518250da2c
Code pages 932 (Shift-JIS), 936 (GBK), 949 (Unified Hangul), and 950 (Big5), generated from the Unicode Consortium's Microsoft WINDOWS tables. Each page carries a three-state single-byte table (map / lead / undefined) plus sorted pair arrays binary-searched in both directions. Where several codes decode to one scalar (932's NEC/IBM overlap, 950's duplicated box-drawing rows), the encoder's winner is resolved from Microsoft's own bestfit WCTABLE — used only for duplicate resolution, never to import lossy best-fit mappings. The full decode direction was cross-validated against Python's cp932/936/949/950 codecs: zero mismatches over 60k+ pairs. Decode gains TruncatedPair and UndefinedPair failure modes; decode_lossy emits one U+FFFD per failed pair. Both feature configurations are clippy-clean and tested.
19 lines
417 B
TOML
19 lines
417 B
TOML
[package]
|
|
name = "msdos-encodings"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
description = "Bidirectional, emulator-grade conversion between MS-DOS code pages and Unicode"
|
|
license = "MIT"
|
|
|
|
[features]
|
|
default = ["dbcs"]
|
|
# The double-byte CJK pages (932/936/949/950). Their tables are large;
|
|
# disable default features for a lean single-byte-only build.
|
|
dbcs = []
|
|
|
|
[dependencies]
|
|
thiserror = "2"
|
|
|
|
[profile.release]
|
|
lto = true
|