mirror of
https://github.com/RustPython/RustPython.git
synced 2026-10-29 03:04:38 +08:00
Jeong, YunWon
322f294a21
* common: add PyPy CJK codec engines
Assisted-by: Codex:GPT-5
* common: mark CJK mapping tables generated
Assisted-by: Codex:GPT-5
* common: add reusable byte and text engines
Assisted-by: Codex:GPT-5
* common: record opt-in engine dependencies
Assisted-by: Codex:GPT-5
* stdlib: add `_multibytecodec` and the six `_codecs_*` modules
Wire the CJK codec engines in `rustpython-common` up to the VM. `_multibytecodec`
holds `MultibyteCodec`, `MultibyteIncrementalEncoder`, `MultibyteIncrementalDecoder`,
`MultibyteStreamReader` and `MultibyteStreamWriter`, the encode/decode drivers and
the error-handler protocol; each `_codecs_*` module exposes `getcodec` for the
encodings of its region.
`rustpython-stdlib` now enables the `cjk-codecs` feature of `rustpython-common`.
Add `cjk::decode_reset`, which the decoder `reset()` methods need. It differs from
building a fresh decoder state: ISO 2022 keeps its G1..G3 designations and the
escape-throughout flag, and resets only G0 and the shifted flag.
Drop the markers from the CJK codec tests and from the `test_codecs`, `test_io`,
`test_email`, `test_zipfile` and `test_traceback` cases that needed a CJK codec.
`test_codecs.BasicUnicodeTest.{test_basics,test_decoder_state}` stay expected
failures for an unrelated reason: `codecs.charmap_encode` rejects a `None` mapping.
Assisted-by: Claude Code:claude-opus-5
* stdlib: use the byte and text engines from `rustpython-common`
`binascii`, `_json` and `_socket`'s address converters now call the engines in
`rustpython-common` instead of carrying their own copies, and `rustpython-stdlib`
enables the `binascii`, `inet` and `json` features for them. That leaves
`base64` and `crc32fast` with no caller in `rustpython-stdlib`, and
`crates/stdlib/src/json/machinery.rs`, the last of the json_in_type-derived code,
goes away with its last caller.
The address converters change behaviour. `inet_aton` reads the lenient forms
(`127.1`, `16909060`, `0x7f.1`, `0177.0.0.1`), `inet_pton` rejects an octet with a
redundant leading zero and a group of five hex digits, `inet_ntop` writes the
IPv4-compatible form as `::c000:201`, and an address family with no converter
raises `EAFNOSUPPORT` instead of a bare `OSError`.
Give the JSON engine the closing-quote scan and the allocation-free `\uXXXX`
escape it needs to carry `_json`'s workload. Against the code it replaces,
`json.dumps` runs 2.3x faster with `ensure_ascii=True` and 1.7x without it, and
`json.loads` 1.2x.
`binascii.a2b_base64` now reports the messages `binascii.c` does: no
`error decoding base64: ` prefix, and the data-character count in parentheses.
Assisted-by: Claude Code:claude-opus-5
* test: enable the Windows cp932 codec case
The shared CJK engine now satisfies the Windows code-page adapter, so keeping this test marked as an expected failure turns its success into a CI failure.
Assisted-by: Codex:GPT-5
70 lines
3.0 KiB
Python
Vendored
70 lines
3.0 KiB
Python
Vendored
#
|
|
# test_codecencodings_kr.py
|
|
# Codec encoding tests for ROK encodings.
|
|
#
|
|
|
|
from test import multibytecodec_support
|
|
import unittest
|
|
|
|
class Test_CP949(multibytecodec_support.TestBase, unittest.TestCase):
|
|
encoding = 'cp949'
|
|
tstring = multibytecodec_support.load_teststring('cp949')
|
|
codectests = (
|
|
# invalid bytes
|
|
(b"abc\x80\x80\xc1\xc4", "strict", None),
|
|
(b"abc\xc8", "strict", None),
|
|
(b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\uc894"),
|
|
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\uc894\ufffd"),
|
|
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\uc894"),
|
|
)
|
|
|
|
class Test_EUCKR(multibytecodec_support.TestBase, unittest.TestCase):
|
|
encoding = 'euc_kr'
|
|
tstring = multibytecodec_support.load_teststring('euc_kr')
|
|
codectests = (
|
|
# invalid bytes
|
|
(b"abc\x80\x80\xc1\xc4", "strict", None),
|
|
(b"abc\xc8", "strict", None),
|
|
(b"abc\x80\x80\xc1\xc4", "replace", 'abc\ufffd\ufffd\uc894'),
|
|
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\uc894\ufffd"),
|
|
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\uc894"),
|
|
|
|
# composed make-up sequence errors
|
|
(b"\xa4\xd4", "strict", None),
|
|
(b"\xa4\xd4\xa4", "strict", None),
|
|
(b"\xa4\xd4\xa4\xb6", "strict", None),
|
|
(b"\xa4\xd4\xa4\xb6\xa4", "strict", None),
|
|
(b"\xa4\xd4\xa4\xb6\xa4\xd0", "strict", None),
|
|
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4", "strict", None),
|
|
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xd4", "strict", "\uc4d4"),
|
|
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xd4x", "strict", "\uc4d4x"),
|
|
(b"a\xa4\xd4\xa4\xb6\xa4", "replace", 'a\ufffd'),
|
|
(b"\xa4\xd4\xa3\xb6\xa4\xd0\xa4\xd4", "strict", None),
|
|
(b"\xa4\xd4\xa4\xb6\xa3\xd0\xa4\xd4", "strict", None),
|
|
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa3\xd4", "strict", None),
|
|
(b"\xa4\xd4\xa4\xff\xa4\xd0\xa4\xd4", "replace", '\ufffd\u6e21\ufffd\u3160\ufffd'),
|
|
(b"\xa4\xd4\xa4\xb6\xa4\xff\xa4\xd4", "replace", '\ufffd\u6e21\ub544\ufffd\ufffd'),
|
|
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xff", "replace", '\ufffd\u6e21\ub544\u572d\ufffd'),
|
|
(b"\xa4\xd4\xff\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xd4", "replace", '\ufffd\ufffd\ufffd\uc4d4'),
|
|
(b"\xc1\xc4", "strict", "\uc894"),
|
|
)
|
|
|
|
class Test_JOHAB(multibytecodec_support.TestBase, unittest.TestCase):
|
|
encoding = 'johab'
|
|
tstring = multibytecodec_support.load_teststring('johab')
|
|
codectests = (
|
|
# invalid bytes
|
|
(b"abc\x80\x80\xc1\xc4", "strict", None),
|
|
(b"abc\xc8", "strict", None),
|
|
(b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\ucd27"),
|
|
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\ucd27\ufffd"),
|
|
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\ucd27"),
|
|
(b"\xD8abc", "replace", "\uFFFDabc"),
|
|
(b"\xD8\xFFabc", "replace", "\uFFFD\uFFFDabc"),
|
|
(b"\x84bxy", "replace", "\uFFFDbxy"),
|
|
(b"\x8CBxy", "replace", "\uFFFDBxy"),
|
|
)
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|