8000 bpo-40328: Add tool for generating cjk mapping headers by corona10 · Pull Request #19602 · python/cpython · GitHub
[go: up one dir, main page]
Skip to content

bpo-40328: Add tool for generating cjk mapping headers #19602

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 14 commits into from
Apr 29, 2020
Merged

bpo-40328: Add tool for generating cjk mapping headers #19602

Changes from 1 commit
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
a681b40
bpo-40328: Add tool for generating mapping headers.
corona10 Apr 19, 2020
45c4242
bpo-40328: Remove
corona10 Apr 19, 2020
b74717e
bpo-40328: nit
corona10 Apr 20, 2020
9a54163
bpo-40328: nit
corona10 Apr 20, 2020
e028c00
bpo-40328: nit
corona10 Apr 20, 2020
2e8a7e3
bpo-40328: partial refactoring
corona10 Apr 20, 2020
e357a08
bpo-40328: Remove unused class
corona10 Apr 20, 2020
ce5414e
bpo-40328: Refactoring genmap_korean.py
corona10 Apr 20, 2020
87b146d
bpo-40328: Refactoring
corona10 Apr 20, 2020
4e008ee
bpo-40328: Remove unicode files
corona10 Apr 20, 2020
402c0e6
bpo-40328: Update
corona10 Apr 20, 2020
c7487f1
bpo-40328: Update README
corona10 Apr 20, 2020
a19a5e9
bpo-40328: Remove unnecessary file
corona10 Apr 20, 2020
60e6307
bpo-40328: fix
corona10 Apr 20, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
bpo-40328: Refactoring genmap_korean.py
  • Loading branch information
@corona10
corona10 committed Apr 20, 2020
commit ce5414ef07efd955abae593579e0d8551978f91f
96 changes: 50 additions & 46 deletions Modules/cjkcodecs/tools/genmap_korean.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,49 +8,53 @@

from genmap_support import *

KSX1001_C1 = (0x21, 0x7e)
KSX1001_C2 = (0x21, 0x7e)
UHCL1_C1 = (0x81, 0xa0)
UHCL1_C2 = (0x41, 0xfe)
UHCL2_C1 = (0xa1, 0xfe)
UHCL2_C2 = (0x41, 0xa0)

mapfile = open_mapping_file('data/CP949.TXT', 'http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP949.TXT')

print("Loading Mapping File...")
decmap = loadmap(mapfile)
uhcdecmap, ksx1001decmap = {}, {}
cp949encmap = {}
for c1, c2map in decmap.items():
for c2, code in c2map.items():
if c1 >= 0xa1 and c2 >= 0xa1:
ksx1001decmap.setdefault(c1&0x7f, {})
ksx1001decmap[c1&0x7f][c2&0x7f] = c2map[c2]
cp949encmap.setdefault(code >> 8, {})
cp949encmap[code >> 8][code & 0xFF] = (c1<<8 | c2) & 0x7f7f
else: # uhc
uhcdecmap.setdefault(c1, {})
uhcdecmap[c1][c2] = c2map[c2]
cp949encmap.setdefault(code >> 8, {}) # MSB set
cp949encmap[code >> 8][code & 0xFF] = (c1<<8 | c2)

with open('mappings_kr.h', 'w') as omap:
print_autogen(omap, os.path.basename(__file__))

print("Generating KS X 1001 decode map...")
filler = BufferedFiller()
genmap_decode(filler, "ksx1001", KSX1001_C1, KSX1001_C2, ksx1001decmap)
print_decmap(omap, filler, "ksx1001", ksx1001decmap)

print("Generating UHC decode map...")
filler = BufferedFiller()
genmap_decode(filler, "cp949ext", UHCL1_C1, UHCL1_C2, uhcdecmap)
genmap_decode(filler, "cp949ext", UHCL2_C1, UHCL2_C2, uhcdecmap)
print_decmap(omap, filler, "cp949ext", uhcdecmap)

print("Generating CP949 (includes KS X 1001) encode map...")
writer = EncodeMapWriter(omap, "cp949", cp949encmap)
writer.generate()


print("Done!")

KSX1001_C1 = (0x21, 0x7e)
KSX1001_C2 = (0x21, 0x7e)
UHCL1_C1 = (0x81, 0xa0)
UHCL1_C2 = (0x41, 0xfe)
UHCL2_C1 = (0xa1, 0xfe)
UHCL2_C2 = (0x41, 0xa0)


def main():
mapfile = open_mapping_file('data/CP949.TXT', 'http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP949.TXT')
print("Loading Mapping File...")
decmap = loadmap(mapfile)
uhcdecmap, ksx1001decmap, cp949encmap = {}, {}, {}
for c1, c2map in decmap.items():
for c2, code in c2map.items():
if c1 >= 0xa1 and c2 >= 0xa1:
ksx1001decmap.setdefault(c1 & 0x7f, {})
ksx1001decmap[c1 & 0x7f][c2 & 0x7f] = c2map[c2]
cp949encmap.setdefault(code >> 8, {})
cp949encmap[code >> 8][code & 0xFF] = (c1 << 8 | c2) & 0x7f7f
else:
# uhc
uhcdecmap.setdefault(c1, {})
uhcdecmap[c1][c2] = c2map[c2]
cp949encmap.setdefault(code >> 8, {}) # MSB set
cp949encmap[code >> 8][code & 0xFF] = (c1 << 8 | c2)

with open('mappings_kr.h', 'w') as omap:
print_autogen(omap, os.path.basename(__file__))

print("Generating KS X 1001 decode map...")
filler = BufferedFiller()
genmap_decode(filler, "ksx1001", KSX1001_C1, KSX1001_C2, ksx1001decmap)
print_decmap(omap, filler, "ksx1001", ksx1001decmap)

print("Generating UHC decode map...")
filler = BufferedFiller()
genmap_decode(filler, "cp949ext", UHCL1_C1, UHCL1_C2, uhcdecmap)
genmap_decode(filler, "cp949ext", UHCL2_C1, UHCL2_C2, uhcdecmap)
print_decmap(omap, filler, "cp949ext", uhcdecmap)

print("Generating CP949 (includes KS X 1001) encode map...")
writer = EncodeMapWriter(omap, "cp949", cp949encmap)
writer.generate()
print("Done!")


if __name__ == '__main__':
main()
0