", gbkdecmap)
omap = open('map_gbcommon.h', 'w')
printcopyright(omap)
print "Generating GB2312 && GBK encode map..."
codebunch =[]
genmap_encode(codebunch, "gbcommon", gb2312_gbkencmap)
print_encmap(omap, codebunch, "gbcommon", gb2312_gbkencmap)
omap = open('map_gb18030ext.h', 'w')
printcopyright(omap)
print "Generating GB18030 extension decode map..."
codebunch = []
for i in range(1, 6):
genmap_decode(codebunch, "gb18030ext", eval("GB18030EXTP%d_C1" % i),
eval("GB18030EXTP%d_C2" % i), gb18030decmap)
print_decmap(omap, codebunch, "gb18030ext", gb18030decmap)
print "Generating GB18030 extension encode map..."
codebunch =[]
genmap_encode(codebunch, "gb18030ext", gb18030encmap)
print_encmap(omap, codebunch, "gb18030ext", gb18030encmap)
omap = open('map_gb18030uni.h', 'w')
printcopyright(omap)
print "Generating GB18030 Unicode BMP Mapping Ranges..."
ranges = [[-1, -1, -1]]
gblinnum = 0
print >> omap, """
static const struct _gb18030_to_unibmp_ranges {
Py_UNICODE first, last;
DBCHAR base;
} gb18030_to_unibmp_ranges[] = {"""
for uni in gb18030unilinear:
if uni == ranges[-1][1] + 1:
ranges[-1][1] = uni
else:
ranges.append([uni, uni, gblinnum])
gblinnum += 1
for first, last, base in ranges[1:]:
print >> omap, " { 0x%04x, 0x%04x, 0x%04x }," % (first, last, base)
print >> omap, """\
{ 0x0000, 0x0000, 0x%04x },
};""" % (ranges[-1][2] + ranges[-1][1] - ranges[-1][0] + 1)
print "\nDone!"
# ex: ts=8 sts=4 et
1.1 cjkcodecs/tools/genmap_tchinese.py
Index: genmap_tchinese.py
===================================================================
#
# genmap_tchinese.py: Traditional Chinese Codecs Map Generator
#
# Copyright (C) 2003 Hye-Shik Chang <pe...@Fr...>.
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
# are met:
#
# 1. Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
#
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
# IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT,
# INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
# (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
# STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
# IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
#
# $Id: genmap_tchinese.py,v 1.1 2003/05/17 20:33:06 perky Exp $
#
from genmap_support import *
BIG5_C1 = (0xa1, 0xfe)
BIG5_C2 = (0x40, 0xfe)
# big5 map doesn't have 0xA3E1 (EURO SIGN), but we ignore
# that for forward compatiblilty. "Hey! we have the euro-big5!" :)
CP950_C1 = BIG5_C1
CP950_C2 = BIG5_C2
try:
big5map = open('BIG5.TXT')
except IOError:
print "=>> Please download mapping table from http://www.unicode." \
"org/Public/MAPPINGS/OBSOLETE/EASTASIA/OTHER/BIG5.TXT"
raise SystemExit
try:
cp950map = open('CP950.TXT')
except IOError:
print "=>> Please download mapping table from http://www.unicode." \
"org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP950.TXT"
raise SystemExit
print "Loading Mapping File..."
datever, cp950decmap = loadmap(cp950map)
big5_datever, big5decmap = loadmap(big5map)
big5encmap, cp950encmap = {}, {}
for c1, m in cp950decmap.items():
for c2, code in m.items():
if not (not big5decmap.has_key(c1) or not big5decmap[c1].has_key(c2)
or big5decmap[c1][c2] != code):
del cp950decmap[c1][c2]
else:
cp950encmap.setdefault(code >> 8, {})
cp950encmap[code >> 8][code & 0xff] = c1 << 8 | c2
for c1, m in big5decmap.items():
for c2, code in m.items():
big5encmap.setdefault(code >> 8, {})
big5encmap[code >> 8][code & 0xff] = c1 << 8 | c2
omap = open('map_big5.h', 'w')
printcopyright(omap)
print "Generating BIG5 decode map..."
codebunch = []
genmap_decode(codebunch, "big5", BIG5_C1, BIG5_C2, big5decmap)
print_decmap(omap, codebunch, "big5", big5decmap)
print "Generating BIG5 encode map..."
codebunch = []
genmap_encode(codebunch, "big5", big5encmap)
print_encmap(omap, codebunch, "big5", big5encmap)
omap = open('map_cp950ext.h', 'w')
printcopyright(omap)
print "Generating CP950 extension decode map..."
codebunch = []
genmap_decode(codebunch, "cp950ext", BIG5_C1, BIG5_C2, cp950decmap)
print_decmap(omap, codebunch, "cp950ext", cp950decmap)
print "Generating CP950 extension encode map..."
codebunch = []
genmap_encode(codebunch, "cp950ext", cp950encmap)
print_encmap(omap, codebunch, "cp950ext", cp950encmap)
print "\nDone!"
# ex: ts=8 sts=4 et
|
