mirror of
https://github.com/RustPython/RustPython.git
synced 2026-10-29 11:14:38 +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
88 lines
3.7 KiB
Python
Vendored
88 lines
3.7 KiB
Python
Vendored
# Codec encoding tests for ISO 2022 encodings.
|
|
|
|
from test import multibytecodec_support
|
|
import unittest
|
|
|
|
COMMON_CODEC_TESTS = (
|
|
# invalid bytes
|
|
(b'ab\xFFcd', 'replace', 'ab\uFFFDcd'),
|
|
(b'ab\x1Bdef', 'replace', 'ab\x1Bdef'),
|
|
(b'ab\x1B$def', 'replace', 'ab\uFFFD'),
|
|
)
|
|
|
|
class Test_ISO2022_JP(multibytecodec_support.TestBase, unittest.TestCase):
|
|
encoding = 'iso2022_jp'
|
|
tstring = multibytecodec_support.load_teststring('iso2022_jp')
|
|
codectests = COMMON_CODEC_TESTS + (
|
|
(b'ab\x1BNdef', 'replace', 'ab\x1BNdef'),
|
|
)
|
|
|
|
class Test_ISO2022_JP2(multibytecodec_support.TestBase, unittest.TestCase):
|
|
encoding = 'iso2022_jp_2'
|
|
tstring = multibytecodec_support.load_teststring('iso2022_jp')
|
|
codectests = COMMON_CODEC_TESTS + (
|
|
(b'ab\x1BNdef', 'replace', 'abdef'),
|
|
)
|
|
|
|
class Test_ISO2022_JP3(multibytecodec_support.TestBase, unittest.TestCase):
|
|
encoding = 'iso2022_jp_3'
|
|
tstring = multibytecodec_support.load_teststring('iso2022_jp')
|
|
codectests = COMMON_CODEC_TESTS + (
|
|
(b'ab\x1BNdef', 'replace', 'ab\x1BNdef'),
|
|
(b'\x1B$(O\x2E\x23\x1B(B', 'strict', '\u3402' ),
|
|
(b'\x1B$(O\x2E\x22\x1B(B', 'strict', '\U0002000B' ),
|
|
(b'\x1B$(O\x24\x77\x1B(B', 'strict', '\u304B\u309A'),
|
|
(b'\x1B$(P\x21\x22\x1B(B', 'strict', '\u4E02' ),
|
|
(b'\x1B$(P\x7E\x76\x1B(B', 'strict', '\U0002A6B2' ),
|
|
('\u3402', 'strict', b'\x1B$(O\x2E\x23\x1B(B'),
|
|
('\U0002000B', 'strict', b'\x1B$(O\x2E\x22\x1B(B'),
|
|
('\u304B\u309A', 'strict', b'\x1B$(O\x24\x77\x1B(B'),
|
|
('\u4E02', 'strict', b'\x1B$(P\x21\x22\x1B(B'),
|
|
('\U0002A6B2', 'strict', b'\x1B$(P\x7E\x76\x1B(B'),
|
|
(b'ab\x1B$(O\x2E\x21\x1B(Bdef', 'replace', 'ab\uFFFDdef'),
|
|
('ab\u4FF1def', 'replace', b'ab?def'),
|
|
)
|
|
xmlcharnametest = (
|
|
'\xAB\u211C\xBB = \u2329\u1234\u232A',
|
|
b'\x1B$(O\x29\x28\x1B(Bℜ\x1B$(O\x29\x32\x1B(B = ⟨ሴ⟩'
|
|
)
|
|
|
|
class Test_ISO2022_JP2004(multibytecodec_support.TestBase, unittest.TestCase):
|
|
encoding = 'iso2022_jp_2004'
|
|
tstring = multibytecodec_support.load_teststring('iso2022_jp')
|
|
codectests = COMMON_CODEC_TESTS + (
|
|
(b'ab\x1BNdef', 'replace', 'ab\x1BNdef'),
|
|
(b'\x1B$(Q\x2E\x23\x1B(B', 'strict', '\u3402' ),
|
|
(b'\x1B$(Q\x2E\x22\x1B(B', 'strict', '\U0002000B' ),
|
|
(b'\x1B$(Q\x24\x77\x1B(B', 'strict', '\u304B\u309A'),
|
|
(b'\x1B$(P\x21\x22\x1B(B', 'strict', '\u4E02' ),
|
|
(b'\x1B$(P\x7E\x76\x1B(B', 'strict', '\U0002A6B2' ),
|
|
('\u3402', 'strict', b'\x1B$(Q\x2E\x23\x1B(B'),
|
|
('\U0002000B', 'strict', b'\x1B$(Q\x2E\x22\x1B(B'),
|
|
('\u304B\u309A', 'strict', b'\x1B$(Q\x24\x77\x1B(B'),
|
|
('\u4E02', 'strict', b'\x1B$(P\x21\x22\x1B(B'),
|
|
('\U0002A6B2', 'strict', b'\x1B$(P\x7E\x76\x1B(B'),
|
|
(b'ab\x1B$(Q\x2E\x21\x1B(Bdef', 'replace', 'ab\u4FF1def'),
|
|
('ab\u4FF1def', 'replace', b'ab\x1B$(Q\x2E\x21\x1B(Bdef'),
|
|
)
|
|
xmlcharnametest = (
|
|
'\xAB\u211C\xBB = \u2329\u1234\u232A',
|
|
b'\x1B$(Q\x29\x28\x1B(Bℜ\x1B$(Q\x29\x32\x1B(B = ⟨ሴ⟩'
|
|
)
|
|
|
|
class Test_ISO2022_KR(multibytecodec_support.TestBase, unittest.TestCase):
|
|
encoding = 'iso2022_kr'
|
|
tstring = multibytecodec_support.load_teststring('iso2022_kr')
|
|
codectests = COMMON_CODEC_TESTS + (
|
|
(b'ab\x1BNdef', 'replace', 'ab\x1BNdef'),
|
|
)
|
|
|
|
# iso2022_kr.txt cannot be used to test "chunk coding": the escape
|
|
# sequence is only written on the first line
|
|
@unittest.skip('iso2022_kr.txt cannot be used to test "chunk coding"')
|
|
def test_chunkcoding(self):
|
|
pass
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|