Skip to content

gh-103583: Isolate CJK codec modules #103869

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
erlend-aasland merged 7 commits into from
Apr 27, 2023
Merged

gh-103583: Isolate CJK codec modules #103869

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
cb2c9e7
Pass codec iso. config to mbcodec API handlers
erlend-aasland Apr 26, 2023
409bf98
Add cjk module state pointer to MultibyteCodec struct
erlend-aasland Apr 26, 2023
fd6a2a0
Make it possible to specify cjk module specific state
erlend-aasland Apr 26, 2023
eb44ae6
PoC: put big5 codec in cjk module state
erlend-aasland Apr 26, 2023
f6ed5df
PoC: iso2022 codecs
erlend-aasland Apr 26, 2023
ef983c4
Add NEWS
erlend-aasland Apr 26, 2023
dec79a7
Merge branch 'main' into isolate-cjk-alt2
erlend-aasland Apr 26, 2023
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
PoC: put big5 codec in cjk module state
  • Loading branch information
@erlend-aasland
erlend-aasland committed Apr 26, 2023
commit eb44ae6caad691947471bc9e1ce269be5b02fd2e
18 changes: 9 additions & 9 deletions Modules/cjkcodecs/_codecs_hk.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,23 +6,23 @@

#define USING_IMPORTED_MAPS

#define CJK_MOD_SPECIFIC_STATE \
const encode_map *big5_encmap; \
const decode_map *big5_decmap;

#include "cjkcodecs.h"
#include "mappings_hk.h"

/*
* BIG5HKSCS codec
*/

static const encode_map *big5_encmap = NULL;
static const decode_map *big5_decmap = NULL;

CODEC_INIT(big5hkscs)
{
static int initialized = 0;

if (!initialized && IMPORT_MAP(tw, big5, &big5_encmap, &big5_decmap))
cjkcodecs_module_state *st = codec->modstate;
if (IMPORT_MAP(tw, big5, &st->big5_encmap, &st->big5_decmap)) {
return -1;
initialized = 1;
}
return 0;
}

Expand Down Expand Up @@ -81,7 +81,7 @@ ENCODER(big5hkscs)
}
}
}
else if (TRYMAP_ENC(big5, code, c))
else if (TRYMAP_ENC_ST(big5, code, c))
;
else
return 1;
Expand Down Expand Up @@ -122,7 +122,7 @@ DECODER(big5hkscs)
REQUIRE_INBUF(2);

if (0xc6 > c || c > 0xc8 || (c < 0xc7 && INBYTE2 < 0xa1)) {
if (TRYMAP_DEC(big5, decoded, c, INBYTE2)) {
if (TRYMAP_DEC_ST(big5, decoded, c, INBYTE2)) {
OUTCHAR(decoded);
NEXT_IN(2);
continue;
Expand Down
5 changes: 5 additions & 0 deletions Modules/cjkcodecs/cjkcodecs.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -211,6 +211,9 @@ get_module_state(PyObject *mod)
(m)->bottom]) != NOCHAR)
#define TRYMAP_ENC(charset, assi, uni) \
_TRYMAP_ENC(&charset##_encmap[(uni) >> 8], assi, (uni) & 0xff)
#define TRYMAP_ENC_ST(charset, assi, uni) \
_TRYMAP_ENC(&(codec->modstate->charset##_encmap)[(uni) >> 8], \
assi, (uni) & 0xff)

#define _TRYMAP_DEC(m, assi, val) \
((m)->map != NULL && \
Expand All @@ -219,6 +222,8 @@ get_module_state(PyObject *mod)
((assi) = (m)->map[(val) - (m)->bottom]) != UNIINV)
#define TRYMAP_DEC(charset, assi, c1, c2) \
_TRYMAP_DEC(&charset##_decmap[c1], assi, c2)
#define TRYMAP_DEC_ST(charset, assi, c1, c2) \
_TRYMAP_DEC(&(codec->modstate->charset##_decmap)[c1], assi, c2)

#define BEGIN_MAPPINGS_LIST(NUM) \
static int \
Expand Down
3 changes: 0 additions & 3 deletions Tools/c-analyzer/cpython/globals-to-fix.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -485,9 +485,6 @@ Modules/_decimal/_decimal.c - _py_float_abs -
Modules/_decimal/_decimal.c - _py_long_bit_length -
Modules/_decimal/_decimal.c - _py_float_as_integer_ratio -
Modules/_elementtree.c - expat_capi -
Modules/cjkcodecs/_codecs_hk.c - big5_encmap -
Modules/cjkcodecs/_codecs_hk.c - big5_decmap -
Modules/cjkcodecs/_codecs_hk.c big5hkscs_codec_init initialized -
Modules/cjkcodecs/_codecs_iso2022.c - cp949_encmap -
Modules/cjkcodecs/_codecs_iso2022.c - ksx1001_decmap -
Modules/cjkcodecs/_codecs_iso2022.c - jisxcommon_encmap -
Expand Down