fix: systematic byte fidelity for config strings and RV7 gaps
Resolves the 9 gap groups in docs/rewrite/notes/review-rv7-codex.md and
audits every string-typed config field against its consumers
(field -> consumers -> decode status table in final-Z9.md):
- Windows EnvMap keys use a port of Zig's nls.zig uppercase table
(upcaseW); Windows locale init follows Zig's chain (setlocale +
_putenv_s); malformed WTF-8 now fails process launch conversions like
Zig instead of substituting U+FFFD; kitty file paths convert WTF-8.
- bash --rcfile/--init-file, configured TERM and inherited GTK LANG
keep their original bytes.
- C API clipboard completion and ghostty_surface_binding_action take
bytes; complete_clipboard_request is byte-typed through the core.
- text:/csi:/esc: bindings, enquiry-response, input = path:, embedded
initial_input, search needles, titles, link regexes, clipboard
codepoint map, command palette text and GTK font/namespace values
decode the escape encoding before use.
Remaining by design: D-Bus a{ss} values and +new-window arguments are
UTF-8 by D-Bus type. C API key/preedit text follows separately.
Test Plan:
- cargo test --workspace
- just check-macos (both), just check-windows, just check-wasm
This commit is contained in:
1 parent
ffc91c31e4
commit
af094276f8
40 files changed
+986
-167
No files matched your search
@@ -5,7 +5,10 @@
|
||||
//! comments): `setlocale(LC_ALL, "")`, then with `LANG` unset, then
|
||||
//! `en_US.UTF-8` (exported as `LANG`). On Darwin (`target_vendor = "apple"`)
|
||||
//! `LANG`/`LANGUAGE` are additionally pre-populated from Cocoa when unset.
|
||||
//! Other targets (Windows, wasm) have no `setlocale` handling.
|
||||
//! Windows runs the same chain against the C runtime: `setlocale` (with
|
||||
//! Zig's literal `LC_ALL = 6`, which the UCRT rejects, so the chain proceeds
|
||||
//! exactly as it does in Zig) and `_putenv_s` for the `LANG` updates.
|
||||
//! wasm has no `setlocale` handling.
|
||||
|
||||
/// The locale Ghostty falls back to (and exports as `LANG`) when the
|
||||
/// environment's locale can't be set.
|
||||
@@ -14,14 +17,14 @@ pub const FALLBACK_LOCALE: &str = "en_US.UTF-8";
|
||||
/// Ensure that the locale is set (`ensureLocale`).
|
||||
/// Returns `Some("en_US.UTF-8")` if we had to fall back to it (and exported
|
||||
/// it as `LANG`), otherwise `None`.
|
||||
#[cfg(unix)]
|
||||
#[cfg(any(unix, windows))]
|
||||
pub fn ensure_locale() -> Option<String> {
|
||||
posix::ensure_locale()
|
||||
}
|
||||
|
||||
/// Ensure that the locale is set: nothing to do on targets without libc
|
||||
/// locales (Windows, wasm).
|
||||
#[cfg(not(unix))]
|
||||
/// Ensure that the locale is set: nothing to do on targets without a C
|
||||
/// runtime locale (wasm).
|
||||
#[cfg(not(any(unix, windows)))]
|
||||
pub fn ensure_locale() -> Option<String> {
|
||||
None
|
||||
}
|
||||
@@ -53,15 +56,52 @@ pub fn preferred_language_value<S: AsRef<str>>(preferred: &[S]) -> Option<String
|
||||
(!out.is_empty()).then_some(out)
|
||||
}
|
||||
|
||||
#[cfg(unix)]
|
||||
#[cfg(any(unix, windows))]
|
||||
#[allow(unsafe_code)]
|
||||
mod posix {
|
||||
#[cfg(windows)]
|
||||
use std::ffi::c_char;
|
||||
use std::ffi::{CStr, CString};
|
||||
|
||||
use super::FALLBACK_LOCALE;
|
||||
#[cfg(target_vendor = "apple")]
|
||||
use super::{format_lang, preferred_language_value};
|
||||
|
||||
/// Zig's `LC_ALL` constant (`os/locale.zig`, "from locale.h"). It is
|
||||
/// the value the Zig code passes on every platform, Windows included.
|
||||
#[cfg(windows)]
|
||||
const LC_ALL: i32 = 6;
|
||||
|
||||
#[cfg(windows)]
|
||||
unsafe extern "C" {
|
||||
fn setlocale(category: i32, locale: *const c_char) -> *mut c_char;
|
||||
fn _putenv_s(name: *const c_char, value: *const c_char) -> i32;
|
||||
}
|
||||
|
||||
#[cfg(windows)]
|
||||
fn setlocale_all(locale: &str) -> Option<String> {
|
||||
let c = CString::new(locale).ok()?;
|
||||
// SAFETY: valid NUL-terminated string; the C runtime returns a
|
||||
// pointer to a static string (or null) which we copy immediately.
|
||||
unsafe {
|
||||
let r = setlocale(LC_ALL, c.as_ptr());
|
||||
(!r.is_null()).then(|| CStr::from_ptr(r).to_string_lossy().into_owned())
|
||||
}
|
||||
}
|
||||
|
||||
/// Zig's Windows `setenv`/`unsetenv`: `_putenv_s` (an empty value
|
||||
/// removes the variable).
|
||||
#[cfg(windows)]
|
||||
fn putenv_s(key: &str, value: &str) {
|
||||
let (Ok(k), Ok(v)) = (CString::new(key), CString::new(value)) else {
|
||||
return;
|
||||
};
|
||||
// SAFETY: both pointers are valid NUL-terminated strings that the
|
||||
// C runtime copies; called during early startup like the Zig code.
|
||||
unsafe { _putenv_s(k.as_ptr(), v.as_ptr()) };
|
||||
}
|
||||
|
||||
#[cfg(unix)]
|
||||
fn setlocale_all(locale: &str) -> Option<String> {
|
||||
let c = CString::new(locale).ok()?;
|
||||
// SAFETY: valid NUL-terminated string; setlocale returns a pointer to
|
||||
@@ -72,12 +112,24 @@ mod posix {
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(windows)]
|
||||
fn set_env(key: &str, value: &str) {
|
||||
putenv_s(key, value);
|
||||
}
|
||||
|
||||
#[cfg(windows)]
|
||||
fn unset_env(key: &str) {
|
||||
putenv_s(key, "");
|
||||
}
|
||||
|
||||
#[cfg(unix)]
|
||||
fn set_env(key: &str, value: &str) {
|
||||
// SAFETY: called during early process startup (locale setup) before
|
||||
// other threads read the environment, mirroring the Zig code.
|
||||
unsafe { std::env::set_var(key, value) };
|
||||
}
|
||||
|
||||
#[cfg(unix)]
|
||||
fn unset_env(key: &str) {
|
||||
// SAFETY: see `set_env`.
|
||||
unsafe { std::env::remove_var(key) };
|
||||
|
||||
Reference in new issue
Block a user